Videos

Remote-sensing videos enable real-time observation of changes in target attributes, short-term activities, and scene evolution. They record motion, actions, interactions, and scene changes that cannot be captured by isolated images. Existing models primarily target single images or discrete temporal observations spanning a long time range. However, a unified evaluation setting for assessing vision-language models on continuous remote-sensing video understanding remains lacking. We introduce RSVideo-10K, a remote-sensing video dataset comprising 10,773 instances, 1.47 million frames, and 17.02 hours of footage, containing both unmanned aerial vehicles and satellite platforms. Its fixed evaluation benchmark, RSVideo-Bench, contains 2,731 test instances and evaluates two complementary aspects of remote-sensing video understanding: L1 Perception and L2 Reasoning, spanning seven capability groups and 17 tasks. Evaluations show that current vision-language models still struggle to recover small local evidence, track short-lived states, and use scene-constrained spatial relations. Based on this analysis, we further propose RSVideo, a reinforcement learning framework for small-target spatiotemporal focusing that selects question-relevant regions across frames and suppresses redundant background tokens. RSVideo achieves a maximum absolute improvement of 9.01% with InternVL3.5-14B and attains the highest accuracy of 40.63% with Qwen3.6-27B across 26 open-source vision-language backbones. Codes will be available at https://github.com/HongjieZhou0329/RSVideo.

Text-to-video (T2V) generation models have advanced rapidly, yet their ability to represent diverse cultural contexts remains underexplored. Existing benchmarks mainly focus on perceptual quality, physical plausibility, and text-video alignment, but do not directly assess whether generated videos capture culturally specific objects, actions, rituals, visible text, or audio cues. We introduce CultureVidBench, a comprehensive benchmark for evaluating cultural understanding in T2V generation. CultureVidBench contains 1,000 curated prompts covering 12 countries, 6 continents, 8 cultural regions, and 14 cultural aspects organized into three categories: material culture, social practice & performance, and ritual & ceremony. Designed specifically for video generation, CultureVidBench emphasizes dynamic and multimodal cultural representation, including social interactions, ritual procedure, and culturally appropriate visible text and audio. We evaluate seven representative T2V models through human user studies and MLLM-based automatic assessment across cultural faithfulness, multimodal cultural rendering, semantic adherence, and perceptual quality. Results show that although current models achieve strong semantic adherence and visual quality, they often fail to faithfully capture fine-grained cultural details, particularly for underrepresented regions, rituals, and multimodal cultural cues.

Long-video question answering requires identifying sparse yet critical evidence from videos containing thousands of frames under a constrained visual-token budget. Existing methods either select query-aware frames in a single pass or rely on timestamped text solely as retrieval guidance, leading to two key limitations. First, selected frames tend to cluster around local relevance peaks, and once the budget is exhausted, omitted evidence cannot be recovered. Second, textual and visual evidence remain weakly aligned. We propose GCR, a training-free framework that casts fixed-budget frame selection as a joint evidence curation problem. Ground converts timestamped text into temporal events, selects query-relevant real frame anchors, and renders each event text onto its temporally aligned frame. Cover supplements grounded events with direct visual anchors for complementary visual evidence and applies global maximal marginal relevance to preserve diverse context. Refine revisits omitted temporal regions and replaces the weakest revisable context frame with a real-frame medoid---but only when the medoid offers greater evidence value. GCR maintains a fixed number of chronologically ordered frames and requires no VLM training or architectural modification. Experiments on LongVideoBench and Video-MME, across three 7B backbones and frame budgets of 8, 32, and 64, demonstrate consistent improvements in long-video QA. With the 7B LLaVA-OV backbone and 32 frames, GCR achieves 64.25% and 62.15% on the two benchmarks, outperforming the strongest reproduced baselines by 2.54 and 1.93 percentage points, respectively.

In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details. Existing token-compression methods either employ heuristic, training-free compression with limited content adaptivity or introduce additional modules that require expensive alignment training, leaving the trade-off between efficiency and adaptivity unresolved. To alleviate this limitation, we propose CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens. CRAFT recursively merges tokens by decoupling parameter-free token selection from learnable token fusion: global similarity determines which tokens to merge, while a position-aware weighting module and a content-adaptive channel-wise gate learn how to fuse them. The whole compression pipeline is query-agnostic. Because every retained token is a linear combination of the original tokens, CRAFT preserves their true spatio-temporal coordinates and stays aligned with the pre-trained language model's input distribution. Experiments on multiple representative video benchmarks show that CRAFT consistently outperforms prior state-of-the-art token-compression methods. At about $8\times$ compression, it retains roughly $97\%$ of the backbone's average accuracy and shows significant efficiency improvement.

Video large language models (Video-LLMs) represent videos as dense sequences of visual tokens, whose length grows with the temporal and spatial extent of the input. These tokens often contain substantial redundancy arising from repeated visual patterns, leading to unnecessary computation in the subsequent language-model processing. Existing token compression methods, including pruning and merging, perform compression online during inference, repeatedly incurring additional computation for each input video and often relying on model-specific designs that limit their generality, we instead rethink this paradigm by shifting the costly compression process offline. We propose \textbf{ONCE}, a plug-in video token compression framework that introduces an offline-to-online paradigm: a frequency-aware global codebook is learned once in the visual feature space and reused for lightweight online compression through codebook lookup and aggregation, reducing repeated per-video computation and the need for model-specific compression designs. Extensive experiments across multiple video understanding benchmarks and against diverse compression baselines demonstrate that our approach achieves a strong accuracy-efficiency trade-off, maintaining competitive performance while achieving the lowest inference latency among compared methods.

Large language models have made text the default medium for human--AI interaction, buttext alone cannot express the full range of responses required by multimodal assistants,avatars, and embodied agents. While recent audio-video generative models can synthesizehigh-fidelity synchronized content, existing supervision is largely \emph{descriptive}:models are trained to render captions rather than to produce audio-visual responsescaused by external user interactions. We introduce \textbf{InteracVid}, \emph{the firstopen-source large-scale dataset that addresses this missing supervision}, so that everysample couples a preceding audio-visual context and an external stimulus with the realinteractive response that follows. We design a metadata-aware pipeline that extractsinteractive clips from long, noisy livestreams, yielding over \textbf{454K}context-query-response triplets from more than \textbf{59K} livestream videos andspanning conversation-centered, object-centric, procedural, embodied, and screen-basedscenarios. A ten-rater human study confirms that the extracted interactions are causal,natural, and temporally complete for both genuine and reconstructed queries. On aheld-out benchmark of \textbf{100} genuine live-chat queries, fine-tuning on InteracVidimproves both interaction planning and audio-video response generation, and anindependent human evaluation reproduces the system ranking and the conclusions obtainedwith our automatic judge. These results highlight interaction-structured data as acritical foundation for interactive multimodal generation.

Object-centric models often produce fragmented masks, boundary leakage, and incorrect region merging. We introduce Similarity-Shift Refinement (SSR), a training-free post-hoc method for improving object-centric masks with a frozen self-supervised Vision Transformer. SSR measures changes in pairwise patch similarity before and after self-attention value aggregation, retains positively strengthened relations, and constructs a sparse affinity graph. This graph propagates the initial soft slot assignments in a single refinement step, without retraining or modifying either model. Across natural-image, synthetic-video, and real-world-video benchmarks, SSR improves all-pixel Adjusted Rand Index in all 24 evaluated model-dataset combinations, with an average gain of 8.5 percentage points. Ablations show that value-space similarity shifts outperform query- and key-space variants as well as static Transformer affinities. However, texture-dense scenes may cause visually similar regions to be over-grouped. Overall, SSR provides a simple and transferable signal for training-free object-centric mask refinement.

Recent advances in large vision-language models (LVLMs) have enabled long-video understanding and analysis. However, processing the large number of frames in a video incurs substantial computational overhead. Existing methods reduce LVLM inference costs by scoring frame-query relevance before inference and selecting keyframes accordingly. Nevertheless, the distribution of relevant frames varies across queries, and these methods often need to score hundreds or thousands of frames. To address this limitation, we propose CSES, a training-free semantic keyframe selector that adaptively determines the numbers of frames to score and keyframes to select. CSES estimates the prominence of the frame-query relevance profile to guide active acquisition and adapt the temporal coverage of each input. It then formulates keyframe selection as a coverage problem that jointly accounts for semantic relevance, temporal redundancy, and visual redundancy. Active acquisition and keyframe selection terminate based on coverage saturation. The selection objective is monotone and submodular, enabling greedy optimization with a standard approximation guarantee. Experiments with four LVLMs on two benchmarks show that our method preserves accuracy while scoring $4$-$13\times$ fewer frames and selecting $18.4\%$-$20.5\%$ fewer input keyframes than existing baselines. CSES further achieves a $3.1$-$5.4\times$ speedup in frame selection over baselines.

Video Scene Procedure Planning (VSPP) supplies the target start-goal observations in advance, leaving open how a planner should act when the evidence must itself be retrieved. We introduce Cross-Video Scene Procedure Planning (CVSPP): given an answer-redacted start-goal query and K candidate videos, a model must retrieve the supporting video, localize the relevant window, and predict the action sequence. Two obstacles couple here. Same-task demonstrations share stages and windows, and an early hard selection passes the wrong scene chain to the planner. We build an eleven-source benchmark with typed negative roles, a fail-closed answer-leakage gate, and separate Evidence- and Plan-axis metrics. On its 14 source-horizon cells we adapt nine planner families against a majority-sequence floor. We then present One-Step Evidence Fusion (OSEF), which scores a query-conditioned cell-and-span lattice over all candidates and feeds the full soft lattice to the planner through a token-global adapter, cropping no window beforehand. OSEF ranks first on all six cells the benchmark certifies as method-rankable. On four matched same-task COIN and CrossTask cells it improves exact-video-and-plan success by 2.9-10.7 points over an enhanced hard-selection SOTA, and a component study assigns the largest single increment to the token-global interface. Five converted-source cells sit at or near the majority-sequence floor, the benchmark's remaining headroom. The supplementary package includes model constructors and evaluation code.

Authorship Verification (AV) represents an important subfield of digital text forensics and addresses the fundamental question of whether two texts were written by the same author. Although the field has made substantial progress over the past two decades, several important challenges remain unresolved or underexplored. For instance, most AV research has focused on written texts, despite the fact that language is expressed not only in written but also in spoken form, such as in videos. Moreover, existing AV studies have predominantly concentrated on English, while other languages, including German, have received comparatively little attention. To address these research gaps, we apply AV to spoken language in the form of transcripts of German-language videos and examine the effectiveness of established AV methods in verifying a speaker's identity across video pairs. Our experimental evaluation, based on a total of ten AV methods applied to three self-compiled corpora comprising 300 videos from 150 speakers, shows that the best performance (up to 88% accuracy and 90% AUC) is achieved by traditional AV approaches based on simple character- and token n-gram representations. In contrast, more modern transformer-based approaches perform significantly worse on all evaluated corpora. Our results therefore suggest that traditional methods in the field of AV remain both competitive and relevant.

Long-video understanding commonly compresses videos into a small set of frames or visual tokens for answer generation. Existing compact pipelines focus on retaining relevant visual content as explicit evidence. Yet making evidence available does not ensure that complementary cues across moments are integrated for answering. Our key idea is to organize selected frames into query-relevant cross-frame evidence before generation. We formulate this post-selection stage as a latent evidence interface and instantiate it with GenEvA ($\textbf{Gen}erative$ $Latent$ $\textbf{Ev}idence$ $\textbf{A}ggregation$), a distribution-guided latent evidence aggregation framework. Specifically, GenEvA uses a query-conditioned evidence distribution to focus aggregation on relevant frames, forming compact cross-frame latent evidence from their frame-specific information. Since cross-frame integration is not always needed, the same distribution determines whether to insert this latent complement. Across four benchmarks and two Video-MLLM backbones, GenEvA consistently improves matched-frame baselines. At 8 frames, it raises the four-benchmark LLaVA-Video average by $+5.2$ points and Qwen2.5-VL accuracy on LVBench by $+10.1$ points. These gains require only $0.11\%$--$0.40\%$ average video-token overhead; analyses further show task-aware allocation and benefits from Adaptive Evidence Invocation.

Large vision-language models (LVLMs) have achieved significant progress in video understanding, yet understanding long videos remains challenging due to the large number of visual tokens and limited context windows. Visual sampling provides a practical solution by selecting an informative subset of frames. However, existing methods typically either rely on relevance-aware sampling, leading to redundant frame selection and insufficient temporal coverage, or adopt a fixed sampling strategy regardless of query type. In this paper, we propose VisualRouter, a training-free and plug-and-play framework for query-grounded visual sampling. VisualRouter first classifies each query as either global or local and then applies the corresponding sampling strategy. For global queries, it employs a relevance-coverage hybrid strategy that preserves temporal coverage while retaining query-relevant visual evidence. For local queries, it adopts an event-aware frame selection strategy that performs event partitioning, segment-level frame allocation, and intra-event frame selection, jointly balancing relevance, coverage, and diversity with a limited number of input frames. Experiments show that VisualRouter consistently improves multiple LVLMs over uniform sampling, achieving gains of 5.2%, 7.7%, and 11.6% on Video-MME, LongVideoBench, and MLVU with Qwen2.5-VL-7B, and outperforming existing training-free visual sampling methods under the same setting.

Streaming video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches primarily manage the growing visual context according to token importance, temporal redundancy, or segment-level relevance, but rarely organize evidence around objects that persist and evolve over time. Thus, in this paper, we introduce ObjectStream, a training-free framework that treats latent objects as memory anchors for streaming video understanding. ObjectStream induces spatially coherent latent objects directly from frozen Video-LLM representations, links them across frames into persistent anchors, and maintains their histories under a bounded memory budget, without requiring external object detectors or segmentation models. Built on these anchors, ObjectStream preserves three complementary forms of evidence: persistent object histories, transient object changes, and recent visual context. This design enables existing Video Large Language Models (Video-LLMs) to reason over object identities, interactions, and state changes while leaving the underlying model unchanged. Extensive experiments on online streaming and offline long-video benchmarks demonstrate both effectiveness and efficiency. In online streaming evaluation, ObjectStream improves Qwen2.5-VL-7B by 10.0 points on OVO-Bench Real-Time Visual Perception, while reducing peak GPU mem-ory and TTFT by approximately 50%. On offline long-video benchmarks, it surpasses the full-token baseline while discarding 82.5% of visual tokens. These results highlight latent objects as a practical and effective organizing principle for compact streaming video memory.

Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt. Existing chain-of-thought approaches introduce intermediate plans or visual states, but these representations are typically non-executable or temporally sparse, limiting their ability to instantiate and control the complete spatiotemporal process. To address this limitation, we introduce VideoCoCo, an agentic dual-engine framework in which executable Blender code serves as a process-level chain of thought. Given a text prompt, a coding agent synthesizes a Blender program that explicitly specifies the scene and its temporal evolution. The executable simulation engine runs the program to produce a deterministic spatiotemporal draft, which is subsequently transformed into a photorealistic video by a generative video engine through draft-conditioned editing. This decomposition separates process-level reasoning from high-fidelity visual realization. To adapt the video editor to simulated drafts, we construct VideoCoCo-3K, a curated dataset of draft-instruction-target triplets. VideoCoCo improves the OmniWeaving baseline from 0.475 to 0.558 on PhyGenBench and from 52.18 to 77.88 on VBench-2.0, achieving the best average score on both benchmarks. These results demonstrate that executable code provides an effective, controllable, and inspectable intermediate representation for physically consistent video generation.

Accurately recovering the camera's calibration and metric poses for any unconstrained video would unlock large-scale training data for navigation and scene understanding. The dominant approaches to this problem are severely limited: Simultaneous Localization and Mapping (SLAM) is sensitive to initialization and transient failures due to its causal, incremental nature; it is often over-optimized for real-time operation and generally requires known camera calibration; while Structure-from-Motion (SfM) typically forgoes any image ordering, enabling optimal initialization and global optimization, but lacks robustness to visual symmetries and extreme motions. To bridge this gap, we introduce a system that combines the strong sequential constraints of SLAM with the flexibility and global optimization of offline SfM, enabling the metric reconstruction of arbitrary, long, uncalibrated videos. This system leverages recent advances in wide-baseline dense image matching, treats temporal ordering as a first-class citizen for reliable loop closure, and augments global optimization with metric monocular depth priors. As a result, thorough evaluations on diverse, challenging datasets that exhibit extreme motion and visual symmetries reveal that our approach is significantly more robust and accurate than both state-of-the-art SLAM and SfM, classical or learned, with given or unknown camera calibration. The code is publicly available at https://github.com/cvg/vidmap.

Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change. Latent action models can extract such priors, but reconstruction-trained codes may predict future observations without the structure required for joint generation with robot actions. Existing structured methods add temporal constraints but retain deterministic transition points, so residual errors in locally inferred transitions may propagate and compound under recursive composition. We introduce DLAM, a distributional latent-action model that represents each transition as a diagonal Gaussian. Reconstruction conditioned on the reference frame grounds the mean in observed visual change, while normalized composition and reversal over equal-gap triplets constrain both the mean and dimension-wise variance. Variance composition uses a lightweight shared-correlation coefficient to account for dependence between adjacent transitions that share an intermediate frame, whereas reversal negates the mean and preserves the variance. For downstream policy learning, we freeze the encoder and train a flow-matching policy to jointly generate mean transition sequences and robot actions. On held-out transitions, DLAM learns more temporally consistent latent dynamics than existing latent-action baselines and achieves stronger direct and cumulative reconstruction on held-out videos. Under the same controlled $π_0$ transfer protocol, it also improves policy performance on MetaWorld MT50, LIBERO, and real-world manipulation tasks. Controlled ablations show that normalized mean constraints account for most of the reconstruction gain, while learned variance and correlation-aware composition provide complementary improvements in downstream control.

Visual front-ends for robotic localization typically rely on point-based features such as Oriented FAST and Rotated BRIEF (ORB), which frequently fail in structured environments dominated by strong linear structures or textureless surfaces. While line-based Simultaneous Localization and Mapping (SLAM) systems mitigate this by utilizing line segments, conventional line extraction and description algorithms are computationally prohibitive for real-time edge robotics. To address this fundamental bottleneck, we propose HOME (Hough-space One-dimensional Matching of Extrema), an ultra-lightweight, training-free feature matching framework. HOME transforms images into Hough space, mapping global linear structures to stable local extrema, which serve as keypoints, thereby reformulating complex line matching into highly efficient one-dimensional point matching. The proposed 1D radial descriptor mathematically guarantees rotational and translational invariance without the overhead of explicit orientation estimation. As a proof of concept to validate the matching accuracy and efficiency of HOME, this paper focuses on homography estimation. Extensive evaluations demonstrate that HOME achieves robust registration in challenging scenarios where point-based methods fail, operating at a much faster speed than existing line-based methods. Extending this robust matching engine to full 3D pose estimation remains a highly promising future direction.

Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible. However, the density of relevant content decreases sharply as video sequence length increases, and exposing the model to more irrelevant content measurably reduces its accuracy. In this paper, we address the problem of maximizing query-relevant information in a frame subset selected at inference time, without training. FORGE (Frame Orthogonality in Relevance Geometry) is a model-agnostic method that induces a query-conditioned geometry on a pretrained multimodal embedding space, unifying relevance and diversity into a single objective. In this space, frames that cover independent query-relevant directions are far apart, and selecting the subset of maximum information captures diverse query-relevant content within the budget. Experiments on Video-MME and LongVideoBench at budgets of 16, 32, and 64 frames show that FORGE improves the unified keyframe selection score by 11.0-15.3 points over the strongest training-free baseline and up to doubles keyframe recall (0.415 vs. 0.204 at K=64 on Video-MME). The gains extend to question answering, where accuracy improves in every evaluated setting across eight open-source MLLMs spanning 4B to 32B parameters, by up to 8.7 points over uniform sampling and 5.2 points over the strongest baseline. Our findings suggest that aligning the embedding space with the query's high-dimensional structure is a promising direction for inference-time video understanding.

Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing methods rely on holistic representations, which are insufficient for capturing subtle interactions and fine-grained semantics. While recent prompt-based approaches introduce disentanglement, they lack explicit semantic guidance, and methods based solely on visual or structured cues remain coarse-grained. In this paper, we propose Knowledge-guided Disentanglement with Atomic Actions (KDA), which leverages fine-grained semantic knowledge to enhance action representations and enable more precise disentanglement. Specifically, we use Large Language Models (LLMs) to decompose action labels into atomic actions, providing explicit spatial-temporal semantics. A Knowledge Injection Module (KIM) first integrates atomic action knowledge into video features. Based on this enhanced representation, a Knowledge Disentanglement Module (KDM) further disentangles atomic action knowledge to produce more precise semantic guidance for action disentanglement. A Knowledge Disentanglement Loss (KD Loss) is introduced to encourage clearer disentanglement of knowledge components within KDM. Extensive experiments demonstrate that KDA improves feature discriminability and achieves state-of-the-art performance on multi-label action recognition benchmarks. Moreover, KIM and KDM can be readily integrated into other methods, demonstrating strong generality.

Deep learning models have achieved state-of-the-art performance in several computer vision tasks. However, they experience severe performance degradation when applied to real-world scenarios due to unanticipated distribution shifts. Test-Time Adaptation (TTA) attempts to solve this problem by using unlabeled data from the target domain to dynamically adapt to the test distribution at inference time, without access to the source data. However, TTA remains a challenging problem when adapting to continuous, temporally correlated data, such as videos, and in scenarios where the target domain contains severe domain shifts. For this reason, few works in the literature explore TTA for videos under such extreme conditions. To overcome these limitations, we propose Test-time Adaptation via Dual Distillation (TADD), an online adaptation framework that relies on a lightweight projection adapter to bridge the domain gap. The adapter module is pre-trained on the source domain and then adapted to the target using our proposed complementary losses: (i) zero-shot distillation, which encourages alignment with the domain-agnostic features from a pre-trained vision-language model (VLM); and (ii) target distillation, which retains the source domain discriminative knowledge encoded in the pre-trained adapter. Built upon a frozen CLIP backbone, our method introduces this lightweight projection adapter as the sole updatable component during inference. We conducted extensive evaluations on three well-known video action recognition benchmarks: UCF-HMDB, Daily-DA, and Sports-DA. Our experiments in the closed-set scenario demonstrate that our method consistently outperforms state-of-the-art TTA baselines. Notably, our TTA approach improves upon previous methods by up to +3.81% on UCF-HMDB, +2.63% on Daily-DA, and +3.03% on Sports-DA.

Video instance segmentation (VIS) requires models to detect, segment, and track object identities across frames, and most methods enforce temporal consistency through video-level supervision. Image-only training approaches, with MinVIS as one prominent example, have challenged this assumption, reaching competitive VIS without video training by treating frames as independent images and associating instances only at inference. The field has nonetheless moved toward ever more elaborate video-trained trackers, which depend on costly identity-consistent annotations, leaving the image-only direction under-explored. A diagnostic analysis identifies object query quality as the bottleneck: queries trained only to localize objects within a frame drift apart across frames and destabilize association. QueenVIS introduces a query-centric framework for strengthening image-trained VIS. During single-frame training, we enrich Mask2Former queries with two auxiliary heads: a feature-prediction loss that aligns each query with the pooled backbone descriptor of its instance, and a center-prediction loss that injects spatial structure. Both heads are discarded at inference, adding zero parameters, and temporal identity is maintained by a training-free query-propagation and memory-bank scheme. On YouTube-VIS and OVIS with a ResNet-50 backbone, QueenVIS improves over MinVIS, up to +6.7 AP on YouTube-VIS, +4.8 AP on OVIS, and +10.3 AP on the long-sequence YouTube-VIS split. QueenVIS achieves 50.9 AP on YouTube-VIS and remains competitive with recent video-supervised state-of-the-art, without processing a single video clip during training. Our findings suggest that strengthening the discriminative power and temporal stability of object queries is an important, underexplored axis for VIS. Code and models: https://github.com/ArianKheir/QueenVIS

We introduce CameraAnything, the first unified framework for camera controlled video editing that enables joint control of both intrinsic and extrinsic camera parameters. Existing approaches either rely on expensive 3D reconstruction to achieve full camera functionality or restrict editing to extrinsic parameter manipulation. Moreover, the coupled influence of intrinsic and extrinsic parameters on video appearance makes disentangled modeling particularly challenging. To address this, we adopt per-pixel Plücker ray injection alongside resolution-aware 3D RoPE in self-attention, building both camera conditioning and spatial positional encoding on the target latent to jointly control camera position, focal length, and native resolution editing without cropping or outpainting. To overcome the scarcity of paired training data, we further develop a scalable synthetic pipeline that constructs diverse dynamic scenes through structured multi-camera recording and generates synchronized videos with varied camera configurations. With a tailored orthogonal training strategy, CameraAnything enables expressive video reshooting with arbitrary viewpoint control, focal length adjustment, resolution adaptation, and multi-shot transitions within a single generation process, offering strong practical value for cinematic video editing and cross-platform content adaptation in video production.

Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality image-text pairs. However, the performance of VLMs often degrades in the video domain due to the essential need for temporal understanding and the scarcity of large-scale annotated video data. In this work, we focus on marine video understanding, which brings further challenges: first, it requires substantial domain expertise; and video VLMs usually struggle with localizing and interpreting critical information from marine videos, as the informative events are typically sparse, unpredictable, and unevenly distributed. To address these challenges, we carefully curate the first event-centric marine video understanding dataset called MarineEVT, which features 20K multi-task, video-level visual question-answering pairs spanning multiple dimensions of marine understanding and analysis. Meanwhile, based on MarineEVT, we decompose marine video understanding as an Event-centric Visual Tool-integrated Reasoning process EVT-R1 for short, where we leverage powerful visual tools to drive the model to localize and interpret critical information aligned with visual questions and human intent. To demonstrate its effectiveness, we compare EVT-R1 against 11 SOTA VLMs in different settings. EVT-R1 outperforms the top open-source and top commercial models by 5.22 and 11.09, respectively. MarineEVT and EVT-R1 lay the foundation for ecological discovery and marine education, fostering the development of VLMs capable of interpreting marine dynamics, reasoning about ecological interactions, and supporting sustainable ocean video understanding and analysis.

Test-time search lets small video diffusion models rival larger ones, but costs 2-10x more. All candidates are fully denoised, although most are discarded. Training-free caching makes each rollout 2-3x faster at near-lossless quality. Composition is safe only if lossy caching preserves verifier rankings. We present the first study of whether caching corrupts candidate ranking in video test-time search. On Wan2.1-T2V-1.3B with an adaptive caching wrapper (~2x per-candidate speedup), ImageReward scores seed-matched cached and full rollouts. Median per-prompt Spearman rank correlation is 0.905, with 72% top-1 agreement on the VBench suite. VBench-2.0 replicates this result on a harder suite. Recomputing the cached winner at full compute retains 90-94% of the full-search gain. Errors cluster among near-tied candidates, making corruption self-limiting. This finding leads to CachedSearch. It explores every candidate with aggressive caching, then re-generates only the winner at full compute. At N=8, it captures 94.7% of best-of-N's gain at 63% of the cost. Capture rises with width. At matched budget, it searches twice as wide for 38% more gain. The result holds from 1.3B-14B across six models and four families: Wan, LTX, CogVideoX, and Hunyuan. Wan2.1-14B matches the 1.3B model's fidelity. Mid-trajectory pruning multiplies the exploration saving to 3.11x at 88.6% capture. Ports to other model families require recalibrating a single parameter, showing that fidelity tracks architecture rather than parameter count. CachedSearch is training-free, verifier-agnostic, and orthogonal to the search algorithm, making it a plug-in multiplier for test-time scaling.

Detecting pollinators in field video is challenging: targets are small, visually similar, and observed against cluttered vegetation under blur and occlusion. We present a systematic empirical study of small-pollinator detection under a practical single-GPU compute budget. Using the BuzzSpot challenge dataset, we compare YOLO and RF-DETR models across input resolutions and evaluate sliced inference, class-gated fusion, size-routed ensembling, and post-hoc temporal processing. RF-DETR Large at 1344-pixel resolution achieved our best hidden-test result, reaching 0.405 mAP50:95 and outperforming the 1120-pixel model (0.379) and the best single-model YOLO26m baseline (0.366). The strongest gains came from adopting RF-DETR and increasing its input resolution, indicating that detector choice and input resolution were more effective levers than added inference-time complexity; the resolution gain was strongest for small objects and the rarer bumblebee and moth classes. Sliced-inference fusion, size-routed ensembling, and warm-started 1536-pixel continuation did not surpass this result, while post-hoc temporal processing did not improve the leaked diagnostic evaluation. Error analysis identified bee-hoverfly discrimination as the clearest remaining bottleneck: neighboring frames rarely supplied correctly classified hoverfly evidence for post-hoc correction. These findings motivate learned feature-level temporal aggregation before the final classification decision.

Recent advances in conventional and learning-based image coding have increased the demand for benchmark datasets that support fine-grained assessment of compressed image quality, particularly for learning-based image compression methods. This paper introduces Assessment of Image Coding 2026 (AIC2026), a large-scale dataset for high-fidelity image compression containing 70 source images selected from 2,787 candidates using semantic clustering, inter-metric disagreement among objective image quality assessment (IQA) methods, and manual inspection and refinement. The dataset covers a wide range of compression artifacts produced by eight conventional and four learning-based codecs across 17 coding configurations. Each source image is encoded using seven codecs. For each source-codec pair, decoded images are provided at 20 perceptually spaced distortion levels, corresponding approximately to 0.2-4.0 just-noticeable difference (JND) units using the ColorVideoVDP (CVVDP) metric for distortion estimation, yielding 9,618 distorted images. This fine-grained sampling enables analysis of rate-distortion behavior and objective metric evaluation for subtle quality differences across a wide range of compression artifacts. We report an extensive objective analysis using 24 conventional and 12 learning-based IQA methods. The results show substantial disagreement among current IQA methods for fine-grained quality differences, particularly for artifacts introduced by learning-based codecs. The complete dataset is publicly available at https://doi.org/10.18419/DARUS-6156.

Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In practice, trajectory-based control often requires users to draw accurate tracks for multiple objects, which scales poorly with scene complexity and becomes ambiguous under occlusion or overlap. To enable flexible yet precise multi-subject control, we introduce $\textbf{GraphVid}$, a graph-conditioned image-to-video generation model that enables interactive control through structured interaction graphs. We further curate $\textbf{GraphVid-Bench}$, a large-scale interaction-centric video dataset with structured relational annotations to enable training of interaction-aware video generation models. Despite using substantially less training data and fewer trainable parameters than prior motion-control methods, GraphVid delivers strong controllability and video quality. Compared with Motion-I2V, GraphVid reduces FID by up to 39.9% and FVD by 37.6%, while improving PSNR (9.87=>15.98) and SSIM (0.38=>0.61). Our results highlight the potential of structured semantic interfaces as a powerful paradigm for controllable video generation.

Understanding motion in video is a fundamental challenge for visual learning, as frame-to-frame change entangles two sources of dynamics: camera motion and object motion. This decomposition has remained underexplored in representation learning, partly because these factors are tightly coupled in natural videos and difficult to supervise separately. Yet recovering it is important for learning robust motion representations that separate meaningful object dynamics from camera-induced variation. We study whether such structured motion representations can be recovered from frozen features of a pretrained image vision transformer. We propose the Structured Dynamics Model (SDM), which explicitly separates the dominant source of temporal change from residual dynamics through future-feature prediction, rather than representing video change with a single entangled latent or with unstructured, spatially dense transition tokens. Training combines self-supervised learning on real video with weak supervision of scene dynamics on synthetic Kubric data. We evaluate SDM on ProbeMotion, a new evaluation suite spanning synthetic and real videos with camera motion, object motion, and combined dynamics. SDM outperforms backbone baselines using global CLS or average-pooled features, and compares favorably to strongly supervised representations such as VGGT on several probes, despite using substantially weaker supervision. These results suggest that pretrained image models can be readily repurposed into structured video-dynamics representations, providing a useful inductive bias for learning and analyzing latent video dynamics.

Open-world video anomaly detection (OWVAD) is expected to detect events that match a user-specified definition of abnormality. This requirement is stronger than generic anomaly localization: in the same video, changing the definition should change which temporal regions are scored as anomalous. We show that current OWVAD evaluation largely fails to isolate this conditional behavior. Standard VAD metrics and the dynamic-definition protocol can be dominated by target-versus-normal separation, allowing models to obtain strong scores while remaining nearly insensitive to the queried definition. We call this failure mode definition blindness. To explain why it is missed, we decompose dynamic-definition evaluation into target-versus-normal detection and target-versus-other-anomaly discrimination, and find that the former receives 7.2-26.8$\times$ more weight across common VAD benchmarks. Motivated by this diagnosis, we introduce three definition-conditioned evaluation metrics, DC-Disc, DC-Det$Δ$, and DC-Sel$Δ$, which progressively remove normal-frame, generic-anomaly, and multi-event selection shortcuts. Experiments on UCF-Crime, XD-Violence, and MSAD reveal that several strong VAD, OWVAD, and general vision language model baselines localize anomalous moments but exhibit weak definition following, often with near-zero definition-response margins. To validate that the failure is actionable, we further introduce DeCoS, a definition-contrastive scoring rule that subtracts anomaly evidence shared across definitions. DeCoS improves the strongest baseline by 7.3-16.0 AUROC points on DC-Disc and 15.5-28.3 points on DC-Det$Δ$. Overall, our results argue that OWVAD should be evaluated as definition-conditioned anomaly scoring, not as anomaly detection under different prompt labels.

Subject-to-video (S2V) generation has made substantial progress in preserving reference subjects across diverse categories, yet generic subject consistency remains insufficient for human-centric generation. A video may appear globally consistent while identity-critical human details still drift across frames, poses, and interactions. This issue becomes more severe in multi-person scenarios, where incorrect identity-role binding leads to subject confusion, attribute swapping, and excessive copying of reference-specific appearance cues. We propose Vera, a unified human-centric S2V framework for single- and multi-person generation. We first construct a million-pair identity-aligned human image-video dataset through person-level cross-clip retrieval, providing explicit identity correspondence and diverse references. Built on this dataset, Vera introduces two complementary designs. Identity-Focal Masked Supervision (IFMS) strengthens identity-aware learning with spatially focused supervision while reducing interference from irrelevant artifacts. Reference-Aware Layer-wise Attention (RALA) regulates how video tokens interact with reference identity cues in the DiT backbone, preserving stable identity anchors and enhancing layer-aware identity readout. Extensive experiments demonstrate that Vera improves human identity consistency, multi-person subject binding, and motion naturalness, while reducing identity confusion and excessive reference-image copying.

Text-guided video editing with diffusion models is impractically slow, hindered by costly multi-step sampling and inversion. We present OSVE, the first framework to successfully adapt one-step Text-to-Image (T2I) models for high-quality video editing, addressing the core challenges of inversion, editability, and temporal consistency. To bypass slow iterative inversion, we train a learnable encoder that predicts the initial noise for each frame in a single forward pass. This encoder is trained with a novel Structure-Aware Editing (SAE) loss on a curated dataset of structurally-aligned image pairs, teaching it to preserve the source video's geometry during edits. For temporal coherence, we introduce Unified-Frame Editing (UFE), a technique that concatenates frame latents to facilitate cross-frame attention in a single generation step. Furthermore, for long videos, a sliding-window strategy with an anchor frame maintains global consistency. Our extensive experiments demonstrate that OSVE achieves editing quality comparable or superior to state-of-the-art multi-step methods, while operating approximately 155--171 times faster. This breakthrough paves the way for practical, real-time video editing applications. Code is available at https://github.com/KU-VGI/OSVE.

Action Quality Assessment (AQA) aims to objectively evaluate performance quality from action videos. Most existing methods follow a ``one-by-one'' paradigm, training a separate model for each action type. This setting limits real-world deployment, as it requires prior action-type knowledge to select the corresponding model and suffers from poor generalization across diverse actions. To address these limitations, we study the challenging task of all-in-one AQA, which aims to assess heterogeneous actions within a single unified model. We propose a novel Mixture of Action Knowledge Experts (MoAKE) framework, designed to mitigate negative knowledge transfer caused by large semantic discrepancies among actions. MoAKE learns complementary experts that capture diverse action patterns within a shared semantic space and dynamically aggregates their knowledge to adapt the assessment to the input action. Each expert is tailored with segment-aware prototypes to handle varying temporal lengths, together with an Adaptive Intra- and Inter-Segment Relationship Modeling (AIISRM) module to model multi-granularity temporal dynamics. Furthermore, we establish comprehensive benchmarks for all-in-one as well as zero/few-shot AQA. Extensive experiments on three long-term datasets demonstrate that MoAKE significantly outperforms existing methods in the all-in-one setting, while also achieving consistent generalization on three short-term datasets under zero/few-shot evaluation. Code is available at https://github.com/XuHuangbiao/MoAKE.

Despite advances in Video Large Language Models (VLLMs) that have displayed promising outcomes in video understanding, the redundancy in the long-duration frames remains a hindrance to efficient reasoning. This paper introduces a training-free $\mathbf{P}$ersistence-Aware $\mathbf{C}$ompression and $\mathbf{A}$ggregation (PCA) method designed to preserve high-fidelity raw visual information before the encoding stage. PCA can be built on arbitrary VLLMs and consists of two modules: 1) A Dynamic Downsampling (DD) module that adaptively removes redundant frames by analyzing frame-wise similarity. 2) A Persistence-Aware Motion Enhancement (PAME) module that enriches each selected keyframe by aggregating the temporal context of its neighbors, ensuring that essential information is preserved even after aggressive frame reduction. Our approach substantially reduces the computation of long-context modeling, while enhancing the performance of the baseline model. Extensive experiments demonstrate that PCA consistently outperforms existing state-of-the-art approaches in both efficiency and accuracy, achieving a speedup of 1.8$\times$ to 2.5$\times$ compared to the baseline VLLM. The code is open-sourced at https://github.com/Heisenberg10110/PCA.

Long-video question answering requires a model to preserve visual evidence over time without repeatedly reprocessing the same video. A practical approach is to store the vision-language model's internal key-value (KV) cache for each video chunk and retrieve that state at query time. However, independently cached video chunks do not compose correctly: every chunk is prefilled from local rotary position zero, so naive concatenation collides temporal phases and removes the global order required for questions about what happened first, how often events occurred, or what changed across the video. This paper presents ChronoStitch, a training-free method for composing independently stored visual KV memories. The method first re-bases stored post-rotary keys onto a global three-axis multimodal RoPE coordinate system that preserves time, height, and width structure. We show why a one-dimensional scalar re-indexing is geometrically inconsistent for visual tokens because it turns spatial order within a frame into false temporal displacement. We then address the residual content gap left by positional repair: later chunks were originally encoded without attending to earlier chunks. ChronoStitch therefore selectively recomputes a small fraction of high-deviation later-chunk visual tokens while allowing them to attend over the composed cache. On Qwen2.5-VL-3B and the temporal split of TempCompass, ChronoStitch outperforms naive composition and position-only variants, improving event-ordering accuracy while running 3.3x faster than full joint re-prefilling.

Training video anomaly detectors is challenging due to the difficulty and cost of annotating diverse and rare abnormal events. Although recent large vision-language models enable training-free inference, existing approaches mostly rely on holistic inference over sampled video and may miss context-specific anomaly cues. In this paper, we present CSI-VAD, a training-free video anomaly detector that identifies abnormal events across diverse contexts. The key idea is to decompose each video into three distinct contexts (environment, objects, time) and perform context-specific inference in separate branches. Because we ground anomaly judgments solely in context-specific visual cues, we do not require predefined text prompts describing abnormal events or dataset-specific tuning. Experiments on UCF-Crime and UBnormal show that CSI-VAD consistently improves over the direct holistic baseline and achieves competitive performance against existing methods, showing the advantage of structured context decomposition for training-free video anomaly detection.

Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learning methods typically rely on shared adaptation spaces, which can induce severe cross-domain interference and catastrophic forgetting. We propose Distribution-Aware Expert Routing, a parameter-efficient framework for continual Video-MLLM adaptation over evolving domains. DAER maintains domain-isolated lightweight experts while keeping the pretrained Video-MLLM backbone frozen, thereby decoupling domain-specific adaptation from the general multimodal knowledge of the pretrained model. To enable fine-grained specialization, we introduce an intra-domain distribution-aware routing mechanism that matches each input to expert-level prototype reservoirs using MMD. To address the absence of task identities at inference time, we further propose an inter-domain routing mechanism that performs prototype matching in a discriminative subspace for robust domain identification. In addition, we introduce adaptive domain merging to improve parameter scalability and adopt a two-stage optimization strategy to stabilize expert specialization during continual learning. We evaluate DAER by curating a domain-incremental benchmark built from ten VidQA datasets covering diverse visual environments and reasoning demands. Experiments on two strong Video-MLLM backbones show that DAER consistently outperforms prior methods.

A single embedding space that covers text, images, video, and audio lets one index serve every query a user can pose. Embedding models built on vision-language backbones now lead text/image/video retrieval benchmarks but lack audio entirely, while audio-text retrieval is led by specialist systems that serve no other modality. We present the Fusion Embedding family, which adds audio to a frozen vision-language embedding base whose parameters are never updated: generation 1 (fusion-embedding-1) trains only a 16.4M-parameter connector between a frozen audio tower and the frozen base, and generation 2 (fusion-embedding-2) adds modality-gated deep adapters (44.2M parameters) whose branch never executes on text, image, or video inputs: their outputs are bit-for-bit those of the released base, verified after every training run. Because the base already binds text, images, and video, aligning audio to text alone makes audio-image retrieval emerge, with zero paired audio-visual training data. Alongside the recipe we map its design space with controlled negative results (rewriting training captions with an LLM, substituting a leaderboard-stronger audio tower, and widening the connector each reduce retrieval) and with training-protocol findings that we expect to transfer to any frozen decoder-LM embedding backbone. Both generations train in hours on a single GPU. Weights, code, and the evaluation harness are openly released.

Teaching videos are becoming a major medium for education, creating a growing need for scalable evaluation of their pedagogical quality. Existing automatic judges do not fully address this setting because teaching quality depends on multimodal evidence and should be evaluated with respect to the intended learner rather than as a universal property. We present EduPanel, a rubric-grounded, learner-conditioned LLM judge that decomposes evaluation across specialized agents to produce interpretable assessments for different aspects of teaching quality. Across expert studies, architecture ablations, and learner-persona analyses, EduPanel achieves reliability comparable to a median human expert. In expert evaluation, its feedback improves scoring accuracy (MAE 0.87 to 0.73), while experts remain able to detect unreliable outputs (AUC = 0.77) instead of accepting them blindly. These results suggest that EduPanel can serve as effective assistants for educational evaluation rather than replacements for human experts.

This paper explores a way to verify that audio has not been maliciously tampered in a specific context: short viral videos taken from news recordings. Rather than trying to detect artifacts of tampering (internal inconsistency), we focus on positively verifying a query against a trusted source such as a news recording (external consistency). We propose a method for cross verifying a short audio query against a reference recording from which it was taken. Our approach is to define two hypotheses (non-tampered vs tampered), calculate the most likely alignment between query and reference for each hypothesis, and then perform a likelihood ratio test on the two alignments. We show that this method is fast to compute, much more robust than using MFCC features with Euclidean distance, and has the key benefit of explainability. Our cross verification approach provides an alternative perspective and complementary tool to existing tampering detection methods.

Video understanding has become more and more important with the growth of Artificial Intelligence (AI) for video generation. Recently, Multimodal Large Language Model(M-LLM) has shown its capability in video understanding. Video summarization, a specific domain of video understanding, has proven its importance for efficient navigation and retrieval. Both video understanding and video summarization require a good selection of key frames in a video. Current video summarization methods heavily focus on the selected key frames and correlated segment captions. However, existing approaches overlook the perspective of treating the importance of the frames globally. We argue that using discrete selected frames for summarization will not only reduce the understanding coherence, but also lost important information in the video, as well as wasting the original capacity of the MLLMs. In this paper, we propose HAS, a Highlight-guided Attention Steering method for video summarization. We consider a challenging but practical setting where the video given to MLLMs for summarize should be continuous but with highlight guidance. HAS mainly consists of two parts: The first part is to find a continuous frame-level highlight distribution for the video globally. The second part is to apply the highlight distribution as an attention steering vector for the MLLM, targeting a better understanding of the video, and thus during the model inference time, putting more attention on the highlighted frames, while avoiding lost entire information on less highlighted frames through putting less attention instead of forgetting them. We evaluated HAS on a variety of benchmarks, and it has shown convincing performance in video summarization.

Detecting high-level semantic concepts like negation across modalities remains a challenge for current multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard vision-language models (VLMs). We demonstrate that pretrained embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal attention architecture that explicitly models inter-modal dependencies, achieving performance gains of up to +7.03% F1 over unimodal baselines. Our analysis reveals a key asymmetry: while textual negation often appears independently, visual negation is semantically dependent on linguistic context, a finding validated through our statistical analysis of 3,222 political video-text pairs automatically annotated via \textsc{Qwen2.5-VL}. By combining this analysis with self-supervised video representations (JEPA2), we advance the modeling of temporal negation. This work provides new methods and insights for learning robust, semantically-aligned representations in multimodal systems.

Modern video transformers typically ignore principles from primate vision and are rarely evaluated against neural data, limiting their biological interpretability. We introduce a sparse winner-takes-all token selection module that replaces dense self-attention to improve efficiency and approximate competitive routing observed in biological visual circuits. We further propose a neuro-inspired split-and-fuse video transformer which uses two complementary pathways: a high-resolution, low-frame-rate "what" stream and a low-resolution, high-frame-rate "where" stream, fused before classification. On Kinetics-400 and Something-Something V2, our best variant operates on the Pareto frontier of accuracy versus inference time among models of comparable scale and pretraining, and showing improved robustness to spatial perturbations. Using representational similarity analysis between model embeddings and time-resolved EEG recordings for the same video stimuli, our model attains a peak brain-model correlation of 0.18 (about 78% of the noise ceiling) and consistently outperforms strong video transformer baselines, suggesting that pathway specialization and sparse competition are useful inductive biases for efficient, brain-aligned video understanding.

Video multimodal large language models (MLLMs) can describe what happens in a video, but rarely identify when the supporting evidence occurs. We study generalist video temporal grounding, in which one model predicts a variable-cardinality set of evidence intervals across video lengths, domains, query forms, and viewpoints. Existing training strategies are misaligned with this set-valued task: long-video labels often rely on brittle one-pass annotation, while reinforcement-learning rewards either fail to distinguish non-overlapping predictions or require fragile segment matching. TimeLens2 treats temporal evidence as an interval set throughout supervision and optimization. TimeLens2-93K constructs reliable multi-span supervision through caption-derived proposals, independent localization, cross-agent consensus, semantic verification, and boundary refinement. Our temporal Wasserstein reward computes exact one-dimensional $W_1$ between uniform distributions over merged interval supports, providing dense, matching-free feedback under unequal cardinalities and equivalent fragmentation; temporal IoU complements it with precise-overlap feedback. Across seven benchmarks, TimeLens2-2B outperforms all size-matched baselines on every benchmark, while the 4B and 8B variants achieve state-of-the-art performance, surpassing open-source models with up to 397B parameters. The 2B, 4B, and 8B variants improve over their Qwen3-VL backbones by 14.2, 13.0, and 18.1 mIoU points, respectively.

Clickbait, where video titles and thumbnails exaggerate or misrepresent content, reduces user trust, wastes attention, and promotes misinformation on video-sharing platforms. Detecting Bengali clickbait remains challenging because publicly available multimodal datasets are limited. To address this gap, we introduce BanClickThumb, a curated dataset of 7,147 Bengali YouTube thumbnail-title pairs from five content domains, annotated by ten annotators with high agreement (Cohen's Kappa: 0.83-0.93). Using this dataset, we benchmark text-only, image-only, and multimodal approaches. Among unimodal models, BanClickTextFormer (XLM-RoBERTa) achieves 0.82 accuracy, while BanClickImageFormer (SwiftFormer) reaches 0.68. Our proposed multimodal model, BanClickFusionFormer, combines ViT and XLM-RoBERTa through intermediate fusion and achieves the best accuracy of 0.84. Error analysis shows that dense thumbnail text, figurative language, and culturally specific slang remain challenging. Our findings demonstrate the effectiveness of multimodal fusion for Bengali clickbait detection and provide a publicly available benchmark to support future research on low-resource multimodal content analysis.

Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time. Long-term identity preservation remains difficult when objects are small, densely distributed, and highly similar in appearance, as in bee swarm scenes. Existing trackers rely on re-identification (re-ID) models trained through single-instance assignment (instance-level querying). At inference, however, MOT requires global assignment between multiple trajectories and detections, corresponding to video-level querying. This training-inference mismatch can cause identity switches among visually similar objects. Existing approaches also often require substantial additional annotations to enhance appearance discrimination. We propose Video-Level Association re-ID (VLA-ReID), which reformulates re-ID as video-level association modeling. It uses aggregated historical trajectory features as queries and all current-frame detections as candidates, enabling direct optimization of their global association at each frame. In addition, Frame-Common Appearance Estimation (FCAE) estimates a common appearance direction from current-frame detections, while Common-Appearance Suppression (CAS) removes the corresponding component along this direction from trajectory and detection features. This amplifies discriminative differences among highly similar objects without additional annotations. Experiments on BEE24 show that VLA-ReID improves HOTA by 1.1, MOTA by 0.3, AssR by 2.6, AssA by 0.7, and IDF1 by 0.8 over state-of-the-art trackers, while reducing identity switches by 28%. These results demonstrate the effectiveness of video-level re-ID modeling for appearance-based association in MOT.

Digital twins enable robots to anticipate and adapt to physical interactions, but existing models struggle with elastoplastic articulated objects (EAOs) that exhibit nonlinear elasticity, plastic yielding, and damage accumulation. We present BoxTwin, an interactive digital twin framework that learns the full dynamics of EAOs from videos. Our pipeline reconstructs the scene, identifies a physics aware constitutive model for each EAO. Experiments on manual folding and dual arm manipulation of EAOs show that BoxTwin accurately tracks joint trajectories and reproduces post contact plastic behavior over long horizons. By integrating video driven reconstruction with elastoplastic damage modeling, BoxTwin advances digital twins toward predictive, adaptive control of deformable articulated objects in unstructured environments.

We present TellTale, a text-only approach to ambivalence/hesitancy (A/H) recognition in interview videos, evaluated on the BAH dataset as part of the 3rd A/H Video Recognition Challenge (11th ABAW Workshop, ECCV 2026). Although the dataset provides video, audio, facial crops, and transcripts, TellTale relies on the transcript alone and combines three probability streams. Two text encoders, multilingual-e5-large and mDeBERTa-v3-base, are fine-tuned with parameter-efficient LoRA adapters under a multiple-instance learning (MIL) objective, in which transcript chunks are scored individually and pooled with a smooth maximum so that only the video-level label is needed for supervision. The third stream requires no training: a quantized 14B instruction LLM is prompted, zero-shot, to rate each transcript for A/H. The three probabilities are combined by a weighted average and a single decision threshold, both selected on participant-grouped cross-validated predictions. On the organizer-scored private test set of 152 videos from unseen participants, TellTale achieves a Macro-F1 of 0.7364 and an average precision of 0.7940, compared with 0.2827 Macro-F1 for the official vision-based baseline.

Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recent agentic methods frame this task as multi-turn exploration with a single crop_video(start, end) action, which supports coarse-to-fine narrowing but provides no primitive for fine-to-coarse backtracking. As a result, these agents typically converge prematurely and cannot recover from an early mistake. We propose VideoTreeSearch (VTS), a framework that casts grounded LVQA as iterative self-correcting search over an adaptive temporal tree. VTS constructs a non-uniform tree from visual scene boundaries so that each node corresponds to a semantically coherent segment, and trains an agent to navigate the tree through four discrete operations: zoom_in, zoom_out, shift, and answer. These operations expose backtracking and recovery as explicit, learnable primitives rather than implicit behaviors. To train this navigation, we introduce a trajectory synthesis pipeline that produces multi-step paths through the tree, including deliberate detours into incorrect branches followed by recovery. We use these trajectories for supervised fine-tuning, followed by reinforcement learning with grounding and answer-accuracy rewards. On three Grounded LVQA benchmarks (CG-Bench, Haystack-LVBench, Haystack-Ego4D), VTS outperforms the strongest prior agentic methods by +12.5 mIoU on CG-Bench and +7.4 T-F1 on Haystack-Ego4D. The learned policy also transfers to general long-video QA, surpassing all prior agentic baselines on Video-MME, MLVU, and LVBench by up to +7.1 accuracy points. Ablations confirm that self-correcting hierarchical search is the central mechanism behind these gains: removing either adaptive descent or explicit backtracking substantially degrades performance. Code is available at https://github.com/CeeZh/VTS.

We present Audio-Visual Flamingo (AV-Flamingo), a fully open state-of-the-art audio-visual large language model (AV-LLM) for joint understanding and reasoning over audio, images, and long-form videos. Unlike prior AV-LLMs that primarily focus on short clips, AV-Flamingo is designed for understanding and reasoning over long and complex real-world (audio-visual) videos. To support this, we make three key contributions: (i) Audio-Visual-Skills, a large-scale collection of real-world videos with ~7M caption and question-answer training instances designed to emphasize temporal, compositional, and cross-modal audio-visual reasoning; (ii) a novel three-stage curriculum that progressively trains the model from short-range perception to long-horizon multi-event reasoning; and (iii) Temporal Audio-Visual Interleaved Chain-of-Thought, a reasoning framework that explicitly grounds intermediate reasoning steps to timestamps in long audio-visual streams, improving temporal alignment and interpretability. Extensive experiments across 15+ audio-visual, omni-modal, audio, and vision benchmarks show that AV-Flamingo outperforms similarly sized open models by clear margins and remains highly competitive with, and in some cases surpasses, much larger open-weight and closed models, particularly on long and complex real-world audio-visual understanding and reasoning tasks. Beyond benchmark performance, AV-Flamingo exhibits strong real-world utility and transfers well to unseen tasks, highlighting its robustness and generalization ability.

Video Large Language Models (Video LLMs) have made significant advancements in various video understanding tasks. However, long-video scenarios remain challenging due to the tension between limited visual token budgets and the need to capture multiple key events. Existing approaches typically process long videos in two stages, i.e., i) select keyframes and ii) perform detailed perception, which exhibit limitations: they lack a modular mechanism for adaptive capacity allocation and self-correction, resulting in unreliable modeling. To tackle these challenges, we propose MoD-VLLM, a novel Modularized Dynamic-Granularity Video LLM framework for multi-event long video understanding, which unifies temporal grounding and semantic understanding iteratively and self-reflectively. Specifically, we propose a Positive-Negative Video Segments Grounding module and a Modularized Dynamic-Granularity Reflection module, which form a closed loop to progressively localize the question-related video segments. The grounding module instructs a Video LLM to distinguish relevant from irrelevant video segments based on the video question. The reflection module employs a modularized scheduler that dynamically selects fine-grained encoding for relevant positive segments to capture detailed perception and coarse-grained encoding for negative segments to maintain global context. We further propose a dynamic-granularity reinforcement learning strategy, allowing MoD-VLLM to learn optimal grounding policies and dynamic granularity visual representation jointly. Moreover, we propose MEventBench, a challenging Multi-Event Long Video Benchmark for complex long video reasoning. Extensive experiments on several long video understanding benchmarks and our MEventBench demonstrate that MoD-VLLM significantly outperforms state-of-the-art baselines.

Understanding long videos with multimodal large language models (MLLMs) requires selecting a compact set of frames from thousands of candidates, yet identifying the right frames seemingly requires understanding the video first. We resolve this circular dependency with a simple observation: cross-modal attention at validation-selected extraction layers in MLLMs already provides query-relevant frame evidence without requiring autoregressive generation. We exploit this property to build DAFS (Dynamic Attention-based Budget-aware Frame Selection), a training-free frame selector. A lightweight MLLM selector, even with only 2B parameters, can extract frame-level evidence by converting selected-layer attention into relevance scores through query-conditioned aggregation. This enables cross-frame comparison without autoregressive decoding. To handle the selector's own context constraint, we formulate the joint allocation of candidate pool size and per-frame token budget as a discrete optimization problem solved by dynamic programming. Under a 32-frame budget, our selector improves over uniform sampling by up to 6.4 points on Video-MME and outperforms prior training-based selectors under matched frame budgets, while generalizing across selector and answerer backbones, and across tasks, without retraining.

Publicly shareable construction-video benchmarks remain scarce, especially for safety-critical hazards that are rare, dangerous to stage, and difficult to release. We study worker under suspended load, a relational hazard that depends on worker-load geometry and temporal persistence rather than object detection alone. We introduce SynthSite, a focused synthetic video benchmark of 55 clips spanning varied load configurations, viewpoints, clutter, occlusions, and surveillance conditions, together with a privacy-aware hybrid generation workflow that supports both publicly shareable benchmark creation and privacy-constrained synthetic video generation. We then ask whether worker appearance can be suppressed without undermining downstream hazard recognition. Under five whole-body privacy conditions, we evaluate worker and load retention, localization stability, and clip-level hazard recognition. We find that structure-preserving obfuscations retain substantially more downstream utility than appearance-smoothing baselines, and that preserving a raw visual reference alone does not guarantee the strongest agreement with human hazard labels. These findings suggest that privacy evaluation for construction safety analytics should assess not only appearance suppression, but also preservation of the geometric cues required for hazard reasoning. Our dataset and code are available at https://huggingface.co/datasets/govtech/SynthSite .

Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world applications. Despite this progress, current open-source models remain limited in several ways. They often struggle to generalize across diverse video types, making them effective only in specific domains. High computational demands further restrict their efficiency and scalability. Moreover, most models are only partially open, with key components such as training code, strategy, or datasets unavailable, which hinders reproducibility and slows community-driven development. To address these issues, we introduce VideoChat3, a fully open, efficient, and generalist video-centric MLLM. VideoChat3 advances video understanding through two complementary designs. For efficiency, we introduce Inflated 3D Vision Transformer (I3D-ViT) and Adaptive Frame Resolution for Streaming Video Perception, which enables efficient spatiotemporal representation and reduces the cost of processing video inputs during training and inference. For effectiveness, we develop a scalable video data synthesis pipeline that curates three diverse, high-quality training datasets: VideoChat3-Academic2M, VideoChat3-LV116K, and VideoChat3-OL617K, covering general, long-form, and streaming video scenarios, improving the model's generalization across domains. By integrating these designs, VideoChat3 achieves a rare balance of broad generalization and computational efficiency. Experiments across general, long-form, and streaming benchmarks demonstrate that VideoChat3 surpasses prior open-source models with equal or larger parameter counts with only 4B parameters and higher efficiency.

In this manuscript we release two datasets for visual sensing of tomato plants grown in commercial-like settings and acquired using a robot. The first is BUTom21 which consists of still images and manual annotations. The second is BUTom-ST21 which consists of video-based data and semi-automated annotations through AI-based methods, referred to as pseudo-labels. In both cases, we provide pixel-level labels for the ripeness of the fruit. The aim is to provide the research community a challenging set of real-world imagery to explore methods to sense and estimate the state of tomato plants and their fruit, which is an important horticultural crop. Importantly, the spatial-temporal dataset provides individual fruit count and ripeness information enabling researchers to push the boundaries of field-based phenotyping.

Recent visual place recognition (VPR) studies have increasingly relied on large-scale datasets to train more robust and discriminative models. Although this trend significantly improves recognition performance, it also introduces substantial storage and training costs, especially when new architectures or training strategies need to be repeatedly developed and evaluated. Dataset pruning (DP) provides a promising way to improve data efficiency by retaining only informative training data. However, conventional DP methods mainly follow the sample-wise classification paradigm, which overlooks the relation-dependent training nature of VPR, where supervision is typically formed by image pairs rather than independent images. To address this issue, we propose a place-wise dataset pruning framework tailored for VPR. Instead of pruning individual images, our method treats each place as the basic pruning unit and introduces two complementary novel metrics, i.e., intra-place diversity (IPD) and inter-place similarity (IPS), to evaluate the training value of each place. By jointly considering these two metrics, our method ranks all places and constructs a compact yet informative coreset, thereby allowing the pruned dataset to still support the training of robust and discriminative VPR models. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art DP baselines under different pruning ratios while reducing selection and training costs. Moreover, by pruning a merged dataset roughly 3.5$\times$ the size of GSV-Cities to a comparable scale, our coreset maintains highly competitive performance, achieving 94.5% R@1 on MSLS-val and 97.0% R@1 on Nordland with only NetVLAD. Codes will be made publicly available.

We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time. In each frame, SEMA attention applies a local window attention in parallel with a global averaging in a Mamba macro-architecture, which is called Mamba-like. Under certain rank conditions, we prove that the computationally cheaper split space-time attention is equivalent to full space-time attention. On benchmark K400 data sets, VideoSEMA out-performs heavier vision transformer and Mamba models. On benchmark SSv2 data, VideoSEMA leads in top-1 accuracy among models of similar parameter sizes. As image resolution scales up from standard $224^2$ to $1024^2$ on K400 and without fine-tuning, VideoSEMA degrades much more gracefully than VideoMamba in accuracy. It is promising to extend VideoSEMA to longer videos with a dilated/sparse temporal attention.

Visually impaired individuals (VIIs) encounter significant daily challenges due to limited access to visual information. Although Multimodal Large Language Models (MLLMs) have achieved impressive results on general vision and language tasks, their practical utility in real-world blind assistance still remains largely underexplored. To fill this gap, we introduce VIABench, a comprehensive video benchmark specifically designed to evaluate MLLMs in Visually Impaired Assistance scenarios using first-person videos recorded or shared by VIIs themselves. VIABench defines three core tasks, each targeting a distinct requirement in visual assistance. Proactive Reminder: Assesses the model's ability to interpret ongoing video content while proactively anticipating and verbally describing upcoming navigation-critical events; Visual Question Answering (VQA): Evaluates the model's capacity to answer user-posed questions about the environment or objects within the video; Vision-Guided Interaction: Tests context-aware reasoning to accomplish intentional interactions between user and environment. To ensure a robust and fair evaluation, we propose a rigorous benchmarking pipeline that supports both online (real-time) and offline settings. Our experiments demonstrate that current MLLMs still struggle to deliver comprehensive support for VIIs, especially in the Proactive Reminder task, which demands accurate anticipation and real-time responsiveness. We hope VIABench will drive future research toward developing customized MLLMs for real-world assistance, ultimately improving navigation and interaction experiences for visually impaired individuals. Code and data will be released at https://github.com/MCG-NJU/VIABench.

Music-driven dance generation aims to produce human motion that is both rhythmically synchronized and semantically consistent with music. While recent neural approaches have achieved impressive visual realism, they typically model motion as a continuous signal and neglect its compositional nature, making generated dances structurally incoherent and difficult to control. In this work, we introduce a structure-aware framework that models choreography as a sequence of atomic movements-semantically interpretable motion events that serve as the building blocks of dance. To construct this atomic movement vocabulary, we first segment large-scale dance data and cluster them into atomic movement groups. We then employ a large language model to semantically relabel and refine the clusters, yielding a set of interpretable and reusable atomic movements. Based on these atomic movement annotations, we design a two-stage generation framework that mirrors the human choreography process. In the atomic movement planning stage, the model predicts the type, duration, and timing of atomic movements conditioned on the input music, forming a symbolic dance allocation. In the completion stage, a transition-aware generator synthesizes smooth and stylistically coherent motion conditioned on the planned structure. Extensive experiments demonstrate that our method produces dances with significantly improved structural coherence, rhythmic alignment, and perceptual naturalness compared to existing baselines, while providing enhanced interpretability and controllable editing through explicit structural representation.

Detecting ambivalence and hesitancy (AH) in unconstrained video is challenging because the target signal is inherently ambiguous and expressed through subtle cross-modal incongruence rather than prototypical affect. We present CF-Net, a deep multimodal network submitted to the 3rd Edition of the AH Video Recognition Challenge (ABAW 11th, ECCV 2026), targeting the BAH dataset. CF-Net encodes visual, audio, and transcript streams with frozen SigLIP2, HuBERT, and DistilBERT backbones, normalises backbone features per speaker to reduce identity leakage, and fuses them via a ConflictFusion module that explicitly computes pairwise cross-modal incongruence. Training combines certainty-weighted focal loss, manifold mixup, and modality dropout; an auxiliary certainty-regression head uses ambiguity annotations to stabilise learning on genuinely borderline samples. CF-Net achieves a Macro F1 of 0.7155 on the BAH validation set and 0.7364 (AP = 0.7439) on the private challenge test set.

Humans can efficiently parse continuous sensory streams, from hours to years, scaffolding an internal world model that grounds spatial reasoning and prediction. To mimic this capacity, spatial supersensing challenges multimodal models to move beyond linguistic understanding toward true world modeling. However, their benchmark relies on synthetic long videos, formed by concatenating random short clips, and is mostly limited to household scenes, leaving real-world continuity and diversity underexplored. To address the gap, we introduce $\textbf{VSI-Super-Wild}$, a large-scale benchmark for evaluating spatial supersensing over long temporal horizons in diverse in-the-wild scenes. Notably, inspired by cognitive studies on how humans structure experience, we systematically probe the full triad of world state: the agent (observer), objects (scene items), and the environment (places and global layout). In total, VSI-Super-Wild contains $\textbf{6,980}$ human-verified question-answer pairs derived from $\textbf{442}$ real-world videos spanning 8 scene categories, including long-form recordings exceeding 4 hours. Results on VSI-Super-Wild expose a fundamental disconnect: despite advances in static image understanding, models consistently fail at tasks that require coherent world-state tracking over time. We characterize how performance degrades with world-state complexity and temporal horizon, and diagnose four failure modes: spatial collapse, semantic shortcuts, insufficient update, and instance confusion. This taxonomy reveals that models lack mechanisms to bind objects, agents, and environments into a unified spatial world model, a fundamental gap that defines the path forward for spatial supersensing.