Video Representation Learning

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 87

May 21, 2026cs.CV

The TIME Machine: On The Power of Motion for Efficient Perception

Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of self-supervised models trained on next-frame prediction. While these factors have pushed the boundaries of what video models can do, they also introduce their own set of limitations. First, scaling video models can reach prohibitive costs, with recent models needing hundreds of years of video to be trained. Second, learning to predict the next frame (or embedding of the frame) naturally focuses on spatial information and as a result, video models still struggle with temporal understanding. In this paper we propose a novel approach that uses motion as a modality to alleviate both of these core issues. Given the motion in a video in the form of point tracks, we mask some of the tracks and use a masked autoencoder to reconstruct the missing tracks. This allows us to learn a representation in a self-supervised manner which we call TIME (Temporally-Informed Motion Embedding), and is focused on capturing temporal information. Also, as motion is inherently appearance-invariant, TIME needs far fewer examples to generalize well. As a result, without bells and whistles, on temporal tasks TIME performs on par with state-of-the-art models, using up to 4 orders of magnitude less training data. For general tasks, TIME can be used in combination with existing representations, and we observe that it leads to a significant improvement for V-JEPA 2, RVM and VideoMAE on standard benchmarks such as SSV2, EgoExo4D and Diving48. These results point to a new promising video paradigm for both more temporally-aware as well as more scalable models.

Mantas Skackauskas, Xinyue Hao, Laura Sevilla-Lara

School of Informatics University of Edinburgh

Representation Learning Video Representation Learning Motion Representation Learning Self-Supervised Visual Representation Learning Temporal Video Understanding

May 20, 2026cs.CV

Seeing Through Fog: Towards Fog-Invariant Action Recognition

Foggy conditions are commonly encountered in real-world applications; however, existing action recognition approaches typically assume favorable weather and high-quality video inputs. On foggy days, unpredictable visibility degradation and reduced contrast obstruct the extraction of semantic cues, posing significant challenges for current action recognition methods. In this paper, we mitigate the issues faced in action recognition under foggy conditions by employing two strategies. First, we present FogAct, the first benchmark dataset for foggy action recognition, consisting of paired clean and foggy videos captured with a stereo camera system. The dataset spans 10 scenes and 55 action categories, comprising nearly 10,000 video clips. Second, we propose FogNet, a two-stream CLIP model that discovers fog-invariant semantic information hidden behind the degraded videos. FogNet learns robust representations of foggy videos with guidance from clean videos, effectively capturing shared structural and motion cues between clean and foggy videos. Extensive experiments on FogAct and three other popular datasets demonstrate that our method achieves competitive performance compared with state-of-the-art (SOTA) approaches. Our FogAct and FogNet are given in our project page.

Enqi Liu, Liyuan Pan, Zhi Gao +2

Beijing Institute of Technology, Beijing, China · Beijing Institute for General Artificial Intelligence, Beijing, China · Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, China

Video Action Recognition Video Representation Learning

May 18, 2026cs.CV

Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models

Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in substantial data and compute costs. In contrast, modern image foundation models already provide powerful spatial representations. This raises an important question: can competitive video models be built by reusing these spatial representations and pre-training only for temporal reasoning? We take initial steps toward exploring a lightweight training paradigm that freezes a pre-trained image foundation model and trains only a recurrent temporal module to process streaming video. By reusing an image foundation model as a spatial encoder, this approach could significantly reduce the amount of video data and compute required compared to end-to-end video pre-training. In this work, we explore the feasibility of this approach before investing in computing for video pre-training. Our empirical findings across multiple video understanding tasks suggest that strong temporal performance can emerge without large-scale video pre-training, motivating future work on recurrent video foundation models obtained by pre-training a temporal module on top of a frozen image foundation model. Code: https://github.com/tue-mps/towards-video-image-frozen .

Svetlana Orlova, Niccolò Cavagnero, Gijs Dubbelman

Eindhoven University of Technology

Streaming Video Understanding Vision Foundation Model Adaptation Video Representation Learning Temporal Video Understanding

May 16, 2026cs.CV

Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives

Joint-Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised video representation learning, yet the behavior of auxiliary objectives in small-scale Video-JEPA training is not well characterized. We report a small-scale empirical study of 18 auxiliary objective variants for Video-JEPA across two pretraining regimes: single-dataset (UCF-101) and mixed-dataset (UCF-101 + Something-Something V2 + ImageNet-100). We evaluate frozen representations on three complementary benchmarks: Diving-48 (fine-grained motion), SomethingSomething V2 (temporal reasoning), and ImageNet-100 (appearance). Our experiments suggest that many auxiliary objectives exhibit capacity trade-offs: gains on one downstream capability often coincide with degradation on another. We then study FWM-HW-LD (Factorized World-Model with Hard-Region-Weighted Latent Dynamics), a training-time objective that separates the latent representation into appearance and dynamics subspaces and applies hard-region weighting to both JEPA prediction errors and latent dynamics errors. In our mixed-dataset setting, FWM-HW-LD improves ImageNet-100 by +5.92 and SSv2 by +3.21 percentage points relative to the reference baseline, while remaining within 0.30 percentage points on Diving-48. These results indicate that latent factorization is a useful direction for studying auxiliary-objective trade-offs in Video-JEPA.

Santosh Premi

Disentangled Representation Learning Latent Dynamics Modeling Joint-Embedding Predictive Architecture Video Action Recognition Video Representation Learning

May 15, 2026cs.CV

Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence

Self-supervised video models are increasingly framed as world models, yet they are still evaluated almost entirely on clean video and reported as a final task score, obscuring how their representations behave under the degraded and ambiguous conditions a deployed world model must handle. We present the first systematic study of this component, analyzing four matched-capacity frontier self-supervised learning models that are strong candidates for world-model encoders -- V-JEPA 2.1, V-JEPA 2, VideoPrism, and VideoMAEv2 -- across five robustness axes relevant to their deployment as video world models: feature discriminability, corruption robustness, fine-grained discrimination, occlusion robustness, and sensitivity to temporal direction. We run the study on Something-Something-v2 and repeat every axis that ports on the egocentric EGTEA Gaze+, where the model ordering is unchanged. Our results reveal a distinct and consistent profile for latent-prediction models across all five axes. They degrade more gracefully under pixel corruption, preserve usable class structure rather than mere geometric stability under occlusion, capture fine-grained physical contact cues without reconstructing pixels, and uniquely encode the arrow of time. We finally test whether these representation-level differences matter for downstream world modeling, pairing each frozen encoder with an identical action-conditioned predictor and planner in a simulated manipulation environment. Only latent prediction yields near-complete task success, remains effective under degraded observations, and transfers to a manipulation task for which the predictor was never trained. Our results provide concrete new evidence that latent prediction is a promising foundation for robust world modeling.

Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam +2

The University of Melbourne · Monash University

Video Representation Learning Video Prediction World Model Evaluation Self-Supervised Visual Representation Learning Video World Models

May 13, 2026cs.CV

STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition

Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal misalignment, where static textual prompts fail to capture decisive visual cues that appear sparsely across sequences, and from inadequate modeling of multi-scale temporal dynamics, as short-term discriminative cues and long-range dependencies are often either oversmoothed or fragmented. To address these challenges, we propose Semantic Temporal Adaptive Representation Learning (STAR), a unified framework, consisting of a semantic-alignment component and a temporal-aware component, effectively bridging the semantic and temporal gaps and transferring the sequence modeling capability of Mamba into the FSAR. The semantic alignment module introduces a Temporal Semantic Attention (TSA) mechanism, which performs frame-level cross-modal alignment with textual cues, ensuring fine-grained semantic-temporal consistency. The temporal-aware module incorporates a Semantic Temporal Prototype Refiner (STPR) that integrates semantic-guided Mamba blocks with multi-frequency temporal sampling and bidirectional state-space refinement, yielding semantically aligned prototypes with enhanced discriminative fidelity and temporal consistency. Furthermore, temporally dependent class descriptors derived from large language models (LLMs) provide long-range semantic guidance. Extensive experiments on five FSAR benchmarks demonstrate the consistent superiority of STAR over state-of-the-art methods. For instance, STAR achieves up to 8.1% and 6.7% gains on the SSv2-Full and SSv2-Small datasets under the 1-shot setting, and 7.3% on HMDB51, validating its effectiveness under limited supervision. The code is available at https://github.com/HongliLiu1/STAR-main.

Hongli Liu, Yu Wang, Shengjie Zhao

School of Computer Science and Technology, Tongji University, Shanghai, China · Engineering Research Center of Key Software Technologies for Smart City Perception and Planning, Ministry of Education

Cross-Modal Representation Learning Few-Shot Learning Visual SSMs Video Representation Learning

May 12, 2026cs.CV

Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos

Learning robust representations of polyp tracklets is key to enabling multiple AI-assisted colonoscopy applications, from polyp characterization to automated reporting and retrieval. Supervised contrastive learning is an effective approach for learning such representations, but it typically relies on correct positive and negative definitions. Collecting these labels requires linking tracklets that depict the same underlying polyp entity throughout the video, which is costly and demands specialized clinical expertise. In this work, we leverage the sequential workflow of colonoscopy procedures to derive self-supervised associations from temporal structure. Since temporally derived associations are not guaranteed to be correct, we introduce a noise-aware contrastive loss to account for noisy associations. We demonstrate the effectiveness of the learned representations across multiple downstream tasks, including polyp retrieval and re-identification, size estimation, and histology classification. Our method outperforms prior self-supervised and supervised baselines, and matches or exceeds recent foundation models across all tasks, using a lightweight encoder trained on only 27 videos. Code is available at https://github.com/lparolari/ntssl.

Luca Parolari, Pietro Gori, Lamberto Ballan +2

Department of Mathematics, University of Padova, Padova, Italy · LTCI, Telecom Paris, Institut Polytechnique de Paris, Palaiseau, France · Cosmo Intelligent Medical Devices, Dublin, Ireland

Contrastive Learning Endoscopy Medical Image Analysis Video Representation Learning Noisy-Label Learning Medical Image Representation Learning

May 11, 2026cs.CV

Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation

Automated, clinician-grade assessment reports for surgical procedures could reduce documentation burden and provide objective feedback, yet remain challenging due to the difficulty of aligning dense spatio-temporal video representations with language-based reasoning and the scarcity of high-quality, privacy-preserving datasets. To address this gap, we establish a benchmark comprising 214 high-quality simulated surgical videos paired with surgeon-authored evaluation reports. Building on this resource, we propose a Perception-Alignment-Reasoning framework for surgical video report generation, featuring Hi-GaTA, a novel lightweight temporal adapter that efficiently compresses long video sequences into compact, LLM-compatible visual prefix tokens through short-to-long-range temporal aggregation. For robust visual perception, we pretrain Sur40k, a surgical-specific ViViT-style video encoder on 40,000 minutes of public surgical videos to capture fine-grained spatio-temporal procedural priors. Hi-GaTA employs a temporal pyramid with text-conditioned dual cross-attention, and improves multi-scale consistency through cross-level gated fusion and an increasing-depth strategy. Finally, we fine-tune the LLM backbone using LoRA to enable coherent and stylistically consistent surgical report generation under limited supervision. Experiments show our approach achieves the best overall performance, with consistent gains over strong Multimodal Large Language Model (MLLM) baselines. Ablation studies further validate the effectiveness of each proposed component.

Kedi Sun, Chaohui Dang, Yue Feng +3

School of Engineering, College of Engineering and Physical Sciences, University of Birmingham, Birmingham, UK · School of Computer Science, University of Birmingham, Birmingham, UK · Department of Applied Health Sciences, University of Birmingham, Birmingham, UK

Surgical Video Understanding Video Representation Learning Temporal Attention

May 9, 2026cs.LG

Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation

We propose Compressed Video Aggregator (CVA), a lightweight micro-video recommendation module that decouples video information from preference learning. It aggregates frozen VFM embeddings, and uses latent reasoning without cross-attention projection, producing compact video embeddings for recommenders. Due to the redundancy in the frame count of the original benchmark and its overly coarse sampling, we used titles to re-select key frames based on CLIP. Experiments on MicroLens and Short-Video show consistent gains with orders-of-magnitude reductions in training time and GPU memory, and re-selected frames can further enhance the performance of all methods, including CVA. Furthermore, we also discussed the impact of several scenarios involving erroneous titles on our method. Code will be released soon.

Yang Xiao, Huiyuan Chen, Kaiyuan Deng +5

University of Tulsa · Amazon · University of Arizona +1

Video Representation Learning Embedding Compression

May 7, 2026cs.CV

LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute

Transformers dominate video recognition. They split videos into tokens, and processing them has expensive superlinear computational cost. Yet videos are filled with redundancy, so we can question the need for this expense. We introduce LookWhen, a selector-extractor framework that factorizes video recognition into learning when, where, and what to compute. Our shallow selector gets a scaled-down video and quickly scores all tokens across space-time, while our deep extractor gets the top-K selected tokens to approximate full-video representations without actually processing all the tokens. A key challenge is defining effective supervision for selection and extraction. For selection pre-training, we introduce a score on representations that ranks tokens by uniqueness using a simple nearest-neighbor distance. For extraction pre-training, we distill both a video teacher and an image teacher, for which we normalize its frame-wise representations to learn what changes within videos. Through these strategies, our selector-extractor learns general and efficient representations for feature extraction or fine-tuning to a task. Through experiments on Kinetics-400, SSv2, Epic-Kitchens, Diving48, Jester, and Charades, we show that LookWhen achieves a better accuracy-computation trade-off than efficient models and upgraded baselines of similar size. LookWhen Pareto-dominates in accuracy-FLOPs on 9 of 12 cases (6 tasks x 2 settings) and roughly matches on 3. In accuracy-throughput, measuring time in practice, LookWhen is more efficient still at 6.7x faster than InternVideo2-B at equal accuracy.

Ali Salamatian, Anthony Fuller, Pritam Sarkar +3

University of British Columbia · Carleton University · Vector Institute

Efficient ViTs Video Action Recognition Video Representation Learning Visual Token Pruning

May 7, 2026cs.CV

HumanNet: Scaling Human-centric Video Learning to One Million Hours

Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, learning physical interaction remains constrained by the lack of large, diverse, and richly annotated human activity data. We present HumanNet, a one-million-hour human-centric video corpus that captures how humans interact with the physical world at scale. HumanNet spans both first-person and third-person perspectives and covers fine-grained activities, human-object interactions, tool use, and long-horizon behaviors across diverse real-world environments. Beyond raw video, the dataset provides interaction-centric annotations, including captions, motion descriptions, and hand and body-related signals, enabling motion-aware and interaction-aware learning. Beyond scale, HumanNet introduces a systematic data curation paradigm for embodied learning, where human-centric filtering, temporal structuring, viewpoint diversity, and annotation enrichment are treated as first-class design principles. This design transforms unstructured internet video into a scalable substrate for representation learning, activity understanding, motion generation, and human-to-robot transfer. We conduct a first-step validation on the value of this design through controlled vision-language-action ablation: under a fixed set of validation data, continued training from the Qwen VLM model with 1000 hours of egocentric video drawn from HumanNet surpasses the continued training with 100 hours of real-robot data from Magic Cobot, indicating that egocentric human video could be a scalable and cost-effective substitute for robot data. By building this project, we aim to explore the opportunity to scale embodied foundation models using human-centric videos, rather than relying solely on robot-specific data.

Yufan Deng, Daquan Zhou

DAGroup · SimpleSilicon Innovation Team Peking University

Human Activity Recognition Cross-Embodiment Robot Learning Egocentric Video Understanding Video Representation Learning

May 4, 2026cs.CV

Video Generation with Predictive Latents

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable reconstruction quality, continued optimization of reconstruction does not necessarily translate into improved generative performance. How to enhance the diffusability of video latents remains a critical and unresolved challenge. In this work, inspired by principles of predictive world modeling, we investigate the potential of predictive learning to improve the video generative modeling. To this end, we introduce a simple and effective predictive reconstruction objective that unifies predictive learning with video reconstruction. Specifically, we randomly discard future frames and encode only partial past observations, while training the decoder to reconstruct the observed frames and predict future ones simultaneously. This design encourages the latent space to encode temporally predictive structures and build a more coherent understanding of video dynamics, thereby improving generation quality. Our model, termed Predictive Video VAE (PV-VAE), achieves superior performance on video generation, with 52% faster convergence and a 34.42 FVD improvement over the Wan2.2 VAE on UCF101. Furthermore, comprehensive analyses demonstrate that PV-VAE not only exhibits favorable scalability, with generative performance improving alongside VAE training, but also yields consistent gains in downstream video understanding, underscoring a latent space that effectively captures temporal coherence and motion priors.

Yian Zhao, Feng Wang, Qiushan Guo +4

ByteDance Seed · Tsinghua University · Peking University

Variational Autoencoders Predictive Coding Video Representation Learning Video Generation

May 3, 2026cs.CV

TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning

The rapid growth of video content across domains such as surveillance, education, and social media has made efficient content understanding increasingly critical. Video summarization addresses this challenge by generating concise yet semantically meaningful representations, but existing approaches often rely on expensive manual annotations, struggle to generalize across domains, and incur significant computational costs due to complex architectures. Moreover, unsupervised and weakly supervised methods typically underperform compared to supervised counterparts in capturing long-range temporal dependencies and semantic structure. In this work, we propose TRIMMER (Temporal Relative Information Maximization for Multi-objective Efficient Reinforcement), a novel self-supervised reinforcement learning framework for video summarization. TRIMMER operates in two stages: it first learns robust representations via self-supervised learning and then performs spatio-temporal decision making through reinforcement learning guided by information-theoretic reward functions. Unlike prior approaches that rely on similarity-based objectives, our method introduces entropy-based metrics to capture higher-order temporal dynamics and semantic diversity, while computing rewards directly over selected frame indices to improve computational efficiency. Extensive experiments on standard benchmarks demonstrate that TRIMMER achieves state-of-the-art performance among unsupervised and self-supervised methods, while remaining competitive with leading supervised approaches, highlighting its effectiveness for scalable and generalizable video summarization.

Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas

Universitat Pompeu Fabra, Barcelona, Spain · Universitat Autònoma de Barcelona, Barcelona, Spain

Reinforcement Learning Video Summarization Video Representation Learning

Apr 29, 2026cs.CV

Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners

One of the most exciting applications of vision models involve pixel-level reasoning. Despite the abundance of vision foundation models, we still lack representations that effectively embed spatio-temporal properties of visual scenes at the pixel level. Existing frameworks either train on image-based pretext tasks, which do not account for dynamic elements, or on video sequences for action-level reasoning, which does not scale to dense pixel-level prediction. We present a framework that learns pixel-accurate feature descriptors from videos, LILA. The core element of our training framework is linear in-context learning. LILA leverages spatio-temporal cue maps -- depth and motion -- estimated with off-the-shelf networks. Despite the noisy nature of those cues, LILA trains effectively on uncurated video datasets, embedding semantic and geometric properties in a temporally consistent manner. We demonstrate compelling empirical benefits of the learned representation across a diverse suite of vision tasks: video object segmentation, surface normal estimation and semantic segmentation.

Nikita Araslanov, Martin Sundermeyer, Hidenobu Matsuki +2

Google · TU Munich · Munich Center for Machine Learning

Video Representation Learning 3D Scene Understanding

Apr 25, 2026cs.CV

Micro-Expression-Aware Avatar Fingerprinting via Inter-Frame Feature Differencing

Avatar fingerprinting, i.e., verifying who drives a synthetic talking-head video rather than whether it is real, is a critical safeguard for authorized use of face-reenactment technology. Existing methods rely on a fixed, non-differentiable landmark extraction stage that prevents the fingerprinting model from being optimized end-to-end from raw pixels. We propose a preprocessing-free system built on a micro-expression-aware backbone operating on raw video frames, with inter-frame feature differencing as the core design principle: consecutive feature maps are subtracted in the learned deep feature space, so that temporally stable appearance dimensions contribute zero to the output while driver-specific motion dynamics are preserved. A controlled ablation on NVFAIR confirms that temporal motion accounts for the large majority of discriminative performance, and that raw appearance features actively degrade identity separation. Both the choice of backbone and the differencing principle are essential: differencing alone is insufficient when applied to a generic encoder, as appearance-dominated features collapse to near-identical representations across adjacent frames, while the micro-expression-aware F5C backbone retains measurable motion variation that the differencing operation can exploit. Without any external preprocessing, our model achieves an overall AUC of 0.877 on NVFAIR and matches or exceeds the landmark-based baseline on the majority of cross-generator pairs.

Masoumeh Chapariniya, Jean-Marc Odobez, Volker Dellwo +1

Department of Computational Linguistics, University of Zurich, Zurich, Switzerland · UZH Digital Society Initiative · Idiap Research Institute, Martigny, Switzerland +1

Biometric Identification Video Representation Learning

Apr 23, 2026cs.CV

Efficient Logic Gate Networks for Video Copy Detection

Video copy detection requires robust similarity estimation under diverse visual distortions while operating at very large scale. Although deep neural networks achieve strong performance, their computational cost and descriptor size limit practical deployment in high-throughput systems. In this work, we propose a video copy detection framework based on differentiable Logic Gate Networks (LGNs), which replace conventional floating-point feature extractors with compact, logic-based representations. Our approach combines aggressive frame miniaturization, binary preprocessing, and a trainable LGN embedding model that learns both logical operations and interconnections. After training, the model can be discretized into a purely Boolean circuit, enabling extremely fast and memory-efficient inference. We systematically evaluate different similarity strategies, binarization schemes, and LGN architectures across multiple dataset folds and difficulty levels. Experimental results demonstrate that LGN-based models achieve competitive or superior accuracy and ranking performance compared to prior models, while producing descriptors several orders of magnitude smaller and delivering inference speeds exceeding 11k samples per second. These findings indicate that logic-based models offer a promising alternative for scalable and resource-efficient video copy detection.

Katarzyna Fojcik

Department of Artificial Intelligence, Wroclaw University of Science and Technology, Wroclaw, Poland

Efficient Neural Network Inference Video Representation Learning

Apr 23, 2026cs.CV

Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) enables cross-modality identity matching for all-day surveillance, yet existing methods predominantly focus on the image level or rely heavily on costly identity annotations. While video-based VI-ReID has recently emerged to exploit temporal dynamics for improved robustness, existing studies remain limited to supervised settings. Crucially, the unsupervised video VI-ReID problem, where models must learn from RGB and infrared tracklets without identity labels, remains largely unexplored despite its practical importance in real-world deployment. To bridge this gap, we propose HiTPro (Hierarchical Temporal Prototyping), a prototype-driven framework without explicit hard pseudo-label assignment for unsupervised video-based VI-ReID. HiTPro begins with an efficient Temporal-aware Feature Encoder that first extracts discriminative frame-level features and then aggregates them into a robust tracklet-level representation. Building upon these features, HiTPro first constructs reliable intra-camera prototypes via Intra-Camera Tracklet Prototyping by aggregating features from temporally partitioned sub-tracklets. Through Hierarchical Cross-Prototype Alignment, we perform a two-stage positive mining process: progressing from within-modality associations to cross-modality matching, enhanced by Dynamic Threshold Strategy and Soft Weight Assignment. Finally, {Hierarchical Contrastive Learning} progressively optimizes feature-prototype alignment across three levels: intra-camera discrimination, cross-camera same-modality consistency, and cross-modality invariance. Extensive experiments on HITSZ-VCM and BUPTCampus demonstrate that HiTPro achieves state-of-the-art performance under fully unsupervised settings, significantly outperforming adapted baselines and establishes a strong baseline for future research.

Zhiyong Li, Wei Jiang, Haojie Liu +3

College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China · School of Computer Science and Technology, Zhejiang University of Water Resources and Electric Power, Hangzhou, 310018, China

Prototype Learning Video Representation Learning Person Re-Identification

Apr 18, 2026cs.CV

Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition

Zero-shot action recognition is challenging due to the semantic gap between seen and unseen classes. We present a novel framework that enhances CLIP with disentangled embeddings and semantic-guided interaction. A Motion Separation Module (MSM) separates motion-sensitive and global-static features, while a Motion Aggregation Block (MAB) employs gated cross-attention to refine motion representation without re-coupling redundant information. To facilitate generalization to unseen categories, we enforce semantic alignment between video features and textual representations by aligning projected embeddings with positive textual prompts, while leveraging negative prompts to explicitly model "non-class" semantics. Experiments on standard benchmarks demonstrate that our method consistently outperforms prior CLIP-based approaches, achieving robust zero-shot action recognition across both coarse and fine-grained datasets.

Yiming Wang, Frederick W. B. Li, Jingyun Wang

Department of Computer Science, Durham University

Representation Learning Video Action Recognition Video Representation Learning Motion Representation Learning Vision-Language Alignment

Apr 17, 2026cs.CV

CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting

Time-to-Collision (TTC) forecasting is a critical task in collision prevention, requiring precise temporal prediction and comprehending both local and global patterns encapsulated in a video, both spatially and temporally. To address the multi-scale nature of video, we introduce a novel spatiotemporal hierarchical transformer-based architecture called CollideNet, specifically catered for effective TTC forecasting. In the spatial stream, CollideNet aggregates information for each video frame simultaneously at multiple resolutions. In the temporal stream, along with multi-scale feature encoding, CollideNet also disentangles the non-stationarity, trend, and seasonality components. Our method achieves state-of-the-art performance in comparison to prior works on three commonly used public datasets, setting a new state-of-the-art by a considerable margin. We conduct cross-dataset evaluations to analyze the generalization capabilities of our method, and visualize the effects of disentanglement of the trend and seasonality components of the video data. We release our code at https://github.com/DeSinister/CollideNet/.

Nishq Poorav Desai, Ali Etemad, Michael Greenspan

Queen’s University, Canada

Collision Avoidance Video Representation Learning Spatiotemporal Forecasting

Apr 12, 2026cs.CV

GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models

Game engines hold what video models struggle to learn: a complete, explicit world state behind every frame. We turn one into a data instrument. GEST-Engine, our production-grade open-source system, deterministically executes Graphs of Events in Space and Time (GESTs), whether procedurally generated or derived from text, into videos of synchronized multi-actor scenarios, recording ground truth as it renders: 3D entity and camera state, pairwise spatial relations, event-to-frame mappings, instance segmentation, and long descriptions, at zero marginal annotation cost. With it we release GTASA, a 938-video sample of what the system can generate at arbitrary scale, carrying, to our knowledge, the densest spatial-relation coverage of any video dataset: a complete entity-pair relation graph at every frame, ~84x denser than the state of the art, frame-for-frame. We validate GTASA both qualitatively, through human evaluation of physical validity and semantic alignment where frontier neural generators, given the same prompts, largely fail, and quantitatively, with GTASA pretraining improving VLM video captioning. Probing six frozen video encoders across 11 spatio-temporal tasks enabled by GTASA's exact 3D ground truth, a previously untestable inter-entity relational probe of frozen video features, reveals that who-is-near-whom barely rises above chance for all of them. We release the engine, the corpus, and the benchmark, making this gap a measurable, trainable target.

Nicolae Cudlenco, Mihai Masala, Marius Leordeanu

Institute of Mathematics of the Romanian Academy, Bucharest, Romania · National University of Science and Technology Politehnica Bucharest, Romania · Büchi Labortechnik AG, Flawil, Switzerland

Synthetic Data Generation Video Representation Learning Video Reasoning 3D Scene Understanding Video Generation Evaluation

Mar 18, 2026cs.CV

LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression

Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally expensive and memory intensive, limiting its deployment in resource-constrained environments. This paper proposes LRConv-NeRV, an efficient NeRV variant that replaces selected dense 3x3 convolutional layers with structured low-rank separable convolutions, trained end-to-end within the decoder architecture. By progressively applying low-rank factorization from the largest to earlier decoder stages, LRConv-NeRV enables controllable trade-offs between reconstruction quality and efficiency. Extensive experiments demonstrate that applying LRConv only to the final decoder stage reduces decoder complexity by 68%, from 201.9 to 64.9 GFLOPs, and model size by 9.3%, while incurring negligible quality loss and achieving approximately 9.2% bitrate reduction. Under INT8 post-training quantization, LRConv-NeRV preserves reconstruction quality close to the dense NeRV baseline, whereas more aggressive factorization of early decoder stages leads to disproportionate quality degradation. Compared to existing work under layer-aligned settings, LRConv-NeRV achieves a more favorable efficiency versus quality trade-off, offering substantial GFLOPs and parameter reductions while maintaining higher PSNR/MS-SSIM and improved temporal stability. Temporal flicker analysis using LPIPS further shows that the proposed solution preserves temporal coherence close to the NeRV baseline, results establish LRConv-NeRV as a potential architectural alternative for efficient neural video decoding under low-precision and resource-constrained settings.

Tamer Shanableh

American University of Sharjah, UAE, Department of Computer Science and Engineering

Video Representation Learning Neural Video Compression Low-Rank Approximation Convolutional Neural Networks Video Compression

Feb 18, 2026cs.CV

Xray-Visual Models: Scaling Vision models on Industry Scale Data

We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag pairs from Facebook and Instagram, employing robust data curation pipelines that incorporate balancing and noise suppression strategies to maximize semantic diversity while minimizing label noise. We introduce a three-stage training pipeline that combines self-supervised MAE, semi-supervised hashtag classification, and CLIP-style contrastive learning to jointly optimize image and video modalities. Our architecture builds on a Vision Transformer backbone enhanced with efficient token reorganization (EViT) for improved computational efficiency. Extensive experiments demonstrate that Xray-Visual achieves state-of-the-art performance across diverse benchmarks, including ImageNet for image classification, Kinetics and HMDB51 for video understanding, and MSCOCO for cross-modal retrieval. The model exhibits strong robustness to domain shift and adversarial perturbations. We further demonstrate that integrating large language models as text encoders (LLM2CLIP) significantly enhances retrieval performance and generalization capabilities, particularly in real-world environments. Xray-Visual establishes new benchmarks for scalable, multimodal vision models, while maintaining superior accuracy and computational efficiency.

Shlok Mishra, Tsung-Yu Lin, Linda Wang +24

Meta-AI · MIT (work done while at Meta AI) · University of Maryland (work done while at Meta AI)

Vision Foundation Models Multimodal Pretraining Video Representation Learning Vision-Language Pretraining

Feb 5, 2026cs.CV

SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos

While foundation models have advanced surgical video analysis, current approaches rely predominantly on pixel-level reconstruction objectives that waste model capacity on low-level visual details, such as smoke, specular reflections, and fluid motion, rather than semantic structures essential for surgical understanding. We present SurgMotion, a video-native foundation model that shifts the learning paradigm from pixel-level reconstruction to latent motion prediction. Built on the Video Joint Embedding Predictive Architecture (V-JEPA), SurgMotion introduces three key technical innovations tailored to surgical videos: (1) motion-guided latent masked prediction to prioritize semantically meaningful regions, (2) spatiotemporal affinity self-distillation to enforce relational consistency, and (3) spatiotemporal feature diversity regularization (SFDR) to prevent representation collapse in texture-sparse surgical scenes. To enable large-scale pretraining, we curate SurgMotion-15M, the largest surgical video dataset to date, comprising 3,658 hours of video from 50 sources across 13 anatomical regions. Extensive experiments across 17 benchmarks demonstrate that SurgMotion significantly outperforms state-of-the-art methods on surgical workflow recognition, achieving 14.6 percent improvement in F1 score on EgoSurgery and 10.3 percent on PitVis; on action triplet recognition with 39.54 percent mAP-IVT on CholecT50; as well as on skill assessment, polyp segmentation, and depth estimation. These results establish SurgMotion as a new standard for universal, motion-oriented surgical video understanding.

Jinlin Wu, Felix Holm, Chuxi Chen +18

Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong, China · State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany +7

Joint-Embedding Predictive Architecture Surgical Video Understanding Video Representation Learning

Jan 29, 2026cs.CV

Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving

End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited improvements. This limitation is compounded by the inherent ambiguity of driving: each scene typically provides only a single human trajectory, making it difficult to learn multimodal behaviors. In this work, we propose Drive-JEPA, a framework that integrates Video Joint-Embedding Predictive Architecture (V-JEPA) with multimodal trajectory distillation for end-to-end driving. First, we adapt V-JEPA for end-to-end driving, pretraining a ViT encoder on large-scale driving videos to produce predictive representations aligned with trajectory planning. Second, we introduce a proposal-centric planner that distills diverse simulator-generated trajectories alongside human trajectories, with a momentum-aware selection mechanism to promote stable and safe behavior. When evaluated on NAVSIM, the V-JEPA representation combined with a simple transformer-based decoder outperforms prior methods by 3 PDMS in the perception-free setting. The complete Drive-JEPA framework achieves 93.3 PDMS on v1 and 87.8 EPDMS on v2, setting a new state-of-the-art.

Linhan Wang, Zichong Yang, Chen Bai +6

Virginia Tech · Purdue University · XPENG Motors +1

End-to-End Autonomous Driving Joint-Embedding Predictive Architecture Video Representation Learning Autonomous Driving Planning

Dec 21, 2025cs.CV

FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation

Short-form video moderation is increasingly pushed toward edge and privacy-sensitive settings, where users may intend videos for a limited audience, such as friends or private groups, but sending raw clips to a central server can broaden exposure, consume bandwidth, and add moderation latency. Federated learning can keep videos on device, but unprotected model updates may still leak information, and full-video backbones are expensive to communicate. We present FedVideoMAE, a privacy-preserving federated framework for violence detection that adapts a frozen VideoMAE backbone with lightweight LoRA and prompt parameters. Each training round combines self-supervised masked video reconstruction with client-side differential privacy and pairwise masked aggregation (SA) of adapter updates. Violence labels are held out from federation and used only for downstream evaluation, separating private representation learning from supervised assessment. On RWF-2000, exchanging 5,518,848 trainable parameters instead of the 156,371,328-parameter instantiated pretraining state gives a 28.3x model-state payload ratio. FedVideoMAE reaches 77.25% test accuracy without DP or SA, while accuracy under DP+SA remains in the 65.25-66.00% range. Transfer experiments on RLVS and binary UCF-Crime show similar behavior. These results characterize the privacy-utility trade-off for edge video moderation. Code is available at: https://github.com/zyt-599/FedVideoMAE

Ziyuan Tao, Chuanzhi Xu, Sandaru Jayawardana +4

School of Computing, Macquarie University, Sydney, Australia · School of Computer Science, The University of Sydney, Sydney, Australia · School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia

Federated Learning Aggregation Video Content Moderation Video Representation Learning Privacy-Preserving ML Secure Aggregation Federated Learning

Mar 20, 2025cs.LG

Structured-Noise Masked Modeling for Video, Audio and Beyond

Masked modeling has emerged as a robust self-supervised learning framework. However, most methods rely on random masking, which disregards the structural properties of different data modalities. To align with the spatiotemporal and spectral characteristics of video and audio data, we introduce a structured noise-based masking approach. By filtering white noise into different color noise distributions, we generate structured masks that capture modality-specific patterns without requiring handcrafted heuristics or access to the data. Our approach enhances masked video and audio modeling frameworks without any additional computational cost. Experiments show that structured noise masking consistently outperforms random masking, underscoring the value of modality-aware masking strategies for representation learning.

Aritra Bhowmik, Carlos Hinojosa, Fida Mohammad Thoker +2

University of Amsterdam · King Abdullah University of Science and Technology

Audio Representation Learning Video Representation Learning

Date pendingcs.CV

What Moves? Localized Motion Representations for Compositional Scene Control

Real-world dynamics are inherently compositional: multiple entities move simultaneously within a shared scene, each exhibiting distinct motion patterns. Yet current motion representation models entangle the dynamics of different entities, without explicitly capturing localized motion for each individually. Crucially, motion is defined relative to a global reference frame, including camera motion and scene layout. However, localized embeddings are often computed from cropped images or obtained by masking features after encoding, discarding the context needed to interpret motion. To address this, we introduce a promptable localized motion representation that produces persistent embeddings for user-specified regions defined by spatial masks. Rather than cropping the input or masking features, our model processes the full video and conditions motion encoding directly on the queried region. This yields temporally consistent, region-addressable embeddings that isolate local dynamics while retaining the global context required for disambiguation. We demonstrate object-level motion transfer, enabling controlled composition of dynamic scenes. Beyond generative control, our embeddings support localized action classification in multi-actor videos. Across both tasks, our approach improves controllability and outperforms global representations localized through cropping or post-hoc masking.

Frank Fundel, Malek Ben Alaya, Thomas Ressler-Antal +2

Representation Learning Object-Centric Representation Learning Video Representation Learning Motion Representation Learning Controllable Video Generation