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

Oct 6, 2026cs.CV

HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data

Modern action recognition models rely on video transformers pretrained on massive collections of web-crawled videos, such as Kinetics-700. However, the use of such data raises ethical concerns, as subjects' consent is typically not obtained. Recent high-quality synthetic video datasets generated from motion-capture data, such as BEDLAM2.0, offer a promising ethical alternative. In this work, we investigate self-supervised pretraining of video transformers on synthetic human-motion datasets. We first show that directly applying the standard VideoMAE masking strategy leads to substantially worse performance than pretraining on Kinetics. To address this limitation, we propose a human-centric masking scheme that leverages body keypoints and person bounding box regions. Our approach encourages the model to focus on the structure and dynamics of human motion during pretraining. Experiments on NTU RGB+D and Toyota-Smarthome demonstrate that our method significantly outperforms standard VideoMAE pretraining on synthetic data, closing 49% of the gap to Kinetics pretraining on NTU RGB+D cross-view-subject without using a single real frame during pretraining. To promote the use of ethical action recognition models, we will publicly release our pretrained models.

Ricardo Pizarro, Roberto Valle, José M. Buenaposada +2

Universidad de Alcal´a, Alcal´a de Henares, Spain · Universidad Polit´ecnica de Madrid, Madrid, Spain · Universidad Rey Juan Carlos, M´ostoles, Spain

Synthetic Data Pretraining Masked Autoencoders Self-Supervised Pre-Training Video Action Recognition Video Representation Learning

Oct 5, 2026cs.CV

Video Encoders Built on Image Representations

The design of a video encoder determines when frames begin to interact and which frame-specific visual evidence remains accessible to the language model. Native video pathways couple neighboring frames during visual encoding, whereas image pathways preserve independently computed frame representations but incur a much larger visual-token cost when all image tokens are forwarded. We ask a basic question: whether a compact video encoder can instead be built on image representations. To answer this question, we separate three operations that are often coupled: per-frame representation, cross-frame token allocation, and temporal interaction. A frozen image encoder first produces frame-specific candidates. A question-aware selector then allocates a fixed token budget across frames using relevance, diversity, and cross-frame correspondence, after which a lightweight learned refiner reads neighboring-frame context and writes residual updates only to the retained anchors. This preserves source positions and keeps the visual output at the fixed budget. Across 13 benchmarks and three vision-language backbones, the resulting pathway matches full-image aggregate performance while using only about 28%-35% of its visual tokens. Specifically, on Qwen3-VL-8B, it achieves a 13-benchmark macro-average of 62.75 with 1,535 visual tokens, compared with 62.58 for the full Image pathway at 4,424 tokens and 59.49 for native Conv3D at 2,212 tokens. On Qwen3-VL-32B, it reaches a 13-benchmark macro-average of 66.28, compared with 66.09 for Image, while providing a 2.16x end-to-end speedup. These results show that compact video encoding does not require early temporal mixing: frame-specific evidence can be preserved first, allocated jointly, and temporally contextualized after selection.

Jusheng Zhang, Wenhao Wang, Longqi Cai +3

Stanford University · Vast Intelligence Lab · Google DeepMind

Video-Language Models Video Representation Learning Video Token Compression

Oct 1, 2026cs.CV

Affine-Aligned Atlas for Canonical Gaussian Construction in Video Representation

Gaussian splatting has recently emerged as an efficient representation for images and videos due to its explicit structure and fast rendering capability. Existing Gaussian-based video representations often decompose a video into canonical Gaussians and temporal deformation. However, when a video contains large global motion such as camera movement, the canonical representation may become misaligned with individual frames, increasing the burden on the temporal deformation model. In this paper, we propose an affine-atlas canonical Gaussian representation, which constructs canonical Gaussians in a larger affine-aligned atlas space. Frame-wise affine transforms absorb global motion before canonical Gaussian construction, reducing the gap between the canonical representation and target frames. Since the proposed method only modifies the canonical construction stage, it can be integrated into existing canonical-Gaussian-based methods with negligible additional parameter cost. Experiments show that our method improves reconstruction quality especially for sequences with large camera motion.

Masaya Takabe, Hiroshi Watanabe, Sujun Hong +1

Graduate School of FSE, Waseda University Tokyo, Japan · Sharp Corporation Chiba, Japan

3D Gaussian Splatting Dynamic Scene Reconstruction Video Representation Learning

Sep 30, 2026cs.CV

Image Classifiers are Efficient Self-Supervised Video Representation Learners

We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of relying on heavy 3D architectures or reconstruction-based autoencoders for learning with unlabeled data, we repurpose standard image Vision Transformers by representing videos as super images which are grids composed of frames sampled from videos. From each super image, we construct two views: one with spatial patch masking and the other with temporal frame masking, ensuring no information leakage across frames. A shared Vision Transformer (ViT) encoder aligns their embeddings using a masked Siamese loss, capturing both motion and appearance cues without reconstruction. Our decoder-free formulation leverages an image foundation model towards efficient video representation learning. Starting from pretrained DINO-v3 and DeiT-v3 image encoders, VideoMSN achieves state-of-the-art performance on Kinetics-400, UCF101, and HMDB51 while requiring up to

32\times

fewer and

160\times

fewer video pretraining epochs compared to prior video self-supervised learning methods. Our proposed approach also shows strong performance in low-shot classification, confirming the transferability of the learned representations in a label-scarce scenario. Project Page: https://cvir.github.io/projects/videomsn.

Owais Iqbal, Sudipta Sarkar, Shyam Marjit +3

Indian Institute of Technology Kharagpur, India · Indian Institute of Science Bangalore, India · École de technologie supérieure Montreal, Canada

Self-Supervised Pre-Training Video Representation Learning

Sep 30, 2026cs.CV

I Have a Stream: Making Self-Supervised Learning Work on Continuous Video

Self-supervised learning draws inspiration from infant visual development, yet standard training pipelines bear little resemblance to it: images are independently sampled and globally shuffled across epochs. We study self-supervised learning from continuous video streams, where frames are consumed in temporal order using strict sliding-window batches, without global reshuffling or multi-epoch replay. To this end, we construct WT++, a 95-hour urban walking-tour video dataset for streaming pretraining. Combined with a comprehensive evaluation suite we find that contrastive and distillation-based methods struggle in this setting, while MAE is more robust but still falls short of standard i.i.d. pretraining. We find that high inter-batch similarity, caused by sliding-window consumption across consecutive batches, does not explain this gap. The main challenge is high intra-batch similarity, where frames within each batch are near-duplicates. To mitigate this, we propose StreamMAE, which preserves the core MAE reconstruction objective while adapting the input pipeline with stream-aware regularization and motion-biased crop selection. StreamMAE outperforms streaming baselines, matches i.i.d. MAE trained on the same video data, remains competitive with ImageNet-pretrained MAE, and scales positively as the pretraining stream grows from 12 to 95 hours.

Ivan Martinović, Lukas Knobel, Yuki M. Asano

Faculty of Electrical Engineering and Computing, University of Zagreb · Fundamental AI Lab, University of Technology Nuremberg

Masked Autoencoders Self-Supervised Learning Video Representation Learning Self-Supervised Visual Representation Learning

Sep 30, 2026cs.CV

CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding

Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, making long-video understanding expensive for the vision encoder and the language model. Existing methods often compress visual tokens after dense encoding, creating a mismatch between the representation used during training and the compact interface required at deployment. We present CoVisco, a codec-native vision encoder with native token compression for unified image-video understanding. By combining codec-native input support with segmented attention, CoVisco can encode long visual inputs in a single forward pass without forming dense patch-to-patch interactions across all frames. Each temporal segment is equipped with learnable abstract tokens that learn a compact segment-level representation, while fine-grained patch tokens remain available throughout the encoder. Alternating intra-segment and abstract-communication layers preserve video-level context through the abstract-token channel. A lightweight selector further exposes either abstract tokens alone or abstract tokens augmented with a runtime-selected subset of patch tokens, yielding a compact visual interface that reduces the visual context and prefill burden of downstream MLLMs while retaining fine-grained evidence when needed. Pretrained with contrastive objectives on 565M image--text pairs and 6.4M videos, CoVisco shows competitive performance on video-oriented embedding and multimodal understanding benchmarks. In the evaluated four-segment, 64-frame setting, abstract-only inference uses only 400 visual tokens while achieving video-understanding performance close to, and on some benchmarks exceeding, OneVision-Encoder. Selected patch tokens further improve fine-grained video reasoning. Project URL: https://github.com/ernie-research/CoVisco.git

Yulong Liu, Xiaotian Han, Junyuan Shang +6

ERNIE Team, Baidu Inc. · The Hong Kong University of Science and Technology · Institute of Automation, Chinese Academy of Sciences (CASIA)

Video Understanding Efficient VLM Inference Video Representation Learning Video Token Compression Visual Token Compression

Sep 30, 2026cs.CV

RESUME: Recurrent State Updates from Motion and Residual Signals for Efficient Video Language Modeling

Existing video language models encode sampled RGB frames independently, so a long video must either exhaust the token budget or drop the changes between sampled frames. Codec-aware front-ends read the motion vectors and residuals that encoding produced, but in their deployed form each predictive frame is still tokenized on its own: the tokens are a function of the current primitives, not of a carried reference. We argue that a more natural function is of both---the current primitives and a carried reference. A clip and its time reversal share the same frames and differ only in the order of changes---an axis that symmetric pooling discards by construction, and that is non-empty in the frozen vision features VideoLMs use---and the codec recurrence already composes those changes in order against a reference state. We introduce RESUME, a stateful codec representation: an anchor I-frame initializes a compact latent state, each subsequent predictive frame is consumed as an update to that state, and a shared readout exposes VideoLM-compatible tokens from the accumulated state. Codec prediction is thereby kept at the representation level and handed to the language model as a trajectory, not as a set of independent token groups. At the same per-predictive-frame token budget as prior codec-aware methods, a predictive frame enters the language model as a readout of what the front-end already knows, not as an encoding of the current primitives alone. Across ten benchmarks, the gains concentrate on temporal reasoning: on all three temporal benchmarks RESUME improves over both the RGB-frame baseline LLaVA-Video-7B (by 2.8, 5.1, and 3.9 points on TempCompass, TOMATO, and MVBench) and the codec-based baseline CoPE-7B, while staying competitive on general and long-form QA. Frozen-transition tests further show anchor dependence, order sensitivity, and useful rollout behavior beyond the training horizon.

Can Zhang, Xiaotian Han, Junyuan Shang +5

Beijing University of Chemical Technology · Baidu, Inc.

Video-Language Models Video Representation Learning Temporal Video Understanding

Sep 29, 2026cs.CV

CurvSpec: Adaptive Multi-Curvature Learning for Partial Relevant Video Retrieval

Partially Relevant Video Retrieval (PRVR) seeks to retrieve untrim-med videos containing a moment that matches a text query, without temporal annotations. The relevant moment may last only seconds within a video spanning several minutes, creating an extremely low signal-to-noise ratio that makes PRVR more challenging than standard full-video retrieval. This task presents two intertwined challenges: (1) signal dilution, where coarse global representations blur the brief relevant signal into the dominant irrelevant surroundings;(2) curvature rigidity, where embedding all videos in the same fixed-geometry space distorts representations for videos that range from flat atomic events to deep compositional hierarchies. Existing PRVR methods have improved moment selection and cross-modal matching, but they still typically encode all videos in a single fixed-curvature retrieval space, limiting their ability to model diverse video structures. To address both challenges, we propose CurvSpec, a framework that learns content-adaptive curvature for video retrieval representations rather than imposing a fixed geometric prior. CurvSpec processes features through parallel Euclidean and hyperbolic attention layers, with independently learned curvatures assigned to the hyperbolic layers, and a content-aware fusion mechanism routes each input to its most suitable geometric regime. To further suppress signal dilution, CurvSpec represents each video with semantic centroids whose number is determined by the video's content complexity, projects them onto the learned manifold, and matches each query against its nearest centroid by geodesic distance. Experiments on ActivityNet Captions, TVR, and Charades-STA demonstrate state-of-the-art retrieval performance.

Zhen Liu, Letian Li, Jinpeng Wang +4

SIGS, Tsinghua University Shenzhen, China · Harbin Institute of Technology, Shenzhen Shenzhen, China

Cross-Modal Retrieval Video Representation Learning Information Retrieval Hyperbolic Representation Learning

Sep 28, 2026cs.CV

W2Rep: Learning Visual Representations by Watching the World Change

Images capture the world at one moment, whereas video reveals how it changes. Image self-supervision learns spatial structure from a single moment, while video methods commonly learn temporal relationships inside a representation computed jointly from several frames. We ask whether watching a scene change can instead improve features available from one image without sacrificing the ability to represent video. We introduce W2Rep, a masked feature-prediction framework in which an independently encoded source image participates in prediction at the same or another moment. The predictor is conditioned on visible video context, the queried location, and the signed time interval between source and target. This gives the cross-frame objective two complementary roles: the image path learns features that remain useful across time, while the video path must gather evidence that is missing from the source image. Across model scales and downstream tasks, W2Rep improves frozen and fine-tuned recognition under our comparison protocol, while joint video encoding provides further gains over frame-wise aggregation. Controlled experiments show that these gains depend on directly updating the source-image features and on using both video context and temporal displacement. Overall, change across a video can supervise a visual encoder whose representations remain useful at either image or video granularity. Code is available at~https://wenooi.github.io/W2Rep.

Wen Huang, Hang Guo, Jiarui Yang +3

Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Nankai University, Tianjin, China · Shenzhen University, Shenzhen, China

Video Representation Learning Self-Supervised Visual Representation Learning

Sep 28, 2026cs.CV

Generative Uncertainty as a Self-supervised Signal for Semantic Similarity Learning

Evaluating semantic similarity between videos is a fundamental challenge in computer vision, essential for tasks ranging from out-of-distribution (OOD) detection to video retrieval. However, defining and labeling video similarity is notoriously difficult and expensive due to the complex spatio-temporal nature. In this paper, we propose a novel self-supervised approach that leverages generative uncertainty from text-to-video (T2V) diffusion models to learn semantic similarity without human annotations. Our method is based on the observation that T2V models produce consistent outputs for familiar concepts but exhibit high variance and uncertainty when prompted with specialized concepts. We utilize this behavior to identify stable semantic features within existing pretrained representations, such as VideoMAE and V-JEPA. Specifically, we learn a mask over these embeddings using purely generated data, encouraging the model to retain features that remain consistent across generations of general concepts while discarding those associated with generative noise or uncertainty. Experimental results across three key tasks demonstrate that our learned feature subspaces consistently outperform original pretrained features and baseline feature selection methods.

Enrico Pallotta, Sina Raoufi, Lars Doorenbos +2

University of Bonn · Lamarr Institute for ML & AI · ENSTA Paris, Institut Polytechnique de Paris

Video Representation Learning Feature Selection Self-Supervised Visual Representation Learning

Sep 28, 2026cs.LG

$λ$ -JEPA Spectral Anti-Collapse Regularization for Self-Supervised Learning

Joint-embedding self-supervised learning typically combines an invariance objective across augmented views with additional mechanisms to prevent representational collapse. These objectives are often applied after a projection head, while downstream tasks use the backbone representation before the projector. We find that this mismatch does not necessarily prevent dimensional collapse in the backbone, which can retain low effective rank and potentially limit downstream transfer. To address this, we introduce SACReg, a spectral anti-collapse regularizer motivated by an analysis of

λ

-balance, which captures the relative scale of weight matrices across layers. In a two-layer linear network, we show that (i)

λ

-balance prevents collapse, and (ii) our regularizer applied to the backbone induces

λ

-balance. In the nonlinear case, this regularizer leads to anti-collapse as well and, in realistic architectures on ImageNet100, it empirically increases the representations' ranks. We apply SACReg to JEPA and propose

λ

-JEPA, which improves over LeJEPA and VISReg on ImageNet-1k classification and in average linear-probe transfer performance across eight downstream image datasets. On video self-supervised learning,

λ

-JEPA improves over LeVJEPA and V-JEPA 2 on the Something-Something-v2 and Kinetics-400 benchmarks. Code is available at https://github.com/berkerdemirel/lambda-jepa.

Berker Demirel, Clémentine Dominé, Valentino Maiorca +3

Institute of Science and Technology Austria (ISTA) Am Campus 1, 3400 Klosterneuburg, Austria

Spectral Regularization Joint-Embedding Predictive Architecture Video Representation Learning Self-Supervised Visual Representation Learning

Sep 27, 2026cs.CV

ReDrive: Shaping Representations with World Modeling for End-to-End Driving

Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically construct complex perception-planning pipelines or introduce world models that explicitly predict future states, resulting in a complex system architecture. Inspired by the transferability of general-purpose visual representations, we argue that combining sufficiently strong visual representations with representation world modeling can support effective planning without relying on complex inference-time auxiliary modules. Based on this insight, we present ReDrive, an end-to-end driving framework that strengthens planning-oriented visual features via future representation prediction. To achieve this, ReDrive adopts a three-stage training pipeline consisting of driving video pretraining, joint world-modeling and planning training, and planner adaptation. This yields a strong planning-oriented representation and a high-performance planner, while requiring neither auxiliary perception modules nor future prediction at inference time. Experiments on NAVSIM demonstrate strong performance, achieving 91.0 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2. These results show that shaping representations with world modeling is sufficient to enable high-performance end-to-end planning while retaining a simple encoder-planner inference pipeline.

Yueting Zhu, Shaoyu Chen, Yuehao Song +4

Huazhong University of Science & Technology · Horizon Robotics

World Model Learning End-to-End Autonomous Driving World Model-Based Planning Video Representation Learning Autonomous Driving Planning

Sep 27, 2026cs.CV

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

Comparisons in video self-supervised learning often evaluate complete training recipes rather than isolating the method itself: architecture, objective, data exposure, schedule, scale, and decoder capacity can all vary at once. This makes it hard to identify which choices yield motion-prioritized representations, whose gains concentrate on frame-to-frame change while retaining useful appearance. We address this with a matched

4 \times 6 = 24

architecture-objective study at roughly 170M ~ 190M encoder scale on

\sim

1.7M OpenVid and Moments-in-Time v2 clips for 8 epochs, and propose TT-VidT. TT-VidT combines a DINOv3-initialized ViT-B/16 per-frame spatial path with a compact Temporal Transfer Layer, trained by Diff Compression to reconstruct target frames from a first-frame appearance anchor and frame-specific motion tokens. The sweep shows that TT3D with Diff Compression, not either component alone, enters the strongest motion-sensitive regime, and decoder ablations favor a compact video-pretrained decoder. In final comparison, TT-VidT leads Jester, Something-Something V2, ARID, and Diving48 fine-tuning simultaneously, improving over the strongest non-TT row by 54% ~ 121%, while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA2. HMDB51, IARD, and EPIC-Kitchens bound the claim.

Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang +3

National Tsing Hua University · Comfy Org Research · Karolinska Institutet +2

Efficient ViTs Video Representation Learning Motion Representation Learning

Sep 21, 2026cs.CV

Video-STLayout Pre-training

In recent years, pre-training has become fundamental to learning effective video representations, enabling strong transfer to downstream tasks. A popular framework in pre-training involves aligning features of a video encoder with that of another modality, for example, language or audio. We introduce Video-STLayout pre-training, a novel strategy for obtaining rich video representations informed by spatio-temporal layout of object bounding boxes. Object layouts can easily be obtained by applying an off-the-shelf object detector on the video frames. Our method uses a contrastive loss to align video features with the layout features from a trained layout encoder. We show the effectiveness of our approach in the task of activity recognition in complex scenes.

Akash Abdu Jyothi, Greg Mori

School of Computing Science Simon Fraser University Burnaby, Canada

Video Action Recognition Video Representation Learning

Sep 20, 2026eess.IV

Resolution-Flexible Decoding for Hybrid Neural Video Representations

Neural video representations (NVRs) represent videos using neural network parameters and, in hybrid formulations, frame-wise latent embeddings. Although hybrid NVRs can improve reconstruction quality by using content-adaptive latent embeddings, their latent spatial sizes and decoder upsampling schedules are tied to the target frame resolution. For high-resolution videos, this dependency may require large and non-uniform upsampling factors and can affect the parameter allocation between the latent embeddings and the decoder. In this paper, we propose a resolution-flexible decoder framework for hybrid NVRs. The decoder is constructed from uniform

2\times

upsampling stages, whose target feature sizes are obtained by tracing the spatial resolution backward from the final output resolution. After each upsampling stage, the feature map is aligned with the target size by minimal padding or cropping when necessary. To support this progressive decoding process, we further use intermediate reconstruction supervision and a reconstruction-difficulty-aware frame sampling strategy based on recent frame-wise losses. The framework preserves the basic representation format of hybrid NVRs and can therefore be applied to different backbones. Experiments on the UVG dataset show that the proposed approach improves reconstruction quality over the corresponding NVR baselines.

Taiga Hayami, Masaya Takabe, Hiroshi Watanabe

Graduate School of FSE, Waseda University Tokyo, Japan

Video Representation Learning

Sep 15, 2026cs.CV

GeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human Videos

Human videos provide rich manipulation experience, but extracting action representations that preserve useful motion remains challenging. Visual reconstruction alone can entangle manipulation-related motion with appearance changes and camera movement. We present GeoLAM, a framework for learning geometry-grounded latent actions from action-free human videos. GeoLAM combines future-frame reconstruction through a frozen geometric feature hierarchy with motion supervision from a training-only 4D geometry teacher. The geometric representation provides a structural prior, while the teacher's predictions yield spatially pooled targets capturing 3D displacement, residual image-plane motion, and surface-orientation changes. Visibility and confidence weighting reduces the contribution of unreliable estimates, encouraging continuous latent actions to retain geometric motion without explicit hand-pose or hand-trajectory annotations. After video pretraining without action labels, the learned representation provides transition targets for a world-action model trained on action-labeled robot demonstrations. The model jointly denoises latent actions and executable action chunks, with future-video prediction used only as an auxiliary training task. Deployment therefore requires neither the geometry teacher nor future-video generation. Evaluations on a latent-action benchmark and robotic manipulation tasks demonstrate the strong performance of GeoLAM.

Yifan Xie, Hekun Tian, Jinkun Liu +3

Tsinghua University · Beijing Institute of Technology · Fudan University

Latent Action Learning Geometric Representation Learning Video Representation Learning Robotic Manipulation Motion Representation Learning

Sep 9, 2026cs.SD

Arti-JEPA: Adapting Video World Model to Real-Time MRI of the Vocal Tract for Speech-Production Analysis

Real-time MRI (rtMRI) captures the dynamics of the entire vocal tract during speech, but labeled data are scarce and the modality - single-slice, grayscale, low-resolution - differs substantially from the natural videos that video foundation models are trained on. We introduce Arti-JEPA, a joint embedding predictive architecture to model vocal tract rtMRI by continuing its self-supervised objective on about 62h of unlabelled vocal-tract videos, and evaluate the frozen representation on three tasks: cross-domain phoneme prediction (on typical speakers), fluent-vs-disfluent classification (a corpus containing stuttered speech), and characterizing pre/post-operative transfer (after partial glossectomy). Three key findings emerge. (1) A temporal video prior decisively outperforms per-frame image encoders, and latent prediction (V-JEPA) is at least as strong as pixel reconstruction (VideoMAE), with the edge on fine-grained phonemes. (2) Domain adaptation is \emph{task-dependent}: it roughly doubles cross-domain phoneme prediction

κ

(to 0.352) but does not help binary stuttering classification. (3) Arti-JEPA was able to recover phoneme signal from pre/post glossectomy speech --- an in-domain probe decodes patients at least as well as a typical speaker, indicating that the residual transfer gap is cross-speaker/domain misalignment, not surgical signal loss, and post-operative decoding does not fall below performance on pre-operative speech. Together, these position a frozen, domain-adapted rtMRI encoder as a reusable measurement tool for articulatory and clinical speech science.

Hong Nguyen, Sean Foley, Christina Hagedorn +4

Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA · Department of English, College of Staten Island, City University of New York, New York, NY, USA · Department of Linguistics, University of Potsdam, Germany +1

Unsupervised Domain Adaptation Joint-Embedding Predictive Architecture Speech Processing Video Representation Learning

Sep 6, 2026cs.CV

VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes

Video foundation models increasingly rely on large-scale pretraining data, yet the end-to-end data pipelines behind them remain largely closed and difficult to inspect or reuse. Researchers seeking to understand how video data recipes affect model pretraining often need to build substantial infrastructure before testing even a focused hypothesis. We present VIDAFORGE, an open research infrastructure that represents a video data recipe as an executable five-stage workflow from raw videos to training datasets. A decision in this workflow can be varied to construct alternative datasets while preserving how every sample was produced. To demon strate this research workflow, we compare data recipes with different coverage and quality in early from-scratch pretraining of Wan 2.1 and V-JEPA 2.1. Across both learning objectives, the broader-coverage recipe achieves the highest downstream benchmark scores, while loss-based evaluation favors different recipes. This study demonstrates how VidaForge connects data-recipe choices to downstream model performance. We further release VIDAFORGE-3M, containing 3.14 million scene level clips totaling 6,475 hours, with fine-grained annotations and curation signals for video data-recipe research.

Yan Ma, Jiadi Su, Zhulin Hu +4

Fudan University · Generative Artificial Intelligence Research Lab (GAIR) · Shanghai Jiao Tong University +2

Vision Foundation Models Training Data Curation Video Representation Learning

Sep 3, 2026cs.CV

The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs

Seeing frames in order does not mean representing time. Modern VideoLMs receive ordered video streams, yet their main supervision acts on generated text rather than video-token representations where event dynamics should first emerge. This mismatch allows models to learn temporal answers from shortcuts such as objects, scenes, and language priors, without requiring internal video representations to capture event progression. To address this, we propose VT-Contrast, a representation-level temporal counterfactual objective for VideoLMs. Its design asks where temporal supervision should act and what temporal differences it should expose. VT-Contrast supervises selected late-layer last-frame video tokens, where temporal information is expected to be integrated before language generation, and contrasts order-preserving views with same-video reordered counterfactuals graded by Kendall tau distance. It requires no architectural changes, is compatible with diverse VideoLM training tasks, and improves overall performance across temporal understanding benchmarks. Our code is available at https://github.com/ANDgate99/VT-Contrast.

Yumeng Shi, Quanyu Long, Yin Wu +1

Nanyang Technological University

Video-Language Models Video Representation Learning Multimodal Contrastive Learning Temporal Video Understanding

Sep 1, 2026cs.CV

What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models

Self-supervised video foundation models learn rich spatiotemporal representations, yet it remains unclear what visual concepts these representations encode, where they emerge across transformer layers, and how they are geometrically organized. In this work, we tackle these three questions through a systematic layer-wise analysis of V-JEPA 2 and VideoMAE-v2. We leverage lightweight probes trained to discover three temporally grounded properties: (i) camera motion understanding, (ii) intuitive physics, and (iii) anomaly detection. Both models encode camera motion, with best results (

>90

ROC AUC) emerging at 60-70% of network depth, and achieve moderate anomaly detection performance (

>60

ROC AUC), but remain near chance on intuitive-physics tasks, suggesting a limited encoding of deeper physical reasoning. Beyond classification, we find that temporal features from individual videos form smooth low-dimensional trajectories in representation space, suggesting that camera motion is not only linearly decodable but also geometrically organized. Based on these results, we apply geometry-aware spline-based steering in the model's latent representations to interpolate camera motion, yielding steered videos with smoother trajectories and more coherent temporal progression than linear interpolation.

Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3

Lassonde School of Engineering, York University, Toronto, Canada · Vector Institute, Toronto, Canada · FAIR, Meta Superintelligence Labs +2

Vision Foundation Models Video Representation Learning Representation Probing Physical Reasoning in Video

Aug 31, 2026cs.CV

Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos

Inferring object dynamics from visual observations is essential for intelligent agents to reason about and interact with the physical world, yet remains challenging due to the fundamental gap between visual evidence and intrinsic dynamics. Existing methods either rely on costly per-scene optimization, limiting efficiency and scalability, or directly map visual evidence to intrinsic dynamics without intermediate physical abstractions, making them prone to appearance and geometry shortcuts. To bridge this gap, we propose Analytic Dynamics, a feed-forward dynamics inference framework that introduces an intermediate physics-grounded dynamics representation between visual observations and intrinsic dynamics. Specifically, we leverage privileged physical states, including position, displacement, and deformation gradient fields, which are available in simulation, to learn a structured dynamics representation that is difficult to discover from visual observations alone. By aligning visual representations with this space, we equip visual models with a physics-grounded inductive bias, guiding them to capture dynamics-relevant patterns for material model classification and parameter regression. To facilitate this research, we develop a dynamics data generation pipeline and benchmark containing paired physical state trajectories, rendered videos, and ground-truth material models and parameters. Extensive experiments demonstrate that Analytic Dynamics achieves efficient, accurate, and generalizable dynamics inference from monocular videos.

Jailing Lin, Jikuan Zhang, Jianhua Sun

School of Artificial Intelligence, Shanghai Jiao Tong University

Materials Property Prediction Video Representation Learning System Identification Physics-Informed ML Inverse Dynamics

Aug 31, 2026cs.CV

MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI

Cardiac magnetic resonance imaging (CMR) produces rich sequential data such as temporal cine videos and spatial LGE/mapping stacks, yet most deep learning approaches process individual 2D slices, discarding this context. We present MR-JEPA, a self-supervised video foundation model for CMR that extends LeJEPA to 3D spatiotemporal inputs through tubelet tokenization, spatiotemporal masking augmentation, and initialization from a 2D CMR foundation model. Unlike prior CMR video models limited to cine data, MR-JEPA is pretrained on multi-sequence data (cine, LGE, mapping) from 10,505 patients across two centers without annotations. We evaluate the frozen encoder on six downstream tasks using a unified multi-view gated attention architecture: LV ejection fraction, RV ejection fraction, three myocardial strains (GLS, GCS, GRS), and four-class disease detection. MR-JEPA outperforms other compared methods on all five regression tasks, including both a domain-specific CMR model pretrained on more data with text supervision and a natural-video foundation model, achieving an LV EF MAE of 4.79% (r =0.764) and a GLS MAE of 1.87 (r=0.805), with 21-27% MAE reductions over baselines on strain tasks. For disease detection, MR-JEPA achieved a macro AUG of 0.868, remaining competitive with the domain-specific baseline despite using a fully self-supervised pretraining objective. These results demonstrate the potential of a unified video encoder for robust, multi-view utilization of diverse CMR sequences in clinical cardiac quantification and diagnosis.

Athira J. Jacob, Puneet Sharma, Dorin Comaniciu +1

Digital Technology and Innovation, Siemens Healthineers, Princeton, NJ, USA · Chair for Al in Healthcare and Medicine, Technical University of Munich (TUM) · TUM University Hospital, Munich, Germany +1

Medical Imaging Foundation Models Self-Supervised Pre-Training Medical Image Analysis Medical Diagnosis Video Representation Learning Cardiac MRI

Aug 31, 2026cs.CV

PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning

Cross-view video representation learning aims to capture viewpoint-invariant action semantics despite substantial appearance changes across egocentric and exocentric videos. However, existing methods encode each video as a unified embedding, where view-invariant and view-variant semantics inevitably entangle under co-occurrences - a failure mode we show persists even in cross-view methods explicitly trained for view-invariance. Our key insight is that a view-invariant feature is truly disentangled when it can be sufficiently recomposed with an arbitrary view-variant feature while preserving their independent semantics. Building on this, we propose PRISM, that decomposes video into view-invariant and view-variant latents and recompose them under language supervision encouraging clean decomposition of the two streams. PRISM achieves state-of-the-art results on EgoExo4D, EgoExoLearn, AE2, even surpassing in-domain models under zero-shot setting. Code is available at https://github.com/litcoderr/prism.

Youngchae Chee, Hosu Lee, Sungjune Park +2

KAIST · University of Illinois Urbana-Champaign

Disentangled Representation Learning Egocentric Video Understanding Video Representation Learning Invariant Representation Learning

Aug 13, 2026cs.CV

V-RAE: Rethinking Video Latent Spaces for Generation

Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization. A reconstruction-optimal latent space, however, need not be well suited to generative modeling. We propose V-RAE, a video representation autoencoder that builds compact generative latents on top of frozen vision foundation model representations. A lightweight temporal pooling module removes temporal redundancy while preserving semantic structure, and a video decoder reconstructs continuous motion from the compressed features. We evaluate V-RAE with four representative frozen encoders on video reconstruction, semantic probing, and class-conditional generation. V-RAE achieves 2.13 rFVD on K600, outperforming all evaluated large-scale pretrained video VAEs. Its latents retain substantially more semantic information than conventional video tokenizer latents. Under matched generation settings, our best variant achieves gFVD scores of 117.86 and 19.16 on UCF101 and K600, respectively, while converging up to 6x faster}. We further show that reconstruction quality alone is insufficient to characterize generative utility and introduce tFVD, a temporal-coherence diagnostic that correlates more reliably with downstream generation quality. Beyond video generation, V-RAE also improves future video prediction on Cityscapes over the Wan 2.2 VAE latent space under matched prediction settings. Taken together, the experiments show that frozen semantic representations can support video reconstruction, generation, and predictive modeling. The project page: https://v-rae.github.io/.

Minghui Guo, Shengqiong Wu, Hao Fei

National University of Singapore · University of Oxford

Autoencoders Video Representation Learning Video Generation Video Generation Evaluation

Aug 13, 2026cs.CV

A Controlled Study of Self-Supervised Image and Video Pretraining under Limited Resources

Visual foundation models are a cornerstone of image and video understanding but typically require large amounts of data and computation. The current scale required for pretraining visual foundation models may be unsustainable or unnecessary, and significant benefits arise when effective models can be obtained with fewer resources. To better understand how self-supervised learning (SSL) objectives behave under resource constraints, we conduct a controlled study of image and video SSL objectives under matched data, architecture, and compute budgets. We compare contrastive, reconstruction, feature-prediction, and diffusion objectives and evaluate both standalone and jointly trained image-video SSL formulations across a diverse set of image and video understanding tasks. Our results show that DINOv2-style pretraining consistently provides the strongest overall performance under limited resources. Furthermore, combining DINOv2 with video SSL objectives such as VideoMAE substantially improves image classification and segmentation performance, but degrades video tracking and camera-pose estimation performance, revealing an important tradeoff between semantic and geometric representation learning. These findings suggest that combining image and video SSL objectives can be beneficial in resource-limited settings, while highlighting the need for improved methods that better balance semantic, temporal, and geometric supervision.

Brunó B. Englert, Gijs Dubbelman

Eindhoven University of Technology

Vision Foundation Models Self-Supervised Pre-Training Video Representation Learning Self-Supervised Visual Representation Learning

Aug 13, 2026cs.CV

Learning Unified Video and Image Representation for Video Face Forgery Detection

Face forgery detection is crucial for preserving the security and integrity of facial data given the rapid developments in face manipulation techniques and deep generative models. Existing methods for video face forgery detection typically assume that all frames in a forged video are manipulated, while detecting partially forged videos that contain only a subset of altered frames remains challenging. To address this issue, we propose a novel framework, UVIF, that utilizes additional annotated images to provide fine-grained supervision for detecting partial forgeries in videos. UVIF employs a unified encoder and a multi-task learning paradigm to jointly model facial videos and images for boosted video face forgery detection. A 2D backbone with temporal fusion modules is employed as the unified encoder. A pseudo labeling process is designed for video frames to bridge their representations with those of static images. A video-oriented feature alignment strategy is further introduced to reduce the distribution gap between videos and images. Extensive experiments on benchmark datasets demonstrate the effectiveness of our framework, which outperforms state-of-theart methods in detecting partially forged videos while introducing no additional computational overhead. Our code is available at https://github.com/haotianll/UVIF.

Haotian Liu, Yang Liu, Guoying Zhao +1

Video Representation Learning Deepfake Detection

Aug 12, 2026cs.CV

AVA-Encoder: Towards Agent-Native Video Representation Learning

Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence of a structured video representation that is both faithful to film content and directly usable for agentic reasoning and manipulation. To address the challenge, we propose the Agentic Video Auto-Encoder (AVA-Encoder), a framework for learning agent-native video representations via agentic auto-encoding. AVA-Encoder transforms a video into a knowledge graph (KG) representation and then reconstructs it back into video. Its hierarchy and state nodes store structured text, while a linked asset layer holds generated images, audio, and video. Typed edges preserve the relations between these text descriptions and assets in a form that agents can easily understand, query, and edit. The video reconstruction differences drive a textual-gradient optimization framework, which expresses evaluation feedback as natural-language update directions for Data-Independent Encoding Policy Pseudo-Training in the outer loop and optional Data-Dependent KG Representation Refinement in the test-time inner loop. Extensive experiments show that AVA-Encoder improves by 20.7 percentage points over the strongest external baseline. In the controlled policy-only setting, its pseudo-trained shot-level Agentic Video Encoder policy also outperforms a carefully human-tuned policy while using 74.3% fewer system-prompt tokens. We release the complete AVA-Encoder framework, a reliable agentic video reconstruction benchmark, and the first dataset of high-quality film KG representations.

Chuyue Li, Jinpeng Yu, Haozhe Wang +7

Qwen Business Unit of Alibaba · ShanghaiTech University · The Hong Kong University of Science and Technology +2

Video Representation Learning

Aug 5, 2026cs.CV

Persistent Object Narratives for Token-Efficient Video Language Models

Video large language models (Video-LLMs) have made strong progress in open-ended video understanding. However, their visual interfaces remain token-intensive and provide limited explicit structure for linking recurring object evidence across time. We introduce SlotNarrative, a slot-based interface that organizes a video into persistent object narratives represented by compact object-state tokens. Rather than compressing frame-wise features before establishing temporal correspondence, SlotNarrative first groups visual features into object-like slots and then associates recurring observations with clip-level object entries through a lightweight, parameter-free memory that integrates multiple complementary matching cues. Each retained entry is serialized into two token types: an identity token that summarizes persistent object appearance and a set of state tokens that encode segment-level appearance, geometry, visibility, and trajectory information. This design yields an interface of only 144 allocated visual-token positions for a frozen Video-LLM, independent of the number of sampled frames. Across multiple datasets, SlotNarrative achieves a favorable trade-off between accuracy and visual-token count compared with prior compact Video-LLM interfaces. Experimental results establish persistent object narratives as a compact, structured, and temporally organized visual interface for Video-LLMs. Our code will be made publicly available.

Junzhe Chen, Siyuan Meng, Xiaojie Guo

Tianjin University

Visual Tokenization Video-Language Models Video Representation Learning Visual Token Compression Temporal Video Understanding

Jul 29, 2026cs.CV

Mitigating Compounding Error via Video Representation Regularization

Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window autoregressive inference suffers from severe error accumulation that degrades frame quality over time. Although this phenomenon has been widely observed, the underlying mechanism of compounding error and how to achieve stable long-horizon generation remain largely unresolved. In this paper, we investigate the internal representation dynamics of video world models and discover that compounding error is tightly coupled with dimensional collapse of hidden representations. Specifically, the effective rank of model representations sharply decreases at the onset of generation drift, revealing a strong connection between representational degradation and long-term rollout instability. Furthermore, we find that pure training data scaling fails to boost model resistance to error drift, contradicting mainstream scaling paradigms. To address this problem, we propose video representation regularization, a lightweight training constraint that stabilizes latent representations and suppresses iterative error accumulation. Compared with Diffusion Forcing, our method achieves improvements from 38.65 to 55.56 and from 44.37 to 72.08 on the Aesthetic Quality and Imaging Quality metrics of VBench. Our work establishes the first connection between autoregressive video drifting and model internal representations, adopts erank as a quantitative metric for error accumulation, reveals counterintuitive scaling limitations for video world models, and presents a simple yet effective regularization strategy to improve long video generation robustness.

Taiye Chen, Qi Zhang, Yisen Wang

Peking University

Video Diffusion Models Long-Horizon Video Generation Video Representation Learning Autoregressive Video Generation

Jul 28, 2026cs.CV

Explicit Layer Modeling for Video Object Insertion and Video Layer Decomposition

Most video editing systems still lack explicit layered video representations, limiting realistic compositing, object reuse, and consistent manipulation. This limitation is particularly evident in video object insertion and video layer decomposition, where existing methods lack direct supervision for foreground layers that capture both objects and their associated visual effects. We introduce TriLayer, a triplet video dataset containing aligned composite--background--foreground videos, where the foreground layers include both object appearance and associated visual effects. With aligned triplet supervision, TriLayer enables explicit supervised learning of layered video representations for the first time. Building on this dataset, we propose DBL-Diffusion, a dual-branch diffusion framework that jointly models scene-level RGB content and RGBA foreground layers through cross-branch interaction during denoising. We instantiate the framework in two tasks: DBL-Insert for layered object insertion, which generates explicit RGBA layers for realistic compositing and flexible post-editing, and DBL-Decompose for video layer decomposition, which recovers foreground and background layers using triplet supervision. Experiments demonstrate that explicit layer modeling substantially improves both insertion fidelity and decomposition quality.

Kyujin Han, Seungjoo Shin, Sunghyun Cho

POSTECH, Republic of Korea

Video Diffusion Models Video Editing Video Representation Learning