{"list":"other","total":67,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2507.04447","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","created":"2025-07-06","cited_by_count":213},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"1511.06432","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","created":"2015-11-19","cited_by_count":148},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","cited_by_count":126},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2402.00847","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","created":"2024-02-01","cited_by_count":120},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"1804.06055","title":"Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation","created":"2018-04-17","cited_by_count":106},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80},{"id":"2009.05769","title":"Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning","created":"2020-09-12","cited_by_count":66},{"id":"2410.24211","title":"DELTA: Dense Efficient Long-range 3D Tracking for any video","created":"2024-10-31","cited_by_count":65},{"id":"2312.00786","title":"Dense Optical Tracking: Connecting the Dots","created":"2023-12-01","cited_by_count":61},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45},{"id":"1712.08416","title":"On the Integration of Optical Flow and Action Recognition","created":"2017-12-22","cited_by_count":42},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39},{"id":"2504.05579","title":"TAPNext: Tracking Any Point (TAP) as Next Token Prediction","created":"2025-04-08","cited_by_count":37},{"id":"2506.21526","title":"WAFT: Warping-Alone Field Transforms for Optical Flow","created":"2025-06-26","cited_by_count":34},{"id":"2206.02846","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","created":"2022-06-06","cited_by_count":26},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23},{"id":"2403.11186","title":"NetTrack: Tracking Highly Dynamic Objects with a Net","created":"2024-03-17","cited_by_count":22},{"id":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19},{"id":"2207.06261","title":"Is Appearance Free Action Recognition Possible?","created":"2022-07-13","cited_by_count":16},{"id":"2408.11208","title":"PooDLe: Pooled and dense self-supervised learning from naturalistic videos","created":"2024-08-20","cited_by_count":11},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11},{"id":"2407.18249","title":"Trajectory-aligned Space-time Tokens for Few-shot Action Recognition","created":"2024-07-25","cited_by_count":10},{"id":"2509.17141","title":"History-Aware Visuomotor Policy Learning via Point Tracking","created":"2025-09-21","cited_by_count":10},{"id":"2511.23428","title":"DisMo: Disentangled Motion Representations for Open-World Motion Transfer","created":"2025-11-28","cited_by_count":10},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10},{"id":"2508.03695","title":"Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition","created":"2025-08-05","cited_by_count":7},{"id":"2604.10582","title":"TAPNext++: What's Next for Tracking Any Point (TAP)?","created":"2026-04-12","cited_by_count":6},{"id":"2502.21201","title":"The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition","created":"2025-02-28","cited_by_count":5},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4},{"id":"2603.27268","title":"TrackMAE: Video Representation Learning via Track Mask and Predict","created":"2026-03-28","cited_by_count":3},{"id":"2604.02586","title":"TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction","created":"2026-04-02","cited_by_count":3},{"id":"1606.04698","title":"Invariant recognition drives neural representations of action sequences","created":"2016-06-15","cited_by_count":2},{"id":"2602.14705","title":"It's a Matter of Time: Three Lessons on Long-Term Motion for Perception","created":"2026-02-16","cited_by_count":2},{"id":"2601.03667","title":"TRec: Learning Hand-Object Interactions through 2D Point Track Motion","created":"2026-01-07","cited_by_count":1}],"next_cursor":null}