{"total":62,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"id":"2106.11250","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","created":"2021-06-21","cited_by_count":56,"area":null},{"id":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52,"area":null},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44,"area":null},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40,"area":null},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2104.02116","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","created":"2021-04-05","cited_by_count":33,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2401.03717","title":"Universal Time-Series Representation Learning: A Survey","created":"2024-01-08","cited_by_count":30,"area":null},{"id":"2308.11606","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2210.07886","title":"PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning","created":"2022-10-14","cited_by_count":23,"area":null},{"id":"2103.16565","title":"Learning Representational Invariances for Data-Efficient Action Recognition","created":"2021-03-30","cited_by_count":22,"area":null},{"id":"2311.07603","title":"PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment","created":"2023-11-11","cited_by_count":19,"area":null},{"id":"2302.07702","title":"Audio-Visual Contrastive Learning with Temporal Self-Supervision","created":"2023-02-15","cited_by_count":18,"area":null},{"id":"2307.16453","title":"Every Mistake Counts in Assembly","created":"2023-07-31","cited_by_count":18,"area":null},{"id":"2305.19478","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2105.14158","title":"SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation","created":"2021-05-29","cited_by_count":15,"area":null},{"id":"2112.06909","title":"Hallucinating Pose-Compatible Scenes","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2303.13505","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","created":"2023-03-23","cited_by_count":14,"area":null},{"id":"2301.00794","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","created":"2023-01-02","cited_by_count":13,"area":null},{"id":"2505.18816","title":"Reasoning Segmentation for Images and Videos: A Survey","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2101.07719","title":"Deep Feedback Inverse Problem Solver","created":"2021-01-19","cited_by_count":11,"area":null},{"id":"2411.17776","title":"Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search","created":"2024-11-26","cited_by_count":11,"area":null},{"id":"2210.10039","title":"How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios","created":"2022-10-18","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2311.01620","title":"ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2209.12074","title":"Self-supervised Learning for Unintentional Action Prediction","created":"2022-09-24","cited_by_count":7,"area":null},{"id":"2311.05669","title":"Multi-Modal Gaze Following in Conversational Scenarios","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2401.11790","title":"Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Review","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2107.05140","title":"Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2402.05917","title":"Point-VOS: Pointing Up Video Object Segmentation","created":"2024-02-08","cited_by_count":5,"area":null},{"id":"2106.02602","title":"InDiD: Instant Disorder Detection via Representation Learning","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2209.11870","title":"Leveraging Self-Supervised Training for Unintentional Action Recognition","created":"2022-09-23","cited_by_count":3,"area":null},{"id":"2402.19405","title":"Navigating Hallucinations for Reasoning of Unintentional Activities","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2410.01180","title":"UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2501.02427","title":"MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance","created":"2025-01-05","cited_by_count":3,"area":null},{"id":"2503.04666","title":"What Are You Doing? A Closer Look at Controllable Human Video Generation","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2606.02443","title":"PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2105.09909","title":"PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection","created":"2021-05-06","cited_by_count":2,"area":null},{"id":"2212.10870","title":"MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2506.01466","title":"Towards Scalable Video Anomaly Retrieval: A Synthetic Video-Text Benchmark","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2605.16403","title":"When Vision Speaks for Sound","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2103.17261","title":"Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos","created":"2021-03-31","cited_by_count":1,"area":null},{"id":"2205.05609","title":"Video-ReTime: Learning Temporally Varying Speediness for Time Remapping","created":"2022-05-11","cited_by_count":1,"area":null},{"id":"2409.01445","title":"Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2505.19889","title":"OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.23433","title":"SPIKE-RL: Video-LLMs meet Bayesian Surprise","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2603.27410","title":"Grounding Social Perception in Intuitive Physics","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2608.28406","title":"Post-Training VLMs for Video Mistake Detection","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2203.12344","title":"How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2204.13548","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2212.02978","title":"Muscles in Action","created":"2022-12-05","cited_by_count":0,"area":null},{"id":"2504.07597","title":"Learning Long Short-Term Intention within Human Daily Behaviors","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2508.18705","title":"Enhancing Video-Based Robot Failure Detection Using Task Knowledge","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2508.21770","title":"What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2608.04426","title":"Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.36924","title":"Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}