{"total":78,"rows":[{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2311.01813","title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation","created":"2023-11-03","cited_by_count":122,"area":null},{"id":"2103.10699","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","created":"2021-03-19","cited_by_count":78,"area":null},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2310.09289","title":"An Unbiased Look at Datasets for Visuo-Motor Pre-Training","created":"2023-10-13","cited_by_count":42,"area":null},{"id":"2104.00682","title":"Multiview Pseudo-Labeling for Semi-supervised Learning from Video","created":"2021-04-01","cited_by_count":32,"area":null},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2107.07695","title":"Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss","created":"2021-07-16","cited_by_count":24,"area":null},{"id":"2510.18873","title":"DSI-Bench: A Benchmark for Dynamic Spatial Intelligence","created":"2025-10-21","cited_by_count":23,"area":null},{"id":"2305.15372","title":"Learning high-level visual representations from a child's perspective without strong inductive biases","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15,"area":null},{"id":"2304.08210","title":"ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding","created":"2023-04-17","cited_by_count":14,"area":null},{"id":"2204.13340","title":"The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction","created":"2022-04-28","cited_by_count":13,"area":null},{"id":"2211.05039","title":"Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task","created":"2022-11-09","cited_by_count":13,"area":null},{"id":"2211.10412","title":"Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2312.00598","title":"Learning from One Continuous Video Stream","created":"2023-12-01","cited_by_count":11,"area":null},{"id":"2407.17085","title":"OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos","created":"2024-07-24","cited_by_count":10,"area":null},{"id":"2211.02077","title":"Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization","created":"2022-11-03","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":"2110.13479","title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","created":"2021-10-26","cited_by_count":8,"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":"2405.20030","title":"EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2202.02212","title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2203.09230","title":"Surgical Workflow Recognition: from Analysis of Challenges to Architectural Study","created":"2022-03-17","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":"2402.00300","title":"Self-supervised learning of video representations from a child's perspective","created":"2024-02-01","cited_by_count":6,"area":null},{"id":"2109.14306","title":"Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2511.02767","title":"Dynamic Reflections: Probing Video Representations with Text Alignment","created":"2025-11-04","cited_by_count":5,"area":null},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2107.11494","title":"TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos","created":"2021-07-24","cited_by_count":4,"area":null},{"id":"2109.11523","title":"How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2202.07308","title":"HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2306.02014","title":"Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts","created":"2023-06-03","cited_by_count":4,"area":null},{"id":"2412.09037","title":"Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2507.01028","title":"Dual Perspectives on Non-Contrastive Self-Supervised Learning","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2510.11204","title":"Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2209.04780","title":"MAiVAR: Multimodal Audio-Image and Video Action Recognizer","created":"2022-09-11","cited_by_count":3,"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":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2304.14104","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2408.12099","title":"Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computing","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2510.07828","title":"MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2512.10725","title":"Video Depth Propagation","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2112.11384","title":"Sports Video: Fine-Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2021","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2203.03796","title":"PAMI-AD: An Activity Detector Exploiting Part-attention and Motion Information in Surveillance Videos","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2208.01910","title":"Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2212.12141","title":"Human Activity Recognition in an Open World","created":"2022-12-23","cited_by_count":2,"area":null},{"id":"2301.13576","title":"Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2303.04068","title":"VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building [Technical Report]","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2407.18067","title":"HVM-1: Large-scale video models pretrained with nearly 5000 hours of human-like video data","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2203.05156","title":"End-to-End Semantic Video Transformer for Zero-Shot Action Recognition","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2303.01105","title":"Evidence-empowered Transfer Learning for Alzheimer's Disease","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2303.14584","title":"Learning video embedding space with Natural Language Supervision","created":"2023-03-25","cited_by_count":1,"area":null},{"id":"2305.01733","title":"Cross-view Action Recognition via Contrastive View-invariant Representation","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2308.09685","title":"Audiovisual Moments in Time: A Large-Scale Annotated Dataset of Audiovisual Actions","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2310.01904","title":"Beyond the Benchmark: Detecting Diverse Anomalies in Videos","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2310.19554","title":"Harvest Video Foundation Models via Efficient Post-Pretraining","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2511.10979","title":"PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2603.03564","title":"Modeling Cross-vision Synergy for Unified Large Vision Model","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2606.14958","title":"MVEB: Massive Video Embedding Benchmark","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2306.10858","title":"Multi-Granularity Hand Action Detection","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2310.00831","title":"Action Recognition Utilizing YGAR Dataset","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2406.07191","title":"MeMSVD: Long-Range Temporal Structure Capturing Using Incremental SVD","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2407.05647","title":"Learning to Adapt Category Consistent Meta-Feature of CLIP for Few-Shot Classification","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2508.07330","title":"Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2511.21202","title":"Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2605.24488","title":"Appearance-Invariant Detection of Suggestive Motion via Laban Movement Descriptors","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2609.31665","title":"Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.13549","title":"ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18176","title":"Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}