{"total":19,"rows":[{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2203.09463","title":"FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos","created":"2022-03-17","cited_by_count":69,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43,"area":null},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31,"area":null},{"id":"2312.00362","title":"Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement","created":"2023-12-01","cited_by_count":21,"area":null},{"id":"2212.05638","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","created":"2022-12-12","cited_by_count":20,"area":null},{"id":"2203.16755","title":"Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models","created":"2022-03-31","cited_by_count":14,"area":null},{"id":"2308.04770","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2407.18289","title":"MARINE: A Computer Vision Model for Detecting Rare Predator-Prey Interactions in Animal Videos","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2505.13429","title":"Understanding Complexity in VideoQA via Visual Program Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2205.11394","title":"Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition","created":"2022-05-23","cited_by_count":2,"area":null},{"id":"2308.11249","title":"Video BagNet: short temporal receptive fields increase robustness in long-term action recognition","created":"2023-08-22","cited_by_count":2,"area":null},{"id":"2112.02523","title":"STSM: Spatio-Temporal Shift Module for Efficient Action Recognition","created":"2021-12-05","cited_by_count":1,"area":null},{"id":"2504.17132","title":"Latent Video Dataset Distillation","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2509.20899","title":"Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification","created":"2025-09-25","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":"2403.08420","title":"ALow-Cost Real-Time Framework for Industrial Action Recognition Using Foundation Models","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2609.33419","title":"TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}