{"total":25,"rows":[{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127,"area":null},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49,"area":null},{"id":"2109.01066","title":"4D-Net for Learned Multi-Modal Alignment","created":"2021-09-02","cited_by_count":44,"area":null},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35,"area":null},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22,"area":null},{"id":"2311.18840","title":"Just Add $\\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living","created":"2023-11-30","cited_by_count":19,"area":null},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15,"area":null},{"id":"2308.14500","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","created":"2023-08-28","cited_by_count":15,"area":null},{"id":"2310.10059","title":"Flow Dynamics Correction for Action Recognition","created":"2023-10-16","cited_by_count":12,"area":null},{"id":"2305.06437","title":"Self-Supervised Video Representation Learning via Latent Time Navigation","created":"2023-05-10","cited_by_count":11,"area":null},{"id":"2103.14633","title":"Visionary: Vision architecture discovery for robot learning","created":"2021-03-26","cited_by_count":4,"area":null},{"id":"2108.12957","title":"Searching for Two-Stream Models in Multivariate Space for Video Recognition","created":"2021-08-30","cited_by_count":4,"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":"2411.15731","title":"Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2506.20342","title":"Feature Hallucination for Self-supervised Action Recognition","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2411.02065","title":"AM Flow: Adapters for Temporal Processing in Action Recognition","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2112.04710","title":"Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search","created":"2021-12-09","cited_by_count":0,"area":null},{"id":"2306.09331","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2502.07277","title":"Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2503.14524","title":"Salient Temporal Encoding for Dynamic Scene Graph Generation","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2603.04509","title":"Recognition of Daily Activities through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living","created":"2026-03-04","cited_by_count":0,"area":null}],"next_cursor":null}