{"total":24,"rows":[{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2312.00634","title":"A Recent Survey of Vision Transformers for Medical Image Segmentation","created":"2023-12-01","cited_by_count":23,"area":null},{"id":"2308.13711","title":"EventTransAct: A video transformer-based framework for Event-camera based action recognition","created":"2023-08-25","cited_by_count":11,"area":null},{"id":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","cited_by_count":9,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2312.10930","title":"Deep Learning Approaches for Seizure Video Analysis: A Review","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2501.12681","title":"Can masking background and object reduce static bias for zero-shot action recognition?","created":"2025-01-22","cited_by_count":6,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2410.21275","title":"Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2506.05274","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","created":"2025-06-05","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":"2310.14556","title":"S3Aug: Segmentation, Sampling, and Shift for Action Recognition","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2412.03214","title":"Continual Low-Rank Scaled Dot-product Attention","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2210.17412","title":"Adversarial Domain Adaptation for Action Recognition Around the Clock","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2502.12415","title":"Gaseous Object Detection","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2508.02978","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2401.14675","title":"Multi-model learning by sequential reading of untrimmed videos for action recognition","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2407.12805","title":"Dark Transformer: A Video Transformer for Action Recognition in the Dark","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2410.15343","title":"POSE: Pose estimation Of virtual Sync Exhibit system","created":"2024-10-20","cited_by_count":0,"area":null},{"id":"2505.03315","title":"Artificial Behavior Intelligence: Technology, Challenges, and Future Directions","created":"2025-05-06","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2510.03558","title":"Real-Time Assessment of Bystander Situation Awareness in Drone-Assisted First Aid","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2512.16133","title":"Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space","created":"2025-12-18","cited_by_count":0,"area":null}],"next_cursor":null}