{"total":21,"rows":[{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2306.06842","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","created":"2023-06-12","cited_by_count":23,"area":null},{"id":"2404.14471","title":"Narrative Action Evaluation with Prompt-Guided Multimodal Interaction","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2311.02538","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","created":"2023-11-05","cited_by_count":17,"area":null},{"id":"2404.09951","title":"Unifying Global and Local Scene Entities Modelling for Precise Action Spotting","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2305.17648","title":"Z-GMOT: Zero-shot Generic Multiple Object Tracking","created":"2023-05-28","cited_by_count":7,"area":null},{"id":"2403.04924","title":"$\\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2411.17130","title":"TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching","created":"2024-11-26","cited_by_count":6,"area":null},{"id":"2212.06206","title":"Contextual Explainable Video Representation: Human Perception-based Understanding","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2409.11223","title":"Multimodal Attention-Enhanced Feature Fusion-based Weekly Supervised Anomaly Violence Detection","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2310.20057","title":"SolarFormer: Multi-scale Transformer for Solar PV Profiling","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2311.04480","title":"CLearViD: Curriculum Learning for Video Description","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2404.11429","title":"CarcassFormer: An End-to-end Transformer-based Framework for Simultaneous Localization, Segmentation and Classification of Poultry Carcass Defect","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2411.05780","title":"GazeSearch: Radiology Findings Search Benchmark","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2309.09611","title":"Collaborative Three-Stream Transformers for Video Captioning","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2405.04489","title":"S3Former: Self-supervised High-resolution Transformer for Solar PV Profiling","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2407.12005","title":"VCEval: Rethinking What is a Good Educational Video and How to Automatically Evaluate It","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2409.00295","title":"Box2Flow: Instance-based Action Flow Graphs from Videos","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.09377","title":"GEM-VPC: A dual Graph-Enhanced Multimodal integration for Video Paragraph Captioning","created":"2024-10-12","cited_by_count":0,"area":null},{"id":"2511.13039","title":"MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization","created":"2025-11-17","cited_by_count":0,"area":null}],"next_cursor":null}