{"total":19,"rows":[{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148,"area":null},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2303.08409","title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","created":"2023-03-15","cited_by_count":40,"area":null},{"id":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36,"area":null},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35,"area":null},{"id":"2211.16636","title":"Iterative Scene Graph Generation with Generative Transformers","created":"2022-11-30","cited_by_count":22,"area":null},{"id":"2406.06044","title":"FRAG: Frequency Adapting Group for Diffusion Video Editing","created":"2024-06-10","cited_by_count":15,"area":null},{"id":"2306.16638","title":"A negation detection assessment of GPTs: analysis with the xNot360 dataset","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2311.02018","title":"Active Reasoning in an Open-World Environment","created":"2023-11-03","cited_by_count":8,"area":null},{"id":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2310.04671","title":"Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction","created":"2023-10-07","cited_by_count":4,"area":null},{"id":"2305.01928","title":"Visual Transformation Telling","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2309.13446","title":"Video Timeline Modeling For News Story Understanding","created":"2023-09-23","cited_by_count":3,"area":null},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2401.10805","title":"Learning to Visually Connect Actions and their Effects","created":"2024-01-19","cited_by_count":2,"area":null},{"id":"2506.00101","title":"EgoVIS@CVPR: What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.10806","title":"Who Benefits from AI Explanations? Towards Accessible and Interpretable Systems","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2510.15470","title":"MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval","created":"2025-10-17","cited_by_count":0,"area":null}],"next_cursor":null}