{"total":34,"rows":[{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190,"area":null},{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166,"area":null},{"id":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148,"area":null},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79,"area":null},{"id":"2107.09609","title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","created":"2021-07-20","cited_by_count":72,"area":null},{"id":"2401.02309","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2404.00801","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","created":"2024-03-31","cited_by_count":34,"area":null},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32,"area":null},{"id":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31,"area":null},{"id":"2407.15051","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","created":"2024-07-21","cited_by_count":30,"area":null},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15,"area":null},{"id":"2401.08086","title":"Spatial-Semantic Collaborative Cropping for User Generated Content","created":"2024-01-16","cited_by_count":13,"area":null},{"id":"2403.14174","title":"Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding","created":"2024-03-21","cited_by_count":12,"area":null},{"id":"2507.12062","title":"MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2111.15050","title":"AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant","created":"2021-11-30","cited_by_count":8,"area":null},{"id":"2501.10787","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2202.01031","title":"MMSys'22 Grand Challenge on AI-based Video Production for Soccer","created":"2022-02-02","cited_by_count":6,"area":null},{"id":"2210.05840","title":"LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2210.11707","title":"Video Summarization Overview","created":"2022-10-21","cited_by_count":6,"area":null},{"id":"2404.01745","title":"Unleash the Potential of CLIP for Video Highlight Detection","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2407.13933","title":"Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence","created":"2024-07-18","cited_by_count":6,"area":null},{"id":"2310.13859","title":"Not all Fake News is Written: A Dataset and Analysis of Misleading Video Headlines","created":"2023-10-20","cited_by_count":5,"area":null},{"id":"2201.09049","title":"LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN","created":"2022-01-22","cited_by_count":4,"area":null},{"id":"2210.08481","title":"TLDW: Extreme Multimodal Summarisation of News Videos","created":"2022-10-16","cited_by_count":3,"area":null},{"id":"2503.06820","title":"Towards Fine-Grained Video Question Answering","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2508.04924","title":"Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2211.12493","title":"Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior","created":"2022-11-22","cited_by_count":1,"area":null},{"id":"2304.12561","title":"TCR: Short Video Title Generation and Cover Selection with Attention Refinement","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2201.09077","title":"LTC-GIF: Attracting More Clicks on Feature-length Sports Videos","created":"2022-01-22","cited_by_count":0,"area":null},{"id":"2202.02930","title":"Towards Micro-video Thumbnail Selection via a Multi-label Visual-semantic Embedding Model","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2506.03171","title":"EdgeVidSum: Real-Time Personalized Video Summarization at the Edge","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2609.32280","title":"HeroFrame-Bench: Reference-Anchored Evaluation via Rubric--Ranking Co-Evolution for Movie Hero Frame Selection","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.04931","title":"Billion-Scale Thumbnail Optimization for Uncurated Short-Form Videos via Multi-Armed Bandits","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}