{"total":38,"rows":[{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","cited_by_count":86,"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":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"area":null},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46,"area":null},{"id":"2209.11572","title":"Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval","created":"2022-09-23","cited_by_count":43,"area":null},{"id":"2303.07863","title":"You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos","created":"2023-03-14","cited_by_count":41,"area":null},{"id":"2208.14882","title":"Hierarchical Local-Global Transformer for Temporal Sentence Grounding","created":"2022-08-31","cited_by_count":38,"area":null},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36,"area":null},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35,"area":null},{"id":"2207.13457","title":"Reducing the Vision and Language Bias for Temporal Sentence Grounding","created":"2022-07-27","cited_by_count":35,"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":"2201.05307","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","created":"2022-01-14","cited_by_count":30,"area":null},{"id":"2301.01871","title":"Hypotheses Tree Building for One-Shot Temporal Sentence Localization","created":"2023-01-05","cited_by_count":25,"area":null},{"id":"2201.00457","title":"Exploring Motion and Appearance Information for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":24,"area":null},{"id":"2207.14698","title":"Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding","created":"2022-07-29","cited_by_count":22,"area":null},{"id":"2207.13450","title":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","created":"2022-07-27","cited_by_count":21,"area":null},{"id":"2301.00514","title":"Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding","created":"2023-01-02","cited_by_count":19,"area":null},{"id":"2306.07515","title":"A Survey on Video Moment Localization","created":"2023-06-13","cited_by_count":18,"area":null},{"id":"2302.09850","title":"Constraint and Union for Partially-Supervised Temporal Sentence Grounding","created":"2023-02-20","cited_by_count":14,"area":null},{"id":"2210.12444","title":"Weakly-Supervised Temporal Article Grounding","created":"2022-10-22","cited_by_count":11,"area":null},{"id":"2305.18969","title":"MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2412.07157","title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2605.29793","title":"Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2509.23867","title":"Sim-DETR: Unlock DETR for Temporal Sentence Grounding","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2305.04123","title":"Transform-Equivariant Consistency Learning for Temporal Sentence Grounding","created":"2023-05-06","cited_by_count":3,"area":null},{"id":"2503.06526","title":"TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2112.10066","title":"LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach","created":"2021-12-19","cited_by_count":2,"area":null},{"id":"2508.04273","title":"Audio Does Matter: Importance-Aware Multi-Granularity Fusion for Video Moment Retrieval","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2605.30742","title":"Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2203.03838","title":"Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding","created":"2022-03-08","cited_by_count":1,"area":null},{"id":"2410.05767","title":"Grounding is All You Need? Dual Temporal Grounding for Video Dialog","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2303.07748","title":"Generation-Guided Multi-Level Unified Network for Video Grounding","created":"2023-03-14","cited_by_count":0,"area":null},{"id":"2501.02811","title":"First-place Solution for Streetscape Shop Sign Recognition Competition","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2505.24282","title":"LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2604.02860","title":"A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos","created":"2026-04-03","cited_by_count":0,"area":null}],"next_cursor":null}