OpenCodePapers

natural-language-moment-retrieval-on-tacos

VideoNatural Language Moment Retrieval
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeR@1,IoU=0.3R@1,IoU=0.5R@1,IoU=0.7R@5,IoU=0.1R@5,IoU=0.3R@5,IoU=0.5mIoUModelNameReleaseDate
Saliency-Guided DETR for Moment Retrieval and Highlight Detection✓ Link58.1046.4033.9042.40SG-DETR (w/ PT)2024-10-02
LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection✓ Link 57.61 44.3126.2440.30LD-DETR2025-01-18
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos✓ Link57.3646.7981.0571.13DeCafNet2025-05-22
Saliency-Guided DETR for Moment Retrieval and Highlight Detection✓ Link56.7144.7029.9040.90SG-DETR2024-10-02
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos✓ Link56.6941.5426.7739.31BAM-DETR2023-11-30
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding✓ Link53.7141.7624.7437.61FlashVTG2024-12-18
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval✓ Link52.7340.1222.7836.55LLMEPET2024-07-21
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding✓ Link52.2339.6122.2336.48CG-DETR2023-11-15
UniVTG: Towards Unified Video-Language Temporal Grounding✓ Link51.4434.9721.0735.76UniVTG2023-07-31
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos✓ Link48.2936.07GVL (paragraph-level)2023-03-11
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos✓ Link45.9234.57GVL2023-03-11
VLG-Net: Video-Language Graph Matching Network for Video Grounding✓ Link45.4634.1981.8070.3856.56VLG-Net2020-11-19
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection✓ Link36.3923.32UVCOM2023-11-28
Check out how to contribute new results.