ML Research Wiki / Benchmarks / Highlight Detection / TvSum

TvSum

Highlight Detection Benchmark

Performance Over Time

📊 Showing 7 results | 📏 Metric: mAP

Top Performing Models

Rank Model Paper mAP Date Code
1 FlashVTG FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding 88.00 2024-12-18 📦 zhuo-cao/flashvtg
2 SG-DETR Saliency-Guided DETR for Moment Retrieval and Highlight Detection 87.10 2024-10-02 📦 ai-forever/sg-detr
3 CG-DETR Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding 86.80 2023-11-15 📦 wjun0830/qd-detr 📦 wjun0830/cgdetr
4 QD-DETR Query-Dependent Video Representation for Moment Retrieval and Highlight Detection 86.60 2023-03-24 📦 wjun0830/qd-detr
5 UVCOM (train from scratch) Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection 86.30 2023-11-28 📦 easonxiao-888/uvcom
6 QD-DETR (only Video) Query-Dependent Video Representation for Moment Retrieval and Highlight Detection 85.00 2023-03-24 📦 wjun0830/qd-detr
7 UMT UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection 83.10 2022-03-23 📦 tencentarc/umt 📦 MindCode-4/code-5 📦 MS-P3/code7

All Papers (7)

zhuo-cao/flashvtg
ai-forever/sg-detr
wjun0830/qd-detr wjun0830/cgdetr
wjun0830/qd-detr
easonxiao-888/uvcom
wjun0830/qd-detr
tencentarc/umt MindCode-4/code-5 MS-P3/code7