Highlight Detection on QVHighlights (val)
88.4HIT@1GroundVTS-I
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GroundVTS-IBackbone=InternVL3.5-8B2026.04 | 88.4 | 52.5 | — | |
| FlashVTGBackbone=InternVideo22024.12 | 72.9 | 44.15 | — | |
| HL-CLIPconfiguration=HL-CLIP-2 (SP)2024.04 | 72.4 | 42.37 | — | |
| InternVideo2-6BFeature=InternVideo2_S2-6B2024.03 | 72 | 42.9 | — | |
| NumPro2026.04 | 70.7 | 40.5 | — | |
| InternVideo2-1BFeature=InternVideo2_S2-1B2024.03 | 69.74 | 42.36 | — | |
| FlashVTGBackbone=SF+C2024.12 | 67.61 | 41.39 | — | |
| CG-DETR2024.04 | 66.71 | 40.79 | — | |
| CG-DETRBackbone=SF+C2024.12 | 66.71 | 40.79 | — | |
| CG-DETRFeatures=Slowfast + CLIP2023.11 | 66.7 | — | 40.8 | |
| CLIP+SlowFastFeature=CLIP+SlowFast2024.03 | 66.21 | 40.33 | — | |
| VCL2024.04 | 65.74 | 38.84 | — | |
| LLMEPETBackbone=SF+C2024.12 | 65.03 | 40.52 | — | |
| UMTFeatures=Slowfast + CLIP2023.11 | 64.2 | — | 39.9 | |
| UMT2024.04 | 64.19 | 39.85 | — | |
| UMTaudio modality=true2024.04 | 64.19 | 39.85 | — | |
| CLIPFeature=CLIP2024.03 | 64.19 | 39.83 | — | |
| UMTBackbone=SF+C2024.12 | 64.19 | 39.85 | — | |
| R2-TuningBackbone=CLIP2024.12 | 64.13 | 39.45 | — | |
| TaskWeave2024.04 | 63.68 | 39.28 | — | |
| QD-DETR2024.04 | 63.03 | 39.13 | — | |
| QD-DETR2024.04 | 63.03 | 39.13 | — | |
| QD-DETRBackbone=SF+C2024.12 | 63.03 | 39.13 | — | |
| QD-DETRFeatures=Slowfast + CLIP2023.11 | 63 | — | 39.1 | |
| UniVGT2024.04 | 61.81 | 38.83 | — | |
| UniVTGpretrain-finetune paradigm=true2024.04 | 61.81 | 38.83 | — | |
| UniVTGBackbone=SF+C2024.12 | 61.81 | 38.83 | — | |
| UniVTGFeatures=Slowfast + CLIP2023.11 | 61.8 | — | 38.8 | |
| GroundVTS-QBackbone=Qwen2.5VL-7B2026.04 | 58.8 | 35.7 | — | |
| EaTRFeatures=Slowfast + CLIP2023.11 | 58.7 | — | 37.2 | |
| EaTR2024.04 | 58.65 | 37.15 | — | |
| EaTR2024.04 | 58.65 | 37.15 | — | |
| EaTRBackbone=SlowFast R-50, CLIP-B/32, PANN, Post Pre-train=No, #Params=9.0M2024.03 | 58.65 | — | 37.15 | |
| EaTRBackbone=SF+C2024.12 | 58.65 | 37.15 | — | |
| M-DETRFeatures=Slowfast + CLIP2023.11 | 55.6 | — | 35.7 | |
| Moment-DETR2024.04 | 55.55 | 35.65 | — | |
| Moment-DETR2024.04 | 55.55 | 35.65 | — | |
| M-DETRBackbone=SF+C2024.12 | 55.55 | 35.65 | — | |
| UniVTG2026.04 | 55.3 | 27 | — | |
| Qwen2.5VL-7B-GBackbone=Qwen2.5VL-7B, SFT=Grounding-FT2026.04 | 44.5 | 34.4 | — | |
| InternVL3.5-8B-GBackbone=InternVL3.5-8B, SFT=Grounding-FT2026.04 | 39.8 | 31.9 | — | |
| VTG-LLM2026.04 | 33.5 | 16.5 | — | |
| TimeChat2026.04 | 23.9 | 14.5 | — | |
| Qwen2.5VL-7BBackbone=Qwen2.5VL-7B2026.04 | 0.6 | 24.9 | — | |
| InternVL3.5-8BBackbone=InternVL3.5-8B2026.04 | 0.32 | 24.8 | — |