Temporal Action Localization on ActivityNet 1.3 (75%-25%)
53.8mAP@0.50Ti-FAD
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ti-FADVenue=NeurIPS’24, Prompt Tuning=false, Text Feature=CLIP-B2025.11 | 53.8 | 34.8 | 7 | 34.7 | |
| MGCA-NetVenue=-, Prompt Tuning=false, Text Feature=CLIP-B2025.11 | 52.8 | 35.6 | 8.2 | 35 | |
| ConTransData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 51.9 | 33.1 | 12.2 | 35.2 | |
| ZEETADTraining-based=Yes2026.05 | 51 | 33.4 | 5.9 | 32.5 | |
| ZEETADVenue=WACV’24, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 51 | 33.4 | 5.9 | 32.5 | |
| UnLoctraining_mode=training-based2024.04 | 48.8 | — | — | — | |
| UnLocTraining-based=Yes2026.05 | 48.8 | — | — | — | |
| GAPData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 47.6 | 32.5 | 8.6 | 31.8 | |
| STOV-TALVenue=WACV’25, Prompt Tuning=false, Text Feature=CLIP-B2025.11 | 47 | 28.1 | 1.6 | 27.9 | |
| OVFormerVenue=BMVC’24, Prompt Tuning=false, Text Feature=DINOv22025.11 | 46.7 | 29.4 | 6.1 | 29.5 | |
| GRIZALData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 46.4 | 32.5 | 6.8 | 30.1 | |
| mProTEAData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 44.5 | 27.4 | 7.9 | 27.6 | |
| mProTEAVenue=TCSVT’24, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 44.5 | 27.4 | 7.9 | 27.6 | |
| DeTALVenue=TPAMI’24, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 39.3 | 26.4 | 5 | 25.8 | |
| STALEtraining_mode=training-based2024.04 | 38.2 | 25.2 | 6 | 24.9 | |
| STALETraining-based=Yes2026.05 | 38.2 | 25.2 | 6 | 24.9 | |
| STALEData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 38.2 | 25.2 | 6 | 24.9 | |
| STABLEVenue=ECCV’22, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 38.2 | 25.2 | 6 | 24.9 | |
| EffPrompttraining_mode=training-based2024.04 | 37.6 | 22.9 | 3.8 | 23.1 | |
| EffPromptTraining-based=Yes2026.05 | 37.6 | 22.9 | 3.8 | 23.1 | |
| EffPromptData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 37.6 | 22.9 | 3.8 | 23.1 | |
| Eff-PromptVenue=ECCV’22, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 37.6 | 22.9 | 3.8 | 23.1 | |
| UnLoc-BVenue=ICCV’23, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 36.9 | — | — | — | |
| CLIP16 w/ Detectortraining_mode=training-based2024.04 | 35.6 | 20.4 | 2.1 | 20.2 | |
| Detector + CLIPTraining-based=Yes2026.05 | 35.6 | 20.4 | 2.1 | 20.2 | |
| B-IData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 35.6 | 20.4 | 2.1 | 20.2 | |
| B-IVenue=-, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 35.6 | 20.4 | 2.1 | 20.2 | |
| TEGUTraining-based=No2026.05 | 34.7 | 19.6 | 2.8 | 19 | |
| B-IIData split Train:Test=75:25, Protocol=Zero-shot, Setting=Open-set2026.05 | 32.6 | 18.5 | 5.8 | 19.6 | |
| B-IIVenue=-, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 32.6 | 18.5 | 5.8 | 19.6 | |
| T3ALtraining_mode=Zero-shot2024.04 | 28.1 | 14.9 | 3.3 | 15.4 | |
| T3ALTraining-based=No2026.05 | 28.1 | 14.9 | 3.3 | 15.4 | |
| T3ALT=0, training_mode=Zero-shot2024.04 | 26.1 | 13.9 | 2.9 | 14.3 | |
| CoCatraining_mode=Zero-shot2024.04 | 3.1 | 1.3 | 0.3 | 1.6 | |
| CLIP16training_mode=Zero-shot2024.04 | 0.9 | 0.3 | 0.1 | 0.4 | |
| CLIP32training_mode=Zero-shot2024.04 | 0.4 | 0.1 | 0 | 0.2 |