Temporal Action Localization on ActivityNet Zero-shot 50% Seen 50% Unseen v1.3
50.6mAP@0.5IoUTi-FAD
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ti-FADVenue=NeurIPS’24, Prompt Tuning=false, Text Feature=CLIP-B2025.11 | 50.6 | 32.2 | 5.2 | 32 | |
| MGCA-NetVenue=-, Prompt Tuning=false, Text Feature=CLIP-B2025.11 | 48.8 | 32.8 | 7 | 32.2 | |
| UnLoc-LSetting=Zero-shot 50% Seen 50% Unseen, Vision Encoder=CLIP, Mode=prompt ensembling2023.08 | 43.7 | — | — | — | |
| UnLoc-LSetting=Zero-shot 50% Seen 50% Unseen, Vision Encoder=CLIP, Mode=1st prompt2023.08 | 43.2 | — | — | — | |
| OVFormerVenue=BMVC’24, Prompt Tuning=false, Text Feature=DINOv22025.11 | 42.8 | 27.3 | 6 | 27.2 | |
| STOV-TALVenue=WACV’25, Prompt Tuning=false, Text Feature=CLIP-B2025.11 | 42.1 | 25 | 1.3 | 24.8 | |
| mProTEAVenue=TCSVT’24, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 41.8 | 24.6 | 6.1 | 25.6 | |
| UnLoc-BVenue=ICCV’23, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 40.2 | — | — | — | |
| ZEETADVenue=WACV’24, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 39.2 | 25.7 | 3.1 | 24.9 | |
| UnLoc-BSetting=Zero-shot 50% Seen 50% Unseen, Vision Encoder=CLIP, Mode=1st prompt2023.08 | 36.9 | — | — | — | |
| DeTALVenue=TPAMI’24, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 34.4 | 23 | 4 | 22.4 | |
| STALESetting=Zero-shot 50% Seen 50% Unseen, Vision Encoder=CLIP2023.08 | 32.1 | — | — | — | |
| STABLEVenue=ECCV’22, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 32.1 | 20.7 | 5.9 | 20.5 | |
| EffPromptSetting=Zero-shot 50% Seen 50% Unseen, Vision Encoder=CLIP2023.08 | 32 | — | — | — | |
| Eff-PromptVenue=ECCV’22, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 32 | 19.3 | 2.9 | 19.6 | |
| B-IVenue=-, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 28 | 16.4 | 1.2 | 16 | |
| B-IIVenue=-, Prompt Tuning=true, Text Feature=CLIP-B2025.11 | 25.3 | 13 | 3.7 | 12.9 | |
| VFEALVisual Encoder=ViCLIP2026.05 | 11.28 | 3.38 | 31 | 4.99 | |
| Baseline-IIVisual Encoder=ViCLIP2026.05 | 1.13 | 0.33 | 11 | 0.52 | |
| Baseline-IVisual Encoder=CLIP2026.05 | 0.78 | 0.27 | 7 | 0.37 |