| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video-to-adverb retrieval | HowTo100M | Acc-A81.7 | 7 | |
| Adverb-to-video retrieval | HowTo100M | mAP W56.7 | 7 | |
| Adverb Recognition | HowTo100M Adverbs | mAP W56.2 | 7 | |
| Adverb recognition | HowTo100M Adverbs v1 (test) | mAP W0.404 | 7 | |
| Task classification | HowTo100M | Top-1 Accuracy15.5 | 6 | |
| Video Classification | HowTo100M | Accuracy64.6 | 4 | |
| Text-to-Video Retrieval | HowTo100M (10K sampled videos) | Recall@5031.6 | 3 | |
| Text-to-Video Retrieval | HowTo100M 1M sampled videos (whole set) | Recall@503.4 | 2 | |
| Text-to-Video Retrieval | HowTo100M (0.5M sampled videos) | Recall@505 | 2 | |
| Text-to-Video Retrieval | HowTo100M 0.1M sampled videos | Recall@500.115 | 2 | |
| Text-to-Video Retrieval | HowTo100M (50K sampled videos) | R@5015.9 | 2 | |
| Task classification | HowTo100M (test) | Top-1 Acc- | 0 |