| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-to-Video Retrieval | VATEX | R@195.1 | 95 | |
| Video-to-Text Retrieval | VATEX | Recall@194.8 | 68 | |
| Text-to-Video Retrieval | VATEX (test) | R@178.5 | 62 | |
| Video Captioning | VATEX (test) | CIDEr84.2 | 59 | |
| Video Captioning | VATEX | CIDEr99.5 | 46 | |
| Video Captioning | VATEX (public test) | CIDEr94.5 | 24 | |
| Human Judgment Correlation | VATEX EVAL (val) | Kendall Tau-b38.1 | 20 | |
| Video-to-Text Retrieval | VATEX (test) | Recall@182.3 | 15 | |
| Video Captioning | VATEX online evaluation (test) | CIDEr73 | 15 | |
| Video Captioning | VATEX (private test) | CIDEr96.6 | 14 | |
| Multimodal Machine Translation | VaTex En-Zh (half of val) | BLEU36.43 | 12 | |
| Video Captioning | VATEX V (test) | CIDEr76.3 | 11 | |
| Text-to-Video Retrieval | VATEX HGR partition (test) | R@163.5 | 9 | |
| Human Correlation | VATEX-EVAL 9 References | Kendall's Tau Correlation0.3681 | 8 | |
| Human Correlation | VATEX EVAL 1 Reference | Kendall's Tau0.2863 | 8 | |
| Video/Caption Retrieval | Vatex full (test) | R@145.9 | 8 | |
| Video-to-adverb retrieval | VATEX | Acc-A0.817 | 7 | |
| Adverb-to-video retrieval | VATEX | mAP W29 | 7 | |
| Adverb Recognition | VATEX Adverbs | mAP (W)28.3 | 7 | |
| Adverb recognition | VATEX Adverbs v1 (test) | mAP W16.9 | 7 | |
| Video-Text Retrieval | VATEX (HGR) | R@165.4 | 7 | |
| Video-to-Text Retrieval | VATEX HGR partition (test) | R@178.7 | 6 | |
| Text-to-Video Retrieval | VATEX (standard) | Recall@183 | 6 | |
| Text-to-Video Retrieval | VATEX English (test) | Recall@136.8 | 6 | |
| Visual Captioning | VATEX Chinese In-domain (test) | BLEU-429.7 | 5 |