Video-Adverb Retrieval
The bidirectional video-adverb retrieval task aims at retrieving adverbs that match an action in a video and vice versa.
Papers
Showing 1–4 of 4 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | ReGaDa | mAP M | 0.42 | — | Unverified |
| 2 | Action Changes (cls) | mAP M | 0.29 | — | Unverified |
| 3 | Action Changes (reg) | mAP M | 0.24 | — | Unverified |
| 4 | Action Changes (reg, fixed δ) | mAP M | 0.19 | — | Unverified |