Video Retrieval
The objective of video retrieval is as follows: given a text query and a pool of candidate videos, select the video which corresponds to the text query. Typically, the videos are returned as a ranked list of candidates and scored via document retrieval metrics.
Papers
Showing 1–10 of 486 papers
All datasetsMSR-VTT-1kADiDeMoMSR-VTTLSMDCActivityNetMSVDYouCook2FIVR-200KVATEXQuerYDSSv2-label retrievalSSv2-template retrieval
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | S2VS | mAP (ISVR) | 0.75 | — | Unverified |
| 2 | DnS (S^f_A) | mAP (ISVR) | 0.74 | — | Unverified |
| 3 | S2VS | mAP (ISVR) | 0.74 | — | Unverified |
| 4 | DnS (S^f_B) | mAP (ISVR) | 0.73 | — | Unverified |
| 5 | ViSiLv (pt) | mAP (ISVR) | 0.72 | — | Unverified |
| 6 | TCAf | mAP (ISVR) | 0.7 | — | Unverified |
| 7 | ViSiLv (tf) | mAP (ISVR) | 0.7 | — | Unverified |
| 8 | Jo et al. (SCFV+TNIP) | mAP (ISVR) | 0.67 | — | Unverified |
| 9 | ViSiLf | mAP (ISVR) | 0.66 | — | Unverified |
| 10 | ViSiLsym | mAP (ISVR) | 0.65 | — | Unverified |