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 | OmniVec | text-to-video R@10 | 70.8 | — | Unverified |
| 2 | OmniVec (pretrained) | text-to-video R@10 | 64.2 | — | Unverified |
| 3 | VAST | text-to-video R@1 | 50.4 | — | Unverified |
| 4 | UniVL + MELTR | text-to-video R@1 | 33.7 | — | Unverified |
| 5 | VideoCLIP | text-to-video R@1 | 32.2 | — | Unverified |
| 6 | MDMMT-2 | text-to-video R@1 | 32 | — | Unverified |
| 7 | TACo | text-to-video R@1 | 29.6 | — | Unverified |
| 8 | UniVL | text-to-video R@1 | 28.9 | — | Unverified |
| 9 | VLM | text-to-video R@1 | 27.05 | — | Unverified |
| 10 | VideoCLIP | text-to-video R@1 | 22.7 | — | Unverified |