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 | GRAM | text-to-video R@1 | 64 | — | Unverified |
| 2 | VAST | text-to-video R@1 | 63.9 | — | Unverified |
| 3 | InternVideo2-6B | text-to-video R@1 | 62.8 | — | Unverified |
| 4 | VALOR | text-to-video R@1 | 59.9 | — | Unverified |
| 5 | UMT-L (ViT-L/16) | text-to-video R@1 | 58.8 | — | Unverified |
| 6 | vid-TLDR (UMT-L) | text-to-video R@1 | 58.1 | — | Unverified |
| 7 | COSA | text-to-video R@1 | 57.9 | — | Unverified |
| 8 | InternVideo2-6B | text-to-video R@1 | 55.9 | — | Unverified |
| 9 | InternVideo | text-to-video R@1 | 55.2 | — | Unverified |
| 10 | VLAB | text-to-video R@1 | 55.1 | — | Unverified |