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 | UMT-L (ViT-L/16) | text-to-video R@1 | 90.8 | — | Unverified |
| 2 | vid-TLDR (UMT-L) | text-to-video R@1 | 90.2 | — | Unverified |
| 3 | HiTeA | text-to-video R@1 | 85.6 | — | Unverified |
| 4 | VindLU | text-to-video R@1 | 83.3 | — | Unverified |
| 5 | Singularity-temporal | text-to-video R@1 | 77.6 | — | Unverified |