Papers › Learning from Video and Text via Large-Scale Discriminative Clustering
Learning from Video and Text via Large-Scale Discriminative Clustering
Antoine Miech, Jean-Baptiste Alayrac, Piotr Bojanowski, Ivan Laptev, Josef Sivic
Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks. Such applications include person and action recognition, text-to-video alignment, object co-segmentation and colocalization in videos and images. One drawback of discriminative clustering, however, is its limited scalability. We address this issue and propose an online optimization algorithm based on the Block-Coordinate Frank-Wolfe algorithm. We apply the proposed method to the problem of weakly supervised learning of actions and actors from movies together with corresponding movie scripts. The scaling up of the learning problem to 66 feature length movies enables us to significantly improve weakly supervised action recognition.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Retrieval | LSMDC | Large-Scale Discriminative Clustering | text-to-video Median Rank | 52 | #35 of 38 | Archive leaderboard | report |
| Video Retrieval | LSMDC | Large-Scale Discriminative Clustering | text-to-video R@1 | 7.3 | #35 of 38 | Archive leaderboard | report |
| Video Retrieval | LSMDC | Large-Scale Discriminative Clustering | text-to-video R@10 | 27.1 | #35 of 38 | Archive leaderboard | report |
| Video Retrieval | LSMDC | Large-Scale Discriminative Clustering | text-to-video R@5 | 19.2 | #35 of 38 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections