Learning from Video and Text via Large-Scale Discriminative Clustering



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.


[arXiv], [poster], [Code]


    author      = "Miech, Antoine and Alayrac, Jean-Baptiste and Bojanowski, Piotr and Laptev, Ivan and Sivic, Josef",
    title       = "{L}earning from {V}ideo and {T}ext via {L}arge-{S}cale {D}iscriminative {C}lustering",
    booktitle   = "ICCV",
    year        = "2017"


Github repo Coming soon!


This work was partly supported by ERC grants Activia (no. 307574) and LEAP (no. 336845), CIFAR Learning in Machines & Brains program and ESIF, OP Research, development and education Project IMPACT No. CZ.02.1.01/0.0/0.0/15 003/0000468 and a Google Research Award.