Action Recognition

  • ssl_teaser

    Accurate Video Action Recognition with a Handful of Labeled Examples

    Action recognition in video remains a very popular research topic. However, current approaches based on supervised learning are hampered by the paucity of high-quality training data. Although a great number of videos are now available on the internet, they are not labeled with the accuracy nor at the temporal granularity required to train such methods. We present a complete action recognition system that learns accurate classifiers from as few as three labeled instances of each class.