We propose a novel method for temporally pooling frames in a video for the task of human action recognition. The method is motivated by the observation that there are only a small number of frames which, together, contain sufficient information to discriminate an action class present in a video, from the rest. The proposed method learns to pool such discriminative and informative frames, while discarding a majority of the non-informative frames in a single temporal scan of the video. Our algorithm does so by continuously predicting the discriminative importance of each video frame and subsequently pooling them in a deep learning framework. We show the effectiveness of our proposed pooling method on standard benchmarks where it consistently improves on baseline pooling methods, with both RGB and optical flow based Convolutional networks. Further, in combination with complementary video representations, we show results that are competitive with respect to the state-of-the-art results on two challenging and publicly available benchmark datasets.
Note: References are as in the paper. There is an error in the table in the paper (Wang et al.  results), which has been corrected here.