Blog
About

8
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Motion Feature Network: Fixed Motion Filter for Action Recognition

      Preprint

      , , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in combination with a set of RGB images that contain spatial information has shown great performance enhancement in the action recognition tasks. However, it has an expensive computational cost and requires two-stream (RGB and optical flow) framework. In this paper, we propose MFNet (Motion Feature Network) containing motion blocks which make it possible to encode spatio-temporal information between adjacent frames in a unified network that can be trained end-to-end. The motion block can be attached to any existing CNN-based action recognition frameworks with only a small additional cost. We evaluated our network on two of the action recognition datasets (Jester and Something-Something) and achieved competitive performances for both datasets by training the networks from scratch.

          Related collections

          Most cited references 9

          • Record: found
          • Abstract: not found
          • Article: not found

          Deep Residual Learning for Image Recognition

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Large-Scale Video Classification with Convolutional Neural Networks

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              FlowNet: Learning Optical Flow with Convolutional Networks

                Bookmark

                Author and article information

                Journal
                26 July 2018
                Article
                1807.10037

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                ECCV 2018, 14 pages, 6 figures, 4 tables
                cs.CV

                Computer vision & Pattern recognition

                Comments

                Comment on this article