Deep Insights into Convolutional Networks for Video Recognition

Christoph Feichtenhofer, Axel Pinz, Richard Wildes, Andrew Zisserman

    Research output: Contribution to journalArticlepeer-review


    As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal representations by visualizing the internal representation of models that have been trained to recognize actions in video. We visualize multiple two-stream architectures to show that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions. Key observations include the following. First, cross-stream fusion enables the learning of true spatiotemporal features rather than simply separate appearance and motion features. Second, the networks can learn local representations that are highly class specific, but also generic representations that can serve a range of classes. Third, throughout the hierarchy of the network, features become more abstract and show increasing invariance to aspects of the data that are unimportant to desired distinctions (e.g. motion patterns across various speeds). Fourth, visualizations can be used not only to shed light on learned representations, but also to reveal idiosyncrasies of training data and to explain failure cases of the system.
    Original languageEnglish
    Number of pages18
    JournalInternational Journal of Computer Vision
    Publication statusE-pub ahead of print - 29 Oct 2019


    • Computer vision
    • Machine learning
    • Deep Learning
    • Video recognition
    • Neural network visualization
    • Action recognition

    Fields of Expertise

    • Information, Communication & Computing


    Dive into the research topics of 'Deep Insights into Convolutional Networks for Video Recognition'. Together they form a unique fingerprint.

    Cite this