Sorry, you need to enable JavaScript to visit this website.

SALIENCY TUBES: VISUAL EXPLANATIONS FOR SPATIO-TEMPORAL CONVOLUTIONS

Citation Author(s):
Georgios Kapidis, Grigorios Kalliatakis, Christos Chrysoulas, Remco Veltkamp and Ronald Poppe
Submitted by:
Alexandros Stergiou
Last updated:
18 September 2019 - 9:52am
Document Type:
Presentation Slides
Document Year:
2019
Event:
Presenters:
Alexandros Stergiou
Paper Code:
2272
 

Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve state-of-the-art performance in many challenging video datasets. Because of the high level of complexity of these methods, as the convolution operations are also extended to an additional dimension in order to extract features from it as well, providing a visualization for the signals that the network interpret as informative, is a challenging task. An effective notion of understanding the network's inner-workings would be to isolate the spatio-temporal regions on the video that the network finds most informative. We propose a method called Saliency Tubes which demonstrate the foremost points and regions in both frame level and over time that are found to be the main focus points of the network. We demonstrate our findings on widely used datasets for third-person and egocentric action classification and enhance the set of methods and visualizations that improve 3D Convolutional Neural Networks (CNNs) intelligibility.

up
0 users have voted: