< Back to previous page

Publication

Beyond temporal pooling : recurrence and temporal convolutions for gesture recognition in video

Journal Contribution - Journal Article

Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling strategy to take into account the temporal aspect of video. We demonstrate that this method is not sufficient for gesture recognition, where temporal information is more discriminative compared to general video classification tasks. We explore deep architectures for gesture recognition in video and propose a new end-to-end trainable neural network architecture incorporating temporal convolutions and bidirectional recurrence. Our main contributions are twofold; first, we show that recurrence is crucial for this task; second, we show that adding temporal convolutions leads to significant improvements. We evaluate the different approaches on the Montalbano gesture recognition dataset, where we achieve state-of-the-art results.
Journal: INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN: 1573-1405
Issue: 2-4
Volume: 126
Pages: 430 - 439
Publication year:2018
BOF-keylabel:yes
IOF-keylabel:yes
BOF-publication weight:10
CSS-citation score:3
Authors:National
Authors from:Higher Education
Accessibility:Closed