Temporal Bilinear Networks for Video Action Recognition

Authors

  • Yanghao Li Peking University
  • Sijie Song Peking University
  • Yuqi Li Peking University
  • Jiaying Liu Peking University

DOI:

https://doi.org/10.1609/aaai.v33i01.33018674

Abstract

Temporal modeling in videos is a fundamental yet challenging problem in computer vision. In this paper, we propose a novel Temporal Bilinear (TB) model to capture the temporal pairwise feature interactions between adjacent frames. Compared with some existing temporal methods which are limited in linear transformations, our TB model considers explicit quadratic bilinear transformations in the temporal domain for motion evolution and sequential relation modeling. We further leverage the factorized bilinear model in linear complexity and a bottleneck network design to build our TB blocks, which also constrains the parameters and computation cost. We consider two schemes in terms of the incorporation of TB blocks and the original 2D spatial convolutions, namely wide and deep Temporal Bilinear Networks (TBN). Finally, we perform experiments on several widely adopted datasets including Kinetics, UCF101 and HMDB51. The effectiveness of our TBNs is validated by comprehensive ablation analyses and comparisons with various state-of-the-art methods.

Downloads

Published

2019-07-17

How to Cite

Li, Y., Song, S., Li, Y., & Liu, J. (2019). Temporal Bilinear Networks for Video Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8674-8681. https://doi.org/10.1609/aaai.v33i01.33018674

Issue

Section

AAAI Technical Track: Vision