Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2022
Abstract
Learning discriminative representation from the complex spatio-temporal dynamic space is essential for video recognition. On top of those stylized spatio-temporal computational units, further refining the learnt feature with axial contexts is demonstrated to be promising in achieving this goal. However, previous works generally focus on utilizing a single kind of contexts to calibrate entire feature channels and could hardly apply to deal with diverse video activities. The problem can be tackled by using pair-wise spatio-temporal attentions to recompute feature response with cross-axis contexts at the expense of heavy computations. In this paper, we propose an efficient feature refinement method that decomposes the feature channels into several groups and separately refines them with different axial contexts in parallel. We refer this lightweight feature calibration as group contextualization (GC). Specifically, we design a family of efficient element-wise calibrators, i.e., ECal-G/S/T/L, where their axial contexts are information dynamics aggregated from other axes either globally or locally, to contextualize feature channel groups. The GC module can be densely plugged into each residual layer of the off-the-shelf video networks. With little computational overhead, consistent improvement is observed when plugging in GC on different networks. By utilizing calibrators to embed feature with four different kinds of contexts in parallel, the learnt representation is expected to be more resilient to diverse types of activities. On videos with rich temporal variations, empirically GC can boost the performance of 2D-CNN (e.g., TSN and TSM) to a level comparable to the state-of-the-art video networks. Code is available at https://github.com/haoyanbin918/GroupContextualization.
Keywords
Recognition, detection, categorization, retrieval, Action and event recognition, Deep learning architectures and techniques, Efficient learning and inferences
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, June 18-24: Proceedings
First Page
918
Last Page
928
ISBN
9781665469463
Identifier
10.1109/CVPR52688.2022.00100
Publisher
IEEE
City or Country
Piscataway, NJ
Citation
HAO, Yanbin; ZHANG, Hao; NGO, Chong-wah; and HE, Xiangnan.
Group contextualization for video recognition. (2022). 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, June 18-24: Proceedings. 918-928.
Available at: https://ink.library.smu.edu.sg/sis_research/7504
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/CVPR52688.2022.00100
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons