Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition
Document Type
Conference Proceeding
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Abstract
Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatiotemporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention for better efficiency. Further, the aggregation step and the interaction step are both implemented using efficient convolution and element-wise multiplication operations that are computationally less expensive than their self-attention counterparts on video representations. We extensively explore the design space of focal modulation-based spatiotemporal context modeling and demonstrate our parallel spatial and temporal encoding design to be the optimal choice. Video-FocalNets perform favorably well against the state-of-the-art transformer-based models for video recognition on five large-scale datasets (Kinetics-400, Kinetics-600, SS-v2, Diving-48, and ActivityNet-1.3) at a lower computational cost. Our code/models are released at https://github.com/TalalWasim/Video-FocalNets.
First Page
13732
Last Page
13743
DOI
10.1109/ICCV51070.2023.01267
Publication Date
1-1-2023
Recommended Citation
S. Wasim et al., "Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition," Proceedings of the IEEE International Conference on Computer Vision, pp. 13732 - 13743, Jan 2023.
The definitive version is available at https://doi.org/10.1109/ICCV51070.2023.01267