๐
๐
Old Age
SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation
November 29, 2023 ยท Entered Twilight ยท ๐ ACM Trans. Multim. Comput. Commun. Appl.
Repo contents: .devcontainer, .gitignore, README.md, configs, img, pyrightconfig.json, src
Authors
Qi Liu, Xinchen Liu, Kun Liu, Xiaoyan Gu, Wu Liu
arXiv ID
2311.17428
Category
cs.CV: Computer Vision
Cross-listed
cs.AI
Citations
1
Venue
ACM Trans. Multim. Comput. Commun. Appl.
Repository
https://github.com/LIUQI-creat/SigFormer
โญ 9
Last Checked
3 months ago
Abstract
Multi-modal human action segmentation is a critical and challenging task with a wide range of applications. Nowadays, the majority of approaches concentrate on the fusion of dense signals (i.e., RGB, optical flow, and depth maps). However, the potential contributions of sparse IoT sensor signals, which can be crucial for achieving accurate recognition, have not been fully explored. To make up for this, we introduce a Sparse signalguided Transformer (SigFormer) to combine both dense and sparse signals. We employ mask attention to fuse localized features by constraining cross-attention within the regions where sparse signals are valid. However, since sparse signals are discrete, they lack sufficient information about the temporal action boundaries. Therefore, in SigFormer, we propose to emphasize the boundary information at two stages to alleviate this problem. In the first feature extraction stage, we introduce an intermediate bottleneck module to jointly learn both category and boundary features of each dense modality through the inner loss functions. After the fusion of dense modalities and sparse signals, we then devise a two-branch architecture that explicitly models the interrelationship between action category and temporal boundary. Experimental results demonstrate that SigFormer outperforms the state-of-the-art approaches on a multi-modal action segmentation dataset from real industrial environments, reaching an outstanding F1 score of 0.958. The codes and pre-trained models have been available at https://github.com/LIUQI-creat/SigFormer.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computer Vision
๐
๐
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
๐
๐
Old Age
SSD: Single Shot MultiBox Detector
๐
๐
Old Age
Squeeze-and-Excitation Networks
๐
๐
Old Age
Fast R-CNN
๐
๐
Old Age