-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2021_CVPR, author = {Zhang, Yanyi and Li, Xinyu and Marsic, Ivan}, title = {Multi-Label Activity Recognition Using Activity-Specific Features and Activity Correlations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {14625-14635} }
Multi-Label Activity Recognition Using Activity-Specific Features and Activity Correlations
Abstract
Multi-label activity recognition is designed for recognizing multiple activities that are performed simultaneously or sequentially in each video. Most recent activity recognition networks focus on single-activities, that assume only one activity in each video. These networks extract shared features for all the activities, which are not designed for multi-label activities. We introduce an approach to multi-label activity recognition that extracts independent feature descriptors for each activity and learns activity correlations. This structure can be trained end-to-end and plugged into any existing network structures for video classification. Our method outperformed state-of-the-art approaches on four multi-label activity recognition datasets. To better understand the activity-specific features that the system generated, we visualized these activity-specific features in the Charades dataset. The code will be released later.
Related Material