Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations
This addresses the problem of recognizing multiple simultaneous or sequential activities in videos for computer vision applications, representing an incremental improvement over single-activity networks.
The paper tackled multi-label activity recognition by introducing a method that extracts independent feature descriptors for each activity and learns activity correlations, outperforming state-of-the-art approaches on four datasets.
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.