Abstract | ||
---|---|---|
Action recognition is a challenging task since the attributes of objects as well as their relationships change constantly in the video. Existing methods mainly use object-level graphs or scene graphs to represent the dynamics of objects and relationships, but ignore modeling the fine-grained relationship transitions directly. In this paper, we propose an Object-Relation Reasoning Graph (OR 2 G) for reasoning about action in videos. By combining an object-level graph (OG) and a relation-level graph (RG), the proposed OR 2 G catches the attribute transitions of objects and reasons about the relationship transitions between objects simultaneously. In addition, a graph aggregating module (GAM) is investigated by applying the multi-head edge-to-node message passing operation. GAM feeds back the information from the relation node to the object node and enhances the coupling between the object-level graph and the relation-level graph. Experiments in video action recognition demonstrate the effectiveness of our approach when compared with the state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.01950 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
Action and event recognition, Recognition: detection,categorization,retrieval, Visual reasoning | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yangjun Ou | 1 | 8 | 1.48 |
Li Mi | 2 | 0 | 0.34 |
Zhenzhong Chen | 3 | 1244 | 101.41 |