Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.11663 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913432851185664 |
|---|---|
| author | Li, Xiaodong Du, Wenchao Yang, Hongyu |
| author_facet | Li, Xiaodong Du, Wenchao Yang, Hongyu |
| contents | In this paper, we present our solution and experiment result for the Multi-Task Learning Challenge of the 7th Affective Behavior Analysis in-the-wild(ABAW7) Competition. This challenge consists of three tasks: action unit detection, facial expression recognition, and valance-arousal estimation. We address the research problems of this challenge from three aspects: 1)For learning robust visual feature representations, we introduce the pre-trained large model Dinov2. 2) To adaptively extract the required features of eack task, we design a task-adaptive block that performs cross-attention between a set of learnable query vectors and pre-extracted features. 3) By proposing the AU-assisted Graph Convolutional Network(AU-GCN), we make full use of the correlation information between AUs to assist in solving the EXPR and VA tasks. Finally, we achieve the evaluation measure of \textbf{1.2542} on the validation set provided by the organizers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11663 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Affective Behavior Analysis using Task-adaptive and AU-assisted Graph Network Li, Xiaodong Du, Wenchao Yang, Hongyu Computer Vision and Pattern Recognition In this paper, we present our solution and experiment result for the Multi-Task Learning Challenge of the 7th Affective Behavior Analysis in-the-wild(ABAW7) Competition. This challenge consists of three tasks: action unit detection, facial expression recognition, and valance-arousal estimation. We address the research problems of this challenge from three aspects: 1)For learning robust visual feature representations, we introduce the pre-trained large model Dinov2. 2) To adaptively extract the required features of eack task, we design a task-adaptive block that performs cross-attention between a set of learnable query vectors and pre-extracted features. 3) By proposing the AU-assisted Graph Convolutional Network(AU-GCN), we make full use of the correlation information between AUs to assist in solving the EXPR and VA tasks. Finally, we achieve the evaluation measure of \textbf{1.2542} on the validation set provided by the organizers. |
| title | Affective Behavior Analysis using Task-adaptive and AU-assisted Graph Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.11663 |