Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.24404 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909629027450880 |
|---|---|
| author | Lertniphonphan, Kanokphan Chen, Feng Xu, Junda Lan, Fengbu Xie, Jun Zhang, Tao Wang, Zhepeng |
| author_facet | Lertniphonphan, Kanokphan Chen, Feng Xu, Junda Lan, Fengbu Xie, Jun Zhang, Tao Wang, Zhepeng |
| contents | This report presents our team's PCIE_Interaction solution for the Ego4D Social Interaction Challenge at CVPR 2025, addressing both Looking At Me (LAM) and Talking To Me (TTM) tasks. The challenge requires accurate detection of social interactions between subjects and the camera wearer, with LAM relying exclusively on face crop sequences and TTM combining speaker face crops with synchronized audio segments. In the LAM track, we employ face quality enhancement and ensemble methods. For the TTM task, we extend visual interaction analysis by fusing audio and visual cues, weighted by a visual quality score. Our approach achieved 0.81 and 0.71 mean average precision (mAP) on the LAM and TTM challenges leader board. Code is available at https://github.com/KanokphanL/PCIE_Ego4D_Social_Interaction |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24404 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PCIE_Interaction Solution for Ego4D Social Interaction Challenge Lertniphonphan, Kanokphan Chen, Feng Xu, Junda Lan, Fengbu Xie, Jun Zhang, Tao Wang, Zhepeng Computer Vision and Pattern Recognition This report presents our team's PCIE_Interaction solution for the Ego4D Social Interaction Challenge at CVPR 2025, addressing both Looking At Me (LAM) and Talking To Me (TTM) tasks. The challenge requires accurate detection of social interactions between subjects and the camera wearer, with LAM relying exclusively on face crop sequences and TTM combining speaker face crops with synchronized audio segments. In the LAM track, we employ face quality enhancement and ensemble methods. For the TTM task, we extend visual interaction analysis by fusing audio and visual cues, weighted by a visual quality score. Our approach achieved 0.81 and 0.71 mean average precision (mAP) on the LAM and TTM challenges leader board. Code is available at https://github.com/KanokphanL/PCIE_Ego4D_Social_Interaction |
| title | PCIE_Interaction Solution for Ego4D Social Interaction Challenge |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.24404 |