Search Results for author: Jiajun Wen

Found 5 papers, 4 papers with code

EPL: Empirical Prototype Learning for Deep Face Recognition

1 code implementation21 May 2024 Weijia Fan, Jiajun Wen, Xi Jia, Linlin Shen, Jiancan Zhou, Qiufu Li

When the prototypes are updated using the facial sample feature gradients in the model training, they are prone to being pulled away from the class center by the hard samples, resulting in decreased overall model performance.

Face Recognition

SFMViT: SlowFast Meet ViT in Chaotic World

1 code implementation25 Apr 2024 Jiaying Lin, Jiajun Wen, Mengyuan Liu, Jinfu Liu, Baiqiao Yin, Yue Li

The task of spatiotemporal action localization in chaotic scenes is a challenging task toward advanced video understanding.

Action Localization Video Understanding

Cannot find the paper you are looking for? You can Submit a new open access paper.