Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation

no code implementations • ECCV 2020 • Qingqiu Huang, Lei Yang, Huaiyi Huang, Tong Wu, Dahua Lin

Captioned images are widely available on the web, while the captions often contain the names of the subjects in the images.

Face Model Face Recognition

Learn to Propagate Reliably on Noisy Affinity Graphs

no code implementations • ECCV 2020 • Lei Yang, Qingqiu Huang, Huaiyi Huang, Linning Xu, Dahua Lin

Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost, which has been a critical issue in developing visual recognition models.

Open-Ended Question Answering

Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations

no code implementations • ECCV 2020 • Huaiyi Huang, Yuqi Zhang, Qingqiu Huang, Zhengkui Guo, Ziwei Liu, Dahua Lin

Place is an important element in visual understanding.