Person In Context

The 3rd Person in Context (PIC) Workshop and Challenge will be held in conjunction with CVPR2021.

We target at four sub-problems of the human-centric image analysis including human-object interaction for application (HOI-A), 3D face reconstruction (3D-Face), human-centric spatio-temporal referring (HSTR) and short-video face parsing (SFP). Notable, the HSTR is the first human-centric video grounding challenge, which requires understanding both image and language, as well as complicated multi-modal reasoning. Moreover, SFP is the first face parsing challenge towards the short-videos which enjoy explosive growth worldwide. The four sub-problems are complementary and collaboratively contribute to a unified human-centric visual and cognition solution.

PIC 2021 Schedule

13:30-13:40
13:40-14:10
14:10-14:15
14:15-14:30
14:30-15:00
15:00-15:05
15:05-15:20
15:20-15:50
15:50-15:55
15:55-16:10
16:10-16:40
16:40-16:45
16:45-17:00
The 3rd Person in Context (PIC) challenge introduction
Invited talk 1: Xiaobo Li (Alibaba Group)
Challenge 1 introduction
Challenge 1 Winner talk [Oral]
Invited talk 2: Han Joo (Facebook AI Research)
Challenge 2 introduction
Challenge 2 Winner talk [Oral]
Invited talk 3: Dacheng Tao(University of Sydney)
Challenge 3 introduction
Challenge 3 Winner talk [Oral]
Invited talk 4: Mohit Bansal (UNC)
Challenge 4 introduction
Challenge 4 Winner talk [Oral]

License

If not otherwise specified, datasets in PIC are made freely available to academic and non-academic entities for non-commercial purposes such as academic research, teaching, scientific publications, or personal experimentation. Permission is granted to use the data given that you agree to our license terms. This license shall be governed by the license agreement of the dataset (if exists).