Email : jasonhsiao97 [AT] gmail [DOT] com
| CV | Google Scholar | Github |
I'm a 3rd-year Ph.D. student at the Berkeley Artificial Intelligence Research (BAIR) Lab at University of California, Berkeley, advised by Prof. Trevor Darrell. My research interests lie in the field of Computer Vision and Machine Learning, particularly in enabling intelligent agents perceive, comprehend and reason with less direct supervision. I'm also affiliated with Facebook AI Research (FAIR) in collaboration with Piotr Dollár and Ross Girshick. Prior to UC Berkeley, I collaborated with Bolei Zhou on a series of works, and was mentored by Yuning Jiang and supervised by Jian Sun.
I graduated from Peking University (PKU) in 2019, the most progressive university in China, summa cum laude with a Bachelor's degree. I started computer programming in primary school and had been participating in programming contests throughout high school and college. I received China National Scholarship in 2016 and was selected as a 2019 Snap Research Scholar for my research and curriculum.
I have a great fondness for arts besides my academic work. I'm deeply passionate about musical works, especially those in classical music (both instrumental & vocal) and jazz. I'm also into laws & public policies. I'm a political activist in both the U.S. and my home country.
- [Oct. 2021] One paper accepted to NeurIPS21!
- [July 2021] Two papers accepted to ICCV21!
- [Jan. 2021] Two papers (including one selected for oral presentation) accepted to ICLR21!
- [Mar. 2020] Our work on compositional action recognition is accepted to CVPR20! Check out the project page with the new dataset "Something-else"!
- [July 2019] One paper on explainable human-object interaction is accepted to ICCV19!
- [May 2019] I will join the wonderful Berkeley Artificial Intelligence Research (BAIR) Lab as a Ph.D. student at the lovely UC Berkeley in August 2019. Go Bears!
---- show more ----
- [Nov. 2018] ADE20K accepted to IJCV! We included a variety of interesting applications plus the study of synchronized batch norm for semantic segmentation. Check out the paper for more details!
- [July 2018] Two papers (including one oral) accepted to ECCV18! (Code is released!)
- [May 2018] Our work on contrastive samples in vision and language learning accepted to COLING18! (Paper and codes are released.)
- [Apr. 2018] A PyTorch implementation of scene parsing networks trained on ADE20K with SOTA performance is released in conjunction with MIT CSAIL. Check out our code, it's popular!
- [Feb. 2018] Two papers accepted to CVPR18!
- [Oct. 2017] As a team member of Megvii (Face++), we won the premier challenge of object detection - COCO and Places Challenges 2017: the 1st places of COCO Detection, COCO Keypoint and Places Instance Segmentation, as well as the 2nd place of COCO Instance Segmentation. I was invited to present at COCO & Places Joint Workshop at ICCV17 in Venice, Italy.
MegDet: A Large Mini-Batch Object Detector
Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (Spotlight)
*: equal contribution
| arXiv |
Scaling-up training of object detectors; winner of MSCOCO Challenge 2017.
- MSCOCO Challenge, 2017
- Snap Research Scholarship, 2019
- China National Scholarship, Peking Univsity
- Scholarship for the Outstanding Talented, Peking Univsity
- Schlumberger Scholarship, Peking Univsity
- Founder Group Scholarship, Peking Univsity
- Gold Medals, ACM International Collegiate Programming Contest (ACM-ICPC) Asia Regional, 2016 & 2017
- Bronze Medal, National Olympiad in Informatics (NOI), 2014
- Champion, Shandong Province Team Selection Contest for NOI, 2014
Teaching Faculty, Practice in Programming (17-18 spring)
Teaching Faculty, Artificial Intelligence and Computer Vision (18-19 spring)
Berkeley Artificial Intelligence Research Lab
Berkeley Way West, 2121 Berkeley Way
Berkeley, CA 94704
Website design: ✩ ✩
Avatar photo: taken in Jerusalem in July 2019 by my good friend Yingcheng Liu.