Chong Zhou 周冲


Ph.D. Student

School of Computer Science and Engineering

Nanyang Technological University

Email: chongzhou1024 at gmail.com


Google Scholar GitHub LinkedIn

Short Bio

I am a Ph.D. student at the MMLab@NTU advised by Prof. Chen Change Loy and Prof. Bo Dai (2021-now). Previously, I completed my Master's degree from UC Davis advised by Prof. Yong Jae Lee (2018-2020), and my Bachelor's degree from Nankai University advised by Prof. Ming-Ming Cheng (2014-2018). I have also spent a year at the Tencent Youtu Lab working as a research intern (2020-2021).

I am broadly interested in computer vision and related problems in machine learning. My previous research focuses on instance segmentation and pedestrian detection. Currently, I'm particularly interested in vision and language.

News

[2021-01] Our pedestrian detection method, NOH-NMS, won the first place at the CrowdHuman Challenge, 2020.

[2020-10] YOLACT is integrated into mmdetection.

[2020-07] 1 paper accepted to TPAMI 2020 and 1 paper accepted to ACM Multimedia 2020.

[2019-10] Our real-time instance segmentation method, YOLACT, won the "most innovative award" at the COCO Object Detection Challenge, ICCV 2019.

[2019-07] 1 paper accepted to ICCV 2019 as oral presentation.

Publications


NON-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination

Penghao Zhou, Chong Zhou, Pai Peng, Junlong Du, Xing Sun,
Xiaowei Guo, Feiyue Huang.
ACM International Conference on Multimedia (ACM MM), 2020
First Place, CrowdHuman Challenge, 2020
PDF Code





YOLACT++: Better Real-time Instance Segmentation

Daniel Bolya*, Chong Zhou*, Fanyi Xiao, Yong Jae Lee.
(*equal contribution)
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020
PDF Code





YOLACT: Real-time Instance Segmentation

Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee.
International Conference on Computer Vision (ICCV), 2019 (Oral)
Most Innovative Award, COCO Object Detection Challenge, 2019
PDF Code