Zhengkai Jiang

Researcher

Tencent Youtu Lab

Email: zhengkjiang [at] tencent (dot) com

Google Scholar / Github / Zhihu / Resume

I am currently a Researcher at Tencent Youtu Lab. My research interests are in computer vision and deep learning.

Previously, I obtained the master's degree at 2020 from National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences. I received the bachelor's degree at 2017 from the Department of Automation, Northeastern University with honors.

We are hiring self-motivated interns! If you are interested, you can email me with your resume.

Publications

AutoAssign: Differentiable Label Assignment for Dense Object Detection

Benjin Zhu, Jianfeng Wang, Zhengkai Jiang, Fuhang Zong, Songtao Liu, Zeming Li, Jian Sun

Arxiv 2020 / Paper / Code

Performing differentiable label assignment for dense object detection.

Fine-Grained Dynamic Head for Object Detection

Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng

NeurIPS 2020 / Paper / Code

A fine-grained dynamic head is proposed to conditionally select a pixel-level combination of FPN features from different scales.

Rethinking Learnable Tree Filter for Generic Feature Transform

Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Xiangyu Zhang, Hongbin Sun, Jian Sun, Nanning Zheng

NeurIPS 2020 / Paper / Code

Performing differentiable tree-filter with a learnable unary term for generic feature transform.

Learning Where to Focus for Efficient Video Object Detection

Zhengkai Jiang, Yu Liu, Ceyuan Yang, Jihao Liu, Peng Gao, Qian Zhang, Shiming Xiang Chunhong Pan,

ECCV 2020 / Paper / Code

The offsets of sampling locations across videos are treated as parameters and would be learned through back-propagation guided by bounding box and classification loss.

Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

Benjin Zhu, Zhengkai Jiang, Xiangxin Zhou, Zeming Li, Gang Yu

Arxiv 2019 / Paper / Code

NuScenes winner of WAD 2019 3D Object Detection Challenges at CVPR 2019 workshop.

Dynamic Fusion with Intra and Inter-Modality Attention Flow for Visual Question Answering

Peng Gao, Zhengkai Jiang, Haoxuan You, Pan Lu, Steven CH Hoi, Xiaogang Wang, Hongsheng Li

CVPR 2019 Paper

Oral Presentation

Cross modality self-attention was proposed to capture the high-level interactions between language and vision domains.

Video Object Detection with Locally-Weightd Deformable Neighboors

Zhengkai Jiang, Peng Gao, Chaoxu Guo, Qian Zhang, Shiming Xiang, Chunhong Pan

AAAI 2019 Paper

Locally-weighted deformable neighbors module was proposed to model motion for video object detection without utilizing time-consuming optical flow extraction networks.

Educations

[2017.09-2020.07] National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
[2013.09-2017.07] Department of Automation, Northeastern University

Competitions

1st at the Objects 365 Challenge, 2020
1st at the NuScenes 3D Detection of CVPR WAD workshop, 2019
3rd at the Instance Segmentation of ECCV COCO Workshop, 2018

Awards

Excellent Student, Institute of Automation, Chinese Academy of Sciences, 2019, 2020
Special Freshman Scholarship, Institute of Automation, Chinese Academy of Sciences, 2017
National Scholarship, 2014, 2015, 2016
First Prize of Chinese Mathematics Competitions (CMC), 2014, 2015
Second Prize of Final Chinese Mathematics Competitions (CMC), Wuhan, China, 2014
Third Prize of Final Chinese Mathematics Competitions (CMC), Fuzhou, China, 2015
First Class Scholarship of NEU, 2014, 2016
Second Prize of China Undergraduate Mathematical Contest in Modeling (CUMCM), 2015

Activities

Conference Reviewer:

International Conference on Computer Vision (ICCV) 2021
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021
Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI) 2021

Journal Reviewer:

International Journal of Computer Vision (IJCV)