 |
Zhou Ren (任洲)
Research Lead / Senior Researcher (CV, Google Scholar, Linkedin)
Wormpex AI Research, Bellevue, WA
<We are hiring Computer Vision researchers!>
Email: renzhou200622 [at] gmail.com
Contact me with your CV if you are interested in full-time or doing an internship with us. :)
|
About me
Zhou is a technical innovator, actively seeking solutions to build and enhance real-world products. He is a founding member of Wormpex AI Research, which is the AI branch of BianLiFeng (便利蜂), a fast growing advanced convenience store chain in China backed by a global capital. At Wormpex AI research (directed by Dr. Gang Hua), we build state-of-the-art AI technologies to facilitate new retail logistics from storefronts, warehouses to manufacture.
Zhou is an active researcher. His research interests include Computer Vision, Multimedia, Natural Language Processing and Machine Learning. He has worked on problems of hand pose estimation, multi-modal joint understanding, object detection, action detection, image captioning, reinforcement learning, and adversarial machine learning, etc. He received his Ph.D. degree in Computer Science from University of California, Los Angeles (UCLA) in 2016, and a M.Eng degree from Nanyang Technological University (NTU) in 2012. Before that, he received his Bachelor’s degree with highest honor from Huazhong University of Science and Technology (HUST) in 2010.
News
[03/19] Three papers accepted by CVPR 2019, two as Orals, and one as Poster. Congratulations to my mentored students (Liuhao Ge, Jonghwan Mun, Cihang Xie) and collaborators!
[07/18] Been invited to present in a panel discussion at ICME 2018, together with Dr. Tao Mei, Dr. Wenjun Zeng, Prof. Xilin Chen, Prof. Mohan Kankanhalli, and Prof. Junsong Yuan.
Research
My research interests lie in the fields of Computer Vision, Multimedia, Natural Language Processing, and Machine Learning. I have worked on hand pose estimation, object detection, multi-modal joint understanding, image captioning, video captioning, shape understanding, reinforcement learning, and adversarial machine learning, etc.
My current research focuses include: 1) human/hand pose estimation, 2) object detection, 3) Human Re-ID, 4)multi-modal joint understanding.
Publications
(Note: “^” indicates the co-author is the student I mentored during whose internship or during an university collaboration)
1. on Hand Gesture Recognition and Pose Estimation
3D Hand Shape and Pose Estimation from a Single RGB Image
Liuhao Ge^, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang, Jianfei Cai, Junsong Yuan
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral).
[PDF][supplementary][video]
End-to-End 3D Hand Pose Estimation from Stereo Cameras
Yuncheng Li, Zehao Xue, Yingying Wang, Liuhao Ge, Zhou Ren, Jonathan Rodriguez
In British Machine Vision Conference (BMVC), 2019 (Oral).
[PDF]
Point-to-Point Regression PointNet for 3D Hand Pose Estimation
Liuhao Ge^, Zhou Ren, and Junsong Yuan
In European Conference on Computer Vision (ECCV), 2018.
[PDF]
Depth Camera based Hand Gesture Recognition and its Applications in Human-Computer-Interaction
Zhou Ren, Jingjing Meng, and Junsong Yuan
In IEEE International Conference on Information, Communication, and Signal Processing (ICICS), Singapore, Dec. 2011 (Oral).
[PDF][Bibtex] [Demo1] [Demo2]
2. on Multi-modal Joint Representation Learning
SibNet: Sibling Convolutional Encoder for Video Captioning
Sheng Liu^, Zhou Ren, and Junsong Yuan;
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.
[PDF]
Streamlined Dense Video Captioning
Jonghwan Mun^, Linjie Yang, Zhou Ren, Ning Xu, and Bohyung Han
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral).
[PDF][supplementary]
SibNet: Sibling Convolutional Encoder for Video Captioning
Sheng Liu^, Zhou Ren, and Junsong Yuan
In ACM Multimedia, 2018 (Oral)
[PDF]
Multiple Instance Visual-Semantic Embedding
Zhou Ren, Hailin Jin, Zhe Lin, Chen Fang, and Alan Yuille
In British Machine Vision Conference (BMVC), 2017 (Oral)
[PDF][Supplementary][Bibtex][Video]
Deep Reinforcement Learning-based Image Captioning with Embedding Reward
Zhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, and Li-Jia Li
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (Oral)
*Best Student Paper Award Nomination*
[PDF][Bibtex][Talk slides][Poster][Video]
Joint Image-Text Representation by Gaussian Visual Semantic Embedding
Zhou Ren, Hailin Jin, Zhe Lin, Chen Fang, and Alan Yuille
In ACM Multimedia Conference, 2016
[PDF][Bibtex]
3. on Object Detection and Representation Learning
Deep Regionlets for Object Detection
Hongyu Xu^, Xutao Lv, Xiaoyu Wang, Zhou Ren, and Rama Chellappa
In European Conference on Computer Vision (ECCV), 2018.
[PDF]
Scene-Domain Active Part Models for Object Representation
Zhou Ren, Chaohui Wang, and Alan Yuille
In International Conference on Computer Vision (ICCV), 2015.
[PDF][Bibtex]
4. on Action Detection
Temporal Structure Mining for Weakly Supervised Action Detection
Tan Yu^, Zhou Ren, Yuncheng Li, Enxu Yan, Ning Xu, and Junsong Yuan
In International Conference on Computer Vision (ICCV), 2019.
[PDF]
5. on Person Re-Identification
ABD-Net: Attentive but Diverse Person Re-Identification
Tianlong Chen^, Shaojin Ding, Jingyi Xie, Ye Yuan, Wuyang Chen, Yang Yang, Zhou Ren, and Zhangyang Wang
In International Conference on Computer Vision (ICCV), 2019.
[PDF]
6. on Adversarial Machine Learning
Improving Transferability of Adversarial Examples with Input Diversity
Cihang Xie^, Yuyin Zhou, Song Bai, Zhishuai Zhang, Jianyu Wang, Zhou Ren, and Alan Yuille
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[PDF]
Mitigating Adversarial Effects Through Randomization
Cihang Xie^, Jianyu Wang, Zhishuai Zhang, Zhou Ren, and Alan Yuille
In International Conference on Learning Representations (ICLR), 2018
* Runner-up Winner in NIPS 2017 Adversarial Attack and Defense Competition (among 107 teams)*
[PDF]
Adversarial Attacks and Defences Competition
Alexey Kurakin, et. al.
In a book chapter from the NIPS 2017 Competition Book, Springer 2018
[PDF]
7. on Shape Representation and Shape Coding
Minimum Near-Convex Shape Decomposition
Zhou Ren, Junsong Yuan, Wenyu Liu
In IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 35(10), 2546-2552, 2013.
[PDF][Bibtex]
Minimum Near-Convex Decomposition for Robust Shape Representation
Zhou Ren, Junsong Yuan, Chunyuan Li and Wenyu Liu
In International Conference on Computer Vision (ICCV), pp.303-310, Barcelona, Spain, Nov. 2011.
[PDF][Bibtex]
Arbitrary Directional Edge Encoding Schemes for the Operational Rate Distortion Optimal Shape Coding Framework
Zhongyuan Lai, Junhuan Zhu, Zhou Ren, Wenyu Liu, and Baolan yan
In IEEE Data Compression Conference (DCC), pp.20-29, Salt Lake City, USA, Nov. 2010 (Oral).
[PDF][Bibtex]
8. on Medical Image Processing
Automated Pericardial Fat Quantification from Coronary Magnetic Resonance Angiography: A Feasibility Study
Xiaowei Ding, Jianing Pang, Zhou Ren, Mariana Diaz-Zamudio, Chenfangfu Jiang, Zhaoyang Fan, Daniel Berman, Debiao Li, Demetri Terzopoulos, Piotr Slomka, and Damini Dey
In Journal of Medical Imaging, 2016.
[PDF][Bibtex]
Automated Pericardial Fat Quantification from Coronary Magnetic Resonance Angiography
Xiaowei Ding, Jianing Pang, Zhou Ren, Mariana Diaz-Zamudio, Daniel Berman, Debiao Li, Demetri Terzopoulos, Piotr Slomka, and Damini Dey
In Medical Image Understanding and Analysis (MIUA), 2015 (Oral).
[PDF][Bibtex]
Selected Patents
System and method for robust hand gesture recognition using commodity depth sensor, Singapore provisional patent application, filed in 10/2011
Co-invented with Junsong Yuan, Jingjing Meng
Modeling semantic concepts in an embedding space as distributions, US patent application, filed in 01/2016
Co-invented with Hailin Jin, Zhe Lin, and Chen Fang
Embedding-driven image captioning using deep reinforcement learning and lookahead beam search, US patent application, filed in 11/2016
Co-invented with Xiaoyu Wang, Ning Zhang, Xutao Lv, and Jia Li
Query Matching to Media Collections in a Messaging System, US patent application, filed in 01/2018
Co-invented with Roger Luo, Sushobhan Nayak, Xinran He, and Christophe Van Gysel
Device Location based on Machine Learning Classifications, US patent, granted in 05/2018
Co-invented with Ebony Charlton, Sumant Hanumante, Dhritiman Sagar
Embedding space for images with multiple text labels, US patent, granted in 07/2018
Co-invented with Hailin Jin, Zhe Lin, and Chen Fang
Mentored Students
Lluis Castrejon (2017 Summer), PhD student at MILA, University of Montreal
Zhe Li (2017 Summer), PhD student at University of Iowa
Hongyu Xu (2017 Summer), PhD student at University of Maryland, College Park
Cihang Xie (2017 Fall - 2018 Spring), PhD student at Johns Hopkins University
Sheng Liu (2017 Fall - present), PhD student at The State University of New York at Buffalo
Liuhao Ge (2018 Spring - 2019 Spring), PhD student at Nanyang Technological University
Tan Yu (2018 Summer), PhD student at Nanyang Technological University
Shibi He (2018 Summer), PhD student at University of Illinois Urbana-Champaign
Jonghwan Mun (2018 Summer), PhD student at Pohang University of Science and Technology
Tianlong Chen (2019 Spring), PhD student at Texas A&M University
Ye Yuan (2019 Spring), PhD student at Texas A&M University
Wuyang Chen (2019 Spring), PhD student at Texas A&M University
Shiyi Lan (2019 Summer), PhD student at University of Maryland, College Park
Teaching
Professional Activities
Associate Editor of The Visual Computer Journal (TVCJ).
Program Committee of CVPR 2017, FG 2018 2019, IJCAI 2018 2019, ECAI 2018, ACM Multimedia 2018 2019, AAAI 2019, etc.
Reviewer of FG 2016 2017 2018, WACV 2017, CVPR 2016 2017 2018 2019, ICCV 2017 2019, ECCV 2018, IJCAI 2018 2019, etc.
Reviewer of IEEE TPAMI; IEEE TIP; IEEE TCSVT; IEEE TMM; IEEE THMS; CVIU; TVCJ; Machine Vision and Application; Journal of Computer Science and Technology; etc.
Page generated 2019-09-11 23:44:23 PDT, by jemdoc.
|
