Joe (Zhou) Ren - Home Page

Joe (Zhou) Ren 

Joe (Zhou) Ren - 任洲
Just-Walk-Out Technology (Google Scholar, Linkedin)
Amazon AWS, Seattle, WA

<We are hiring Computer Vision researchers!>

Publish under Zhou Ren
Email: renzhou200622 [at-gmail] [dotcom]
Contact me with your CV if you are interested in full-time or doing an internship with us. :)

About me

  • I am leading a team (of Applied Scientists and Machine Learning Engineers) working on Amazon's Just Walk Out (JWO) technology - the autonomous retailing technology that powers JWO as a Service to third party retailers. My team focuses on developing algorithms for human-centric understanding (activity, human-object-interaction, product identification, counting, etc), planogram intelligence, and 3D space modeling using Vision Language Models (VLM), Large Video Models (LVM), and Geometry Foundation Model (GFM).

  • Previously, I was one of the three founding members and a Principal Research Manager of Wormpex AI Research, the AI branch of BianLiFeng (便利蜂), which was a top-10 convenience store chain in China. I was responsible for building state-of-the-art human-centric AI technologies to facilitate new retail business from new site selection, storefront management, to storefront operation. Before that, I was a senior research scientist at Snap Inc., working on multimodal understanding to support Snapchat’s content monetization, content security, and creative content creation. From 2010 to 2012, I was a researcher at Nanyang Technological University (NTU) working on hand gesture recognition using depth sensor.

  • Selected honors: 1. The 1st Prize in ICCV 2021 Low Power Computer Vision Challenge (among 31 teams); 2. Runner-up winner in NIPS 2017 Adversarial Attack and Defense Competition (among 107 teams); 3. “CVPR 2017 Best Student Paper Award” nominee; 4. winner of the “IEEE Trans. on Multimedia 2016 Best Paper Award”; 5. developed the first part-based hand gesture recognition system using Kinect sensor with Nanyang Technological University and Microsoft Research Redmond (Demo1, Demo2, Demo3). I’m a senior member of IEEE.

Services

Research Highlights

  • My research interests lie in the fields of Computer Vision, Multimedia, Machine Learning, and Natural Language Processing. I have worked on Human Centric Understanding (including hand gesture recognition, hand pose estimation, human pose estimation and tracking, human ReID, action detection, etc.), Multi-modal Joint Understanding (including image captioning, video captioning, visual-semantic embedding, etc.), shape understanding, adversarial machine learning, etc.

  • My current focuses are: 1. human centric understanding (pose, hand, gesture, human Re-ID, and tracking); 2. object detection, action detection and video representation learning, 3. multi-modal joint understanding, vision and language.