Senior Applied Scientist · Computer Vision

Hi, I’m Suchen Wang.

I’m a Senior Applied Scientist at Amazon AWS AI Solutions, working on Just Walk Out (JWO) autonomous retail technology. I design and deploy large-scale perception systems that power seamless, frictionless shopping experiences across hundreds of automated retail stores worldwide.

My current work focuses on vision-language models and improving video reasoning capabilities to better understand actions, interactions, and how humans engage with the physical world.

Seattle, WA, USA
Ph.D., Nanyang Technological University, Singapore
Portrait of Suchen Wang

About

I'm a Senior Applied Scientist at Amazon AWS, working on Just Walk Out (JWO) autonomous retail technology. I received my Ph.D. from Nanyang Technological University (NTU), Singapore in 2022, advised by Prof. Junsong Yuan and Prof. Yap-Peng Tan. My research interests span action recognition, object detection, human–object interaction (HOI), large-scale video understanding, and visual reasoning.

Just Walk Out (JWO) is Amazon’s checkout-free retail technology that uses machine learning and computer vision to create a checkout-free shopping experience. This system allows shoppers to enter a store, take the items they want, and simply walk out without having to use a traditional checkout. The total for their items is automatically charged to their payment method after they exit. I'm working at the shopping team with mission of generating accurate receipts. As shoppers pick up items, overhead cameras and the shopping model running behind will add the picked products to their virtual cart. Our shopping model continuously recognizes shopping activities to maintain individual virtual cart for each shopper. Since joining Amazon, I'm contributing to JWO’s large-scale perception systems. We have built and developed visual reasoning models that power 300+ JWO stores across the United States, United Kingdom, Canada, Australia, and France, etc.

Experience

Senior Applied Scientist

Amazon AWS AI Solutions · JWO Research Seattle, WA · Dec 2024 – Present
  • Worked with an excellent small team to develop the first visual-reasoning multimodal LLMs for Just Walk Out receipt generation, including pretraining visual encoders, mid-training the reasoning language model, and post-training for real-world robustness.

Applied Scientist II

Amazon AWS AI Solutions · JWO Research Seattle, WA · Nov 2022 – Nov 2024

Research Assistant

Nanyang Technological University (NTU) Singapore · Sep 2016 – Oct 2022
  • Conducted research in HOI detection, multi-view vision, video understanding, and behavior modeling.
  • Developed perception algorithms for smart classrooms, robotics, and video analytics.
  • Published in CVPR, ICCV, IJCAI, TPAMI, TIP.

Research & Publications

Research Interests

  • Action recognition & temporal reasoning
  • Human–object interaction (HOI)
  • Object detection & segmentation
  • Video reasoning & analytics
  • Vision-language models
  • Multi-camera perception

Selected Publications

Full list available on Google Scholar .

  1. Boundary Voting Network for Ambiguity-aware Timestamp-supervised Action Segmentation.
    Runzhong Zhang, Yueqi Duan, Yang Chen, Weipeng Hu, Chen Cai, Suchen Wang, Yap-Peng Tan. IEEE TCSVT, 2025.
  2. Top-down Framework for Weakly-supervised Grounded Image Captioning.
    Chen Cai, Suchen Wang, Kim-Hui Yap, Yi Wang. KBS, 2024.
  3. HOI-Aware Adaptive Network for Weakly Supervised Action Segmentation.
    Runzhong Zhang, Suchen Wang, Yueqi Duan, Yansong Tang, Yue Zhang, Yap-Peng Tan. IJCAI, 2023.
  4. VLT: Vision-Language Transformer for Referring Segmentation.
    Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang. IEEE TPAMI, 2022.
  5. Learning Transferable Human-Object Interaction Detector with Natural Language Supervision.
    Suchen Wang, Yueqi Duan, Henghui Ding, Yap-Peng Tan, Kim-Hui Yap, Junsong Yuan. CVPR, 2022.
  6. Discovering Human Interactions with Large-Vocabulary Objects via Multi-Scale Detection.
    Suchen Wang, Kim-Hui Yap, Henghui Ding, Jiyan Wu, Junsong Yuan, Yap-Peng Tan. ICCV, 2021.
  7. Vision-Language Transformer and Query Generation for Referring Segmentation.
    Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang. ICCV, 2021.
  8. Discovering Human Interactions with Novel Objects via Zero-shot Learning.
    Suchen Wang, Kim-Hui Yap, Junsong Yuan, Yap-Peng Tan. CVPR, 2020.
  9. Joint Representative Selection and Feature Learning: A Semi-Supervised Approach
    Suchen Wang, Jingjing Meng, Junsong Yuan, Yap-Peng Tan CVPR, 2019.
  10. Video Summarization via Multi-View Representative Selection.
    Jingjing Meng, Suchen Wang, Hongxing Wang, Junsong Yuan, Yap-Peng Tan. IEEE TIP, 2018.

Service

  • Outstanding Reviewer, CVPR 2025.
  • Reviewer for top-tier conferences: CVPR, ICCV, ECCV, NeurIPS, ICASSP.
  • Reviewer for journals: IEEE TPAMI, TIP, TMM, TCSVT.

Contact

You can reach me by email or connect with me on LinkedIn.