News
Mar. 2022
One paper accepted by CVPR'22. And I will be the official reviewer in ECCV-22 and NeurIPS-22.
Jan. 2022
I will be the official reviewer in ICML-22.
Sept. 2021
I will be the official reviewer in AAAI-22 and CVPR-22.
July. 2021
One full paper is accepted by MM'21, on food image segmentation.
July. 2021
I will be the official reviewer in Neurips-21 and ICLR-22 .
April. 2021
One dataset is released in Project, on food image segmentation .
Jan. 2021
One full paper is accepted by ICLR'21, on object detection .
July. 2020
One full paper is accepted by MM'20, on few-shot detection .
March. 2020
One survey paper is accepted by neurocomputing, on object detection .
March. 2020
One full paper is accepted by neurocomputing, on object detection .
Jan. 2020
One full paper is accepted by neurocomputing, on face detection .
|
Xiongwei Wu
Research Scientist
969 West Wen Yi Road, Yuhang District, Hangzhou, China.
Email: xwwu2015 AT gmail.com
|
I am currently the Research Scientist in Alibaba Inc. My research direction lies in vision-language and multimodal ai. I used to work on object detection and food computing during my PhD and Postdoc career. I have published some papers in ICLR, CVPR, MM, and KDD, and have served as the PC member for these top-tier conferences. I obtained my B.A from Zhejiang University and Ph.D from Singapore Management University.
Selected Publications
 |
OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation
Xiongwei Wu, Sicheng Yu, Ee-Peng Lim, Chong Wah Ngo. CVPR'2024 |
|
Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation
Zhaozheng Chen, Tan Wang, Xiongwei Wu, Xian-Sheng Hua, Hanwang Zhang, Qianru Sun. CVPR'2022 |
|
A Large-Scale Benchmark for Food Image Segmentation
Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C.H. Hoi, Qianru Sun MM'2021, Project |
|
PolarNet: Learning to Optimize Polar Keypoints for Keypoint Based Object Detection
Xiongwei Wu, Doyen Sahoo, Steven C.H. HOI ICLR'2021 |
|
Meta-RCNN: Meta Learning for Few-Shot Object Detection
Xiongwei Wu, Doyen Sahoo, Steven C.H. HOI MM'2020 (extension version) |
|
Recent Advances in Deep Learning for Object Detection
Xiongwei Wu, Doyen Sahoo, Steven C.H. HOI Neurocomputing |
|
Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
Xiongwei Wu, Doyen Sahoo, Daoxin Zhang, Jianke Zhu, Steven C.H. HOI Neurocomputing |
|
FoodAI: Food Image Recognition via Deep Learning for Smart Food Logging
Doyen Sahoo, Wang Hao, Shu Ke, Xiongwei Wu, Hung Le, Palakorn Achananuparp, Ee-Peng Lim, Steven C. H. Hoi KDD'2019 |
Professional Experience
| Alibaba Inc. Research Scientist Mar. 2025 - Now |
| HyperGAI Research Scientist Dec. 2023 - Oct. 2024, Singapore |
Education Experience
| Singapore Management University (SMU) Ph.D. in Computer Science Aug. 2015 - Jul. 2020, Singapore Advisor: Prof. Steven C.H. Hoi |
| Zhejiang University (ZJU) B.A. in Computer Science Aug. 2011 - Jun. 2015, China Advisor: Prof. Jianke Zhu |
Research Experience
| SCIS, SMU Postdoc Research Fellow Apr. 2022 - Nov. 2023 Singapore Topic: Open-Vocabulary Object Detection Advisor: Prof. Lim Ee-Peng and Prof. Ngo Chong-Wah |
|
Living Analytics Research Centre (LARC) Postdoc Research Fellow Mar. 2021 - Nov. 2023 Singapore Topic: Food-related research probelm, e.g., recognition and semantic segmentation. Advisor: Prof. Lim Ee-Peng and Prof. Ngo Chong-Wah |
|
Institute of Data Science and Technologies, Alibaba Inc. (IDST) Algorithm Engineer May 2015 - Aug. 2015, China Topic: Logo detection based on deep learning methods. Advisor: Prof. Jin Rong |
Academic Service
|
PC/SPC Member of Conferences: ICLR, NeurIPS, ICML, CVPR, ECCV, ICCV, ACMMM, AAAI Invited Reviewer for TMM, Neurocomputing, PR, TIST, TOMM, NCAA, MDPI |
Teaching Experience
|
2017 - TA for IS424 Data Mining and Business Analytics (SMU) 2018 - TA for IS424 Data Mining and Business Analytics (SMU) 2021 - Guest Lecture on CS701 Deep Learning and Vision on“Deep Learning for Object Detection”(SMU) |
Last update: March. 3, 2025. Webpage template borrows from Jiawei Chen.