Dawei Du
Research Scientist
ByteDance, Inc., San Jose, CA, USA
Contact: cvdaviddo@gmail.com
News!
One co-authored CVPR paper was accepted on February 27th, 2023.
I joined ByteDance as a Research Scientist on November 6th, 2023.
One co-authored WACV paper was accepted on October 28th, 2024.
Professional Experiences
11/2023~Present Research Scientist at ByteDance, Inc.
02/2020~10/2023 Computer Vision Researcher/Senior R&D Engineer at Kitware, Inc.
08/2018~01/2020 Postdoc at Univeristy at Albany, State Univeristy of New York
05/2012~01/2013 Research Intern at NEC Laboratories China
Educations
09/2013~06/2018 Ph.D. in University of Chinese Academy of Sciences (UCAS)
09/2010~06/2013 M.S. in University of Electronic Science and Technology of China (UESTC)
09/2006~06/2010 B.S. in University of Electronic Science and Technology of China (UESTC)
Research Interests
• Computer Vision, Machine Learning, Deep Learning
• Multi-Modal LLMs, Vision+Language Learning, Image Generation
• Visual Tracking, Object Detection, Video Segmentation, Action Recognition, Image Retrieval
Preprints
1. Lu Xu, Sijie Zhu, Chunyuan Li, Chia-Wen Kuo, Fan Chen, Xinyao Wang, Guang Chen, Dawei Du, Ye Yuan, Longyin Wen "Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model", 2024 [arXiv]
Selected Publications
The following are selected journal and conference papers from 61 co-author papers, highlighting 1 T-PAMI, 1 IJCV, 5 T-IP, 1 T-MM, 3 T-CYB, 3 T-CSVT, 1 CVIU, 6 CVPR, 4 ECCV, 3 AAAI, and 2 ACM MM.
Open Set Action Recognition via Multi-Label Evidential Learning. Chen Zhao, Dawei Du, Anthony Hoogs, Christopher Funk. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [PDF]
Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition. Dawei Du, Ameya Shringi, Anthony Hoogs, Christopher Funk. IEEE Winter Conference on Applications of Computer Vision (WACV), 2023. [PDF]
MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification. Daniel Davila*, Dawei Du*, Bryon Lewis, Christopher Funk, Joseph Van Pelt, Roderic Collins, Kellie Corona, Matt Brown, Scott McCloskey, Anthony Hoogs, Brian Clipp. IEEE Winter Conference on Applications of Computer Vision (WACV), 2023. [PDF][Code] (*equal contribution)
Unbiased Multi-Modality Guidance for Image Inpainting. Yongsheng Yu, Dawei Du, Libo Zhang, Tiejian Luo. European Conference on Computer Vision (ECCV), 2022. [PDF][Code]
Cascade Transformers for End-to-End Person Search. Rui Yu, Dawei Du, Rodney LaLonde, Daniel Davila, Christopher Funk, Anthony Hoogs, Brian Clipp. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [PDF][Code]
Multi-Granularity Alignment Domain Adaptation for Object Detection. Wenzhang Zhou, Dawei Du, Libo Zhang, Tiejian Luo, Yanjun Wu. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [PDF][Code]
Detection and Tracking Meet Drones Challenge. Pengfei Zhu*, Longyin Wen*, Dawei Du*, Xiao Bian, Heng Fan, Qinghua Hu, Haibin Ling. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021. [PDF] (*equal contribution)
Graph Regularized Flow Attention Network for Video Animal Counting from Drones. Pengfei Zhu, Tao Peng, Dawei Du*, Hongtao Yu, Libo Zhang, Qinghua Hu. IEEE Transactions on Image Processing (TIP), 2021. [PDF] (*corresponding author)
Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark. Longyin Wen*, Dawei Du*, Pengfei Zhu, Qinghua Hu, Qilong Wang, Liefeng Bo, Siwei Lyu. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. (*equal contribution) [PDF][Code]
SiamCAN: Real-time Visual Tracking based on Siamese Center-aware Network. Wenzhang Zhou, Longyin Wen, Libo Zhang, Dawei Du, Tiejian Luo, Yanjun Wu. IEEE Transactions on Image Processing (TIP), 2021. [PDF]
Embedding Perspective Analysis into Multi-Column Convolutional Neural Network for Crowd Counting. Yifan Yang, Guorong Li, Dawei Du, Qingming Huang, Nicu Sebe. IEEE Transactions on Image Processing (TIP), 2021. [PDF]
Rethinking Object Detection in Retail Stores. Yuanqiang Cai, Longyin Wen, Libo Zhang, Dawei Du, Weiqiang Wang. AAAI Conference on Artificial Intelligence (AAAI), 2021. [PDF]
Iterative Knowledge Distillation for Automatic Check-Out. Libo Zhang, Dawei Du*, Congcong Li, Yanjun Wu, Tiejian Luo. IEEE Transactions on Multimedia (TMM), 2020. [PDF] (*corresponding author)
Guided Attention Network for Object Detection and Counting on Drones. Yuanqiang Cai, Dawei Du, Libo Zhang, Longyin Wen, Weiqiang Wang, Yanjun Wu, Siwei Lyu. ACM International Conference on Multimedia (ACM MM, oral), 2020. [PDF]
Learning Semantic Neural Tree for Human Parsing. Ruyi Ji*, Dawei Du*, Libo Zhang, Longyin Wen, Yanjun Wu, Chen Zhao, Feiyue Huang, Siwei Lyu. European Conference on Computer Vision (ECCV), 2020. [PDF] (*equal contribution)
Spatial Attention Pyramid Network for Unsupervised Domain Adaptation. Congcong Li, Dawei Du, Libo Zhang, Longyin Wen, Tiejian Luo, Yanjun Wu, Pengfei Zhu. European Conference on Computer Vision (ECCV), 2020. [PDF]
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization. Ruyi Ji, Longyin Wen, Libo Zhang, Dawei Du, Yanjun Wu, Chen Zhao, Xianglong Liu, Feiyue Huang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [PDF][Code]
UA-DETRAC: A New Benchmark and Protocol for Multi-Object Tracking. Longyin Wen, Dawei Du, Zhaowei Cai, Zhen Lei, Ming-Ching Chang, Honggang Qi, Jongwoo Lim, Ming-Hsuan Yang, Siwei Lyu. Computer Vision and Image Understanding (CVIU), 2020. [PDF][Project Page]
The unmanned aerial vehicle benchmark: Object detection, tracking and baseline. Hongyang Yu, Guorong Li, Weigang Zhang, Qingming Huang, Dawei Du, Qi Tian, Nicu Sebe. International Journal of Computer Vision (IJCV), 2020. [PDF]
Data Priming Network for Automatic Check-Out. Congcong Li*, Dawei Du*, Libo Zhang, Tiejian Luo, Yanjun Wu, Qi Tian, Longyin Wen, Siwei Lyu. ACM International Conference on Multimedia (ACM MM), 2019. [PDF][Code] (*equal contribution)
Detecting Small Objects Using a Channel-Aware Deconvolutional Network. Kaiwen Duan, Dawei Du, Honggang Qi and Qingming Huang. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019. [PDF]
Learning Non-Uniform Hypergraph for Multiple Object Tracking. Longyin Wen*, Dawei Du*, Shengkun Li, Xiao Bian, and Siwei Lyu. AAAI Conference on Artificial Intelligence (AAAI), 2019. [PDF][Code] (*equal contribution)
Scale-Invariant Fully Convolutional Network: Detecting Hands Efficiently. Dan Liu, Dawei Du, Libo Zhang, Tiejian Luo, Yanjun Wu, Feiyue Huang and Siwei Lyu. AAAI Conference on Artificial Intelligence (AAAI), 2019. [PDF][Code]
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking. Dawei Du, Yuankai Qi, Hongyang Yu, Yifan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, and Qi Tian. European Conference on Computer Vision (ECCV), 2018. [PDF][Project Page]
Iterative Graph Seeking for Object Tracking. Dawei Du, Longyin Wen, Honggang Qi, Qingming Huang, Qi Tian, and Siwei Lyu. IEEE Transactions on Image Processing (TIP), 27(4): 1808-1821, 2018. [PDF][Code]
Global Contrast Enhancement Detection via Deep Multi-Path Network. Cong Zhang, Dawei Du*, Lipeng Ke, Honggang Qi, and Siwei Lyu. IEEE International Conference on Image Processing (ICPR), 2018. [PDF][Code][Models] (*corresponding author)
Geometric Hypergraph Learning for Visual Tracking. Dawei Du, Honggang Qi, Longyin Wen, Qi Tian, Qingming Huang, and Siwei Lyu. IEEE Transactions on Cybernetics (TCYB), 2017. [PDF]
Online Deformable Object Tracking based on Structure-Aware Hyper-graph. Dawei Du, Honggang Qi, Wenbo Li, Longyin Wen, Qingming Huang, and Siwei Lyu. IEEE Transactions on Image Processing (TIP), 25(8):3572–3584, 2016. [PDF][Demo] [Project Page]
Hybrid Strucuture Hypergraph for Online Deformable Object Tracking. Shengkun Li, Dawei Du, Longyin Wen, Ming-Ching Chang, and Siwei Lyu. IEEE International Conference on Image Processing (ICIP), 2017. [PDF][Code]
JOTS: Joint Online Tracking and Segmentation. Longyin Wen, Dawei Du, Zhen Lei, Stan Z. Li, Ming-Hsuan Yang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 2226-2234, 2015. [PDF][Project Page]
Abnormal event detection in crowded scenes based on Structural Multi-scale Motion Interrelated Patterns. Dawei Du, Honggang Qi, Qingming Huang, Wei Zeng, Changhua Zhang. IEEE International Conference on Multimedia and Expo (ICME): 2013. [PDF]
Sources
Deform-SOT Benchmark [Project Page]
UAVDT Benchmark [Project Page]
UA-DETRAC Benchmark [Project Page]
Professional Acitivities
• Journal Reviewer for Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Multimedia (TMM), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Intelligent Transportation Systems (TITS), IEEE Transactions on Information Forensics and Security (TIFS), IEEE Transactions on Knowledge and Data Engineering (TKDE), ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), IEEE Systems, Man and Cybernetics: Systems (TSMCA), IEEE Signal Processing Letters (SPL), Machine Vision and Applications (MVAP), Neurocomputing, Computing and Informatics, IET Computer Vision, Sensor.
• Conference Reviewer for ICIP 2016~2019, CVPR 2019, 2021~2024, ICCV 2019~2021, ECCV 2020~2022, ICPR 2020, AAAI 2021~2022, IJCAI 2021~2022, ICLR 2024.
• Senior Program Committee for IJCAI 2021.
• Area Chair for AVSS 2019, MIPR 2022.
• Workshop Organizer for AVSS 2018, ICCV 2019, ECCV 2020, WACV 2023.
Awards and Honors
• 2019 Outstanding Doctoral Dissertation in Chinese Academy of Sciences (100 doctoral dissertations from all majors in 2018~2019)
• 2018 Excellent Graduate in Chinese Academy of Sciences (1 recipient in CSE department)
• 2018 Presidential Outstanding Prize in Chinese Academy of Sciences (1 recipient in CSE department)
• 2010 Excellent Graduate in University of Electronic Science and Technology of China (UESTC)
• 2010 Outstanding Dissertation in University of Electronic Science and Technology of China (UESTC)
• 2009 Meritorious Winner of 2009 Mathematical Contest in Modeling (MCM)
Collaborators
Dr. Longyin Wen (ByteDance, Inc.)
Prof. Libo Zhang (Institute of Software, Chinese Academy of Sciences)
Prof. Siwei Lyu (University at Buffalo, State University of New York)
Prof. Pengfei Zhu (Tianjin University)
Prof. Haibin Ling (Stony Brook University)
Prof. Qingming Huang (University of Chinese Academy of Sciences)
Dr. Anthony Hoogs (Kitware, Inc.)