Jialian Wu (吴嘉濂)


Ph.D. Candidate
State University of New York at Buffalo
Email: jialianw at buffalo dot edu

[Resume] [Github] [Linkedin]

[Google Scholar]

Short Bio


    I am a final-year Ph.D. candidate at the CSE department, State University of New York at Buffalo (UB), advised by Prof. Junsong Yuan. Before that, I got B.Eng. from Tianjin University, where I continued one-year M.Eng. study and left for UB before finishing the degree. I received the Best Graduate Research Award and Best First Year Achiever Award from the CSE department of UB. My previous research experience lies in object understanding in videos and images including detection, segmentation, and tracking; open-set object understanding with vision and language.

Publications

GRiT: A Generative Region-to-text Transformer for Object Understanding
Jialian Wu, Jianfeng Wang, Zhengyuan Yang, Zhe Gan, Zicheng Liu, Junsong Yuan, and Lijuan Wang
ArXiv Preprint, 2022
PDF Code
Our new work, GRiT, is a general and open-set object understanding framework that localizes objects and can generate any style of free-form texts it was trained with to describe objects, e.g., class names, descriptive sentences (including object attributes, actions, etc). GRiT can be applied in various region/object-level tasks, e.g., object detection, object captioning.
Efficient Video Instance Segmentation via Tracklet Query and Proposal
Jialian Wu, Sudhir Yarram, Hui Liang, Tian Lan, Junsong Yuan, Jayan Eledath, and Gerard Medioni
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Project page Video PDF
Track to Detect and Segment: An Online Multi-Object Tracker
Jialian Wu, Jiale Cao, Liangchen Song, Yu Wang, Ming Yang, and Junsong Yuan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Project page Video PDF Code
ForestDet: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
Jialian Wu, Liangchen Song, Qian Zhang, Ming Yang, and Junsong Yuan
IEEE Transactions on Multimedia (TMM), 2021. (Extension of MM'20)
PDF Code
Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians
Jialian Wu, Chunluan Zhou, Ming Yang, Qian Zhang, Yuan Li, and Junsong Yuan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
PDF Supp
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
Jialian Wu, Liangchen Song, Tiancai Wang, Qian Zhang, and Junsong Yuan
ACM International Conference on Multimedia (ACM MM), 2020.
PDF Code
Self-Mimic Learning for Small-scale Pedestrian Detection
Jialian Wu, Chunluan Zhou, Qian Zhang, Ming Yang, and Junsong Yuan
ACM International Conference on Multimedia (ACM MM), 2020.
PDF Supp
Stacked Homography Transformations for Multi-View Pedestrian Detection
Liangchen Song, Jialian Wu, Ming Yang, Qian Zhang, Yuan Li, and Junsong Yuan
IEEE International Conference on Computer Vision (ICCV), 2021 (Oral).
PDF
Handling Difficult Labels for Multi-label Image Classification via Uncertainty Distillation
Liangchen Song, Jialian Wu, Ming Yang, Qian Zhang, Yuan Li, and Junsong Yuan
ACM International Conference on Multimedia (ACM MM), 2021.
PDF
Robust Knowledge Transfer via Hybrid Forward on the Teacher-Student Model
Liangchen Song, Jialian Wu, Ming Yang, Qian Zhang, Yuan Li, and Junsong Yuan
AAAI Conference on Artificial Intelligence (AAAI), 2021.
PDF

Internships


Professional Services


Awards


  • Outstanding Bachelor Thesis, Tianjin University, 2018.
  • Tianjin City Fellowship, 2016.
Music is a great passion of my life:) My favorite music is here