Qian Yu 于 茜


Responsive image

Associate Professor

Beihang University
37 Xueyuan Rd. Haidian District, Room 419 Zengxianzi Building(曾宪梓楼)
Beijing, China
Email: qianyu@buaa.edu.cn
[Google Scholar] [Github]

I am an associate professor at the School of Software, Beihang University . Before I joined Beihang in 2020, I was a postdoctoral research fellow at UC Berkeley / ICSI during 2018~2019, working with Prof. Stella Yu. I received my Ph.D. degree from Queen Mary University of London in 2018, advised by Prof. Yi-Zhe Song and Prof. Tao (Tony) Xiang.

My research is on computer vision and deep learning, with a foucs on sketch understanding and sketch-related applications. I am also interested in video understanding and medical image analysis.

For Prospective Students: I am actively looking for highly-motivated Ph.D., Master students and Research Assistants (undergraduate/graduate level). Please email me with your CV and transcripts if you are interested in my research.

News

[Jun.2024] Our SketchSampler++ paper got accepted by T-PAMI!
[Jun.2024] One paper got accepted by TMI!
[Feb.2024] Two papers got accepted by CVPR'24!
[Dec.2023] Three papers got accepted by AAAI'24!
[Dec.2023] Selected for the Ninth Young Elite Scientists Sponsorship Program by CAST(中国科协青年人才托举工程)!
[Aug.2023] Will serve as Area Chair of CVPR'24!
[Jul.2023] Will serve as Social Media & Web Chair of ACM MM'24!
[Sep.2023] Awarded the CCF- Baidu Open Fund Project(CCF-百度松果基金项目)!
[Sep.2023] Our DiffSketcher paper got accepted by NeurIPS 2023!
[Sep.2023] One paper got accepted by PG'23!
[Jul.2023] One paper got accepted by ACM MM'23!
[Jun.2023] One paper got accepted by MICCAI'23!
[Mar.2023] One paper got accepted by T-CSVT!
[Feb.2023] One paper got accepted by ICDE'23!
[Nov.2022] One paper got accepted by AAAI'23 (Student Abstract Track)!
[Oct.2022] One paper got accepted by WACV'22!
[Sep.2022] One paper got accepted by T-CSVT!
[Jul.2022] One paper got accepted by ECCV'22!
[Apr.2022] Our Workshop on Sketching for Human Expressivity has been accepted by ECCV'22.
[Dec.2021] Co-organized the workshop on Sketching Understanding and Advanced Applications at PRCV'21.
[Oct.2021] Co-organized the 1st workshop on Sketching for Human Expressivity (SHE) at ICCV'21!
[Jul.2021] One conference paper on spatio-temporal video grounding (STVG) got accepted by ICCV 2021!
[Jun.2021] One journal paper on human-centric STVG got accepted by IEEE T-CSVT!
[Apr.2021] Gave a talk "Sketch-based photo and 3D generation" at CCF-CV seminar (CCF-CV视界无限)
[Feb.2021] One journal paper on AI for Civil Engineering got published by Automation in Construction!
[Dec.2020] Organized the CCF-CV series talk (CCF-CV走进高校) at Beihang. See details here (in Chinese).
[Oct.2020] One journal paper on AI for Civil Engineering got published on EEEV!
[Sep.2020] One journal paper on sketch-based photo retrieval got accepted by IJCV!
[Jul.2020] One conference paper on sketch-based photo synthesis got accepted at ECCV 2020 as Oral presentation!
[Jan.2020] Joined School of Software, Beihang University. New journey!

Selected Publications

Full publication list can be found on Google Scholar.
*: corresponding author #: equal contribution

2024

Responsive image

3D Reconstruction From a Single Sketch via View-Dependent Depth Sampling
Chenjian Gao#, Xilin Wang#, Qian Yu*, Lu Sheng, Jing Zhang, Xiaoguang Han, Yi-Zhe Song, and Dong Xu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024.
[ Paper (preprint) ]-- [ DOI ]
Responsive image

SVGDreamer: Text Guided SVG Generation with Diffusion Model
Ximing Xing, Haitao Zhou, Chuang Wang, Jing Zhang, Dong Xu, Qian Yu*.
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2024.
[ Paper ]-- [ Project Page ]
Responsive image

GenesisTex: Adapting Image Denoising Diffusion to Texture Space
Chenjian Gao, Boyan Jiang, Xinghui Li, Yingpeng Zhang, Qian Yu*.
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2024.
[ Paper ]

2023

Responsive image

Distortion-aware Transformer in 360 Salient Object Detection
Yinjie Zhao, Lichen Zhao, Qian Yu*, Jing Zhang, Lu Sheng, Dong Xu.
ACM Multimedia(MM), 2023. Oral
[ Paper ]
Responsive image

DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu*, Dong Xu.
Conference on Neural Information Processing Systems(NeurIPS), 2023.
[ Paper ]-- [ Project Page ]

2022

Responsive image

SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling
Chenjian Gao, Qian Yu*, Lu Sheng, Yi-Zhe Song, Dong Xu.
European Conference on Computer Vision(ECCV), 2022.
[ Paper ]
Responsive image

Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization
Weiqi Sun, Rui Su, Qian Yu*, Dong Xu.
IEEE Transactions on Circuits and Systems for Video Technology(T-CSVT), 2022.
[ Paper ]

2021 and before

Responsive image

STVGBert: A Visual-Linguistic Transformer Based Framework for Spatio-Temporal Video Grounding
Rui Su, Qian Yu, Dong Xu.
IEEE International Conference on Computer Vision (ICCV), 2021.
[ Paper ]-- [ Bibtex ]
Responsive image

Fine-Grained Instance-Level Sketch-Based Image Retrieval
Qian Yu#*, Jifei Song#, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales.
International Journal of Computer Vision (IJCV), 2021.
[ Paper ]--[ DOI ]-- [ Bibtex ]
Responsive image

Human-centric Spatio-temporal Video grounding with Visual Transformers
Zongheng Tang, Yue Liao, Si Liu, Guanbin Li, Xiaojie Jin, Hongxu Jiang, Qian Yu, Dong Xu
IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2021.
[ Paper ]--[ DOI ]--[ HC-STVG Dataset ]-- [ Bibtex ]
Responsive image



Machine learning-based regional scale intelligent modeling of building information for natural hazard risk management
Chaofeng Wang, Qian Yu, Kincho H. Law, Frank McKenna, Stella X. Yu, Ertugrul Taciroglu, Adam Zsarn{\'o}czay, Wael Elhaddad, Barbaros Cetiner.
Automation in Construction, 2021.
[ Paper ]--[ DOI ]-- [ Bibtex ]
Responsive image


Unsupervised Sketch to Photo Synthesis
Runtao Liu#, Qian Yu#*, Stella X. Yu.
European Conference on Computer Vision (ECCV), 2020. Oral
[ Paper ]--[ supp ]--[ Code ]--[QMUL-Sketch Dataset (Google Drive)]
[QMUL-Sketch Dataset (Baidu Cloud)](Password:68uo)-- [ Bibtex ]
Responsive image

Rapid visual screening of soft-story buildings from street view images using deep learning classification
Qian Yu, Chaofeng Wang, Frank McKenna, Stella X. Yu, Ertugrul Taciroglu, Barbaros Cetiner, Kincho H. Law.
Earthquake Engineering and Engineering Vibration, 2020.
[ Paper ]--[ DOI ]-- [ Bibtex ]
Responsive image


Building Information Modeling and Classification by Visual Learning At A City Scale
Qian Yu, Chaofeng Wang, Barbaros Cetiner, Stella X. Yu, Frank McKenna, Ertugrul Taciroglu, Kincho H. Law.
AI + HADR workshop @ NeurIPS 2019.
[ arXiv Paper ]-- [ Bibtex ]
Responsive image

SketchyScene: Richly-Annotated Scene Sketches
Changqing Zou#, Qian Yu#, Ruofei Du, Haoran Mo, Yi-Zhe Song, Tao Xiang, Chengying Gao, Baoquan Chen, Hao Zhang.
European Conference on Computer Vision (ECCV), 2018.
[ Paper ]--[ Project Page ]-- [ Bibtex ]
Responsive image

Sketch-a-Net: A Deep Neural Network that Beats Humans
Qian Yu*, Yongxin Yang, Feng Liu, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales.
International Journal of Computer Vision (IJCV), 2017.
[ Paper ]--[ DOI ]--[ Code ]-- [ Bibtex ]
Responsive image

Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval
Jifei Song#, Qian Yu#, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales.
IEEE International Conference on Computer Vision (ICCV), 2017.
[ Paper ]--[ supp ]--[ Code ]-- [ Bibtex ]
Responsive image

Sketch Me That Shoe
Qian Yu*, Feng Liu, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Chen-Change Loy.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. Oral
[ Paper ]--[ Code ]--[ Video ]-- [ Bibtex ]
Responsive image

Sketch-a-Net that Beats Humans
Qian Yu#*, Yongxin Yang#, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales.
British Machine Vision Conferenc (BMVC), 2015. Best Scientific Paper
[ Paper ]--[ Video ]-- [ Bibtex ]
Postgraduate Courses:
  • Deep Learning (2021~)
  • Machine Learning (Spring 2021)
  • Undergraduate Course:
  • AI Computing Systems (2021~)


  • Updated February 2022, page created using Bootstrap