Siyu Huang

Siyu Huang (黄思羽)

Postdocotoral Fellow at Harvard University
Research Interests: Computer Vision, Deep Learning, Multimedia Analysis

Address: 150 Western Ave, Boston, MA 02134
Email: huang@seas.harvard.edu
My Google Scholar

Education

Ph.D. at College of Information Science and Electronic Engineering, Zhejiang University
Sept 2014 - July 2019 Hangzhou, China
Supervised by Prof. Zhongfei (Mark) Zhang and Prof. Xi Li.
Dissertation: "Semantic Understanding-Aware Neural Network Architecture Design for Video Surveillance"
Successfully defended at June, 2019
Visiting Scholar at Language Technologies Institute, School of Computer Science, Carnegie Mellon University
Jan 2018 - Jan 2019 Pittsburgh, USA
Supervised by Prof. Alexander G. Hauptmann.
Bachelor at College of Information Science and Electronic Engineering, Zhejiang University
Sept 2010 - June 2014 Hangzhou, China
Chu Kochen Honors College
Graduation Thesis: "Feature Learning and Its Applications"

Work Experiences

Postdoctoral Fellow at Harvard University
Visual Computing Group (VCG), School of Engineering and Applied Sciences
Nov 2021 - Now Boston, USA
Working with Prof. Hanspeter Pfister
Research Fellow at Nanyang Technological University
Rapid-Rich Object Search (ROSE) Lab, School of Electrical and Electronic Engineering
Feb 2021 - Oct 2021 Singapore
Working with Dr. Bihan Wen
Research Scientist at Baidu Research
Big Data Lab
July 2019 - Jan 2021 Beijing, China
Working with Prof. Dejing Dou and Prof. Jun Huan
Research Intern at Baidu Research
Big Data Lab
Mar 2019 - June 2019 Beijing, China
Supervised by Prof. Jun Huan.

Preprint

QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity [pdf]
Siyu Huang*, Jie An*, Donglai Wei, Jiebo Luo, Hanspeter Pfister
arXiv:2212.10431, 2022
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal [pdf]
Lanqing Guo, Chong Wang, Wenhan Yang, Siyu Huang, Yufei Wang, Hanspeter Pfister, Bihan Wen
arXiv:2212.04711, 2022

Publications

Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Xuhong Li, Haoyi Xiong, Siyu Huang, Shilei Ji, Dejing Dou
Machine Learning, 2023
ShadowFormer: Global Context Helps Shadow Removal
Lanqing Guo, Siyu Huang, Ding Liu, Hao Cheng, Bihan Wen
AAAI, 2023
Making Your First Choice: To Address Cold Start Problem in Vision Active Learning [pdf]
Liangyu Chen, Yutong Bai, Siyu Huang, Yongyi Lu, Bihan Wen, Alan Yuille, Zongwei Zhou
NeurIPS Workshop on Human in the Loop Learning, 2022
Temporal Output Discrepancy for Loss Estimation-based Active Learning [pdf] [code]
Siyu Huang, Tianyang Wang, Haoyi Xiong, Bihan Wen, Jun Huan, Dejing Dou
IEEE Transactions on Neural Networks and Learning Systems, 2022
MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts [pdf]
Weibin Liao, Haoyi Xiong, Qingzhong Wang, Yan Mo, Xuhong Li, Yi Liu, Zeyu Chen, Siyu Huang, Dejing Dou
MICCAI, 2022
A Unified Framework for Bidirectional Prototype Learning from Contaminated Faces across Heterogeneous Domains [pdf]
Meng Pang, Binghui Wang, Siyu Huang, Yiu-ming Cheung, Bihan Wen
IEEE Transactions on Information Forensics and Security, 2022
Parameter-Free Style Projection for Arbitrary Style Transfer [pdf] [code] [Official PaddleHub]
Siyu Huang, Haoyi Xiong, Tianyang Wang, Bihan Wen, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou
ICASSP, 2022
BM-NAS: Bilevel Multimodal Neural Architecture Search [pdf] [video] [code]
Yihang Yin, Siyu Huang, Xiang Zhang
AAAI, 2022 (Oral)
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators [pdf] [video] [code]
Yihang Yin, Qingzhong Wang, Siyu Huang, Haoyi Xiong, Xiang Zhang
AAAI, 2022
Boosting Active Learning via Improving Test Performance [pdf] [code]
Tianyang Wang, Xingjian Li, Pengkun Yang, Guosheng Hu, Xiangrui Zeng, Siyu Huang, Cheng-Zhong Xu, Min Xu
AAAI, 2022
Semi-Supervised Active Learning with Temporal Output Discrepancy [pdf] [supp] [poster] [slides] [video] [code]
Siyu Huang, Tianyang Wang, Haoyi Xiong, Jun Huan, Dejing Dou
ICCV, 2021
ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement [pdf] [code]
Rongkai Zhang, Lanqing Guo, Siyu Huang, Bihan Wen
ACM MM, 2021
ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows [pdf] [supp] [code]
Jie An*, Siyu Huang*, Yibing Song, Dejing Dou, Wei Liu, Jiebo Luo
CVPR, 2021
Dual Low-Rank Multimodal Fusion [pdf]
Tao Jin*, Siyu Huang*, Yingming Li, Zhongfei Zhang
EMNLP Findings, 2020
Neighbours Matter: Image Captioning with Similar Images [pdf]
Qingzhong Wang, Jiuniu Wang, Antoni Chan, Siyu Huang, Haoyi Xiong, Xingjian Li, Dejing Dou
BMVC, 2020
Generating Person Images with Appearance-aware Pose Stylizer [pdf] [code]
Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huan, Dejing Dou
IJCAI, 2020
SBAT: Video Captioning with Sparse Boundary-Aware Transformer [pdf]
Tao Jin, Siyu Huang, Ming Chen, Yingming Li, Zhongfei Zhang
IJCAI, 2020
Stacked Pooling for Boosting Scale Invariance of Crowd Counting [pdf] [code]
Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann
ICASSP, 2020
Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning [pdf]
Tao Jin, Siyu Huang*, Yingming Li, Zhongfei Zhang
EMNLP, 2019
Text Guided Person Image Synthesis [pdf] [supp]
Xingran Zhou, Siyu Huang*, Bin Li, Yingming Li, Jiachen Li, Zhongfei Zhang.
CVPR, 2019
User-Ranking Video Summarization with Multi-Stage Spatio-Temporal Representation [pdf] [demo]
Siyu Huang, Xi Li, Zhongfei Zhang, Fei Wu, Junwei Han.
IEEE Transactions on Image Processing, 2019
Perceiving Physical Equation by Observing Visual Scenarios [pdf]
Siyu Huang*, Zhi-Qi Cheng*, Xi Li, Xiao Wu, Zhongfei Zhang, Alexander Hauptmann.
NeurIPS Workshop on Modeling the Physical World, 2018
TVT: Two-View Transformer Network for Video Captioning [pdf]
Ming Chen, Yingming Li, Zhongfei Zhang, Siyu Huang.
ACML, 2018
GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning [pdf] [slides] [poster]
Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann.
ACM MM, 2018 (Oral)
Learning to Transfer: Generalizable Attribute Learning with Multitask Neural Model Search [pdf]
Zhi-Qi Cheng, Xiao Wu, Siyu Huang, Jun-Xiu Li, Alexander Hauptmann, Qiang Peng.
ACM MM, 2018
Body Structure Aware Deep Crowd Counting [pdf] [demo]
Siyu Huang, Xi Li, Zhongfei Zhang, Fei Wu, Shenghua Gao, Rongrong Ji, Junwei Han.
IEEE Transactions on Image Processing, 2018
Deep Learning Driven Visual Path Prediction From a Single Image [pdf] [dataset]
Siyu Huang, Xi Li, Zhongfei Zhang, Zhouzhou He, Fei Wu, Wei Liu, Jinhui Tang, Yueting Zhuang.
IEEE Transactions on Image Processing, 2016

Contest

AI Challenger Global Contest, 2017
Organizers: Sinovation Ventures, ByteDance, Sogou
Track: English-Chinese Simultaneous Interpretation Competition
Ranked: 2nd/675 teams [news] [short slides]
Team Members：Siyu Huang (team leader), Ming Chen, Lei Wang

Patents

Data mining system, method, and storage medium. Ji Liu, Haoyi Xiong, Siyu Huang, Dejing Dou. Filed, US20210248139A1, CN111597226A
Pose transfer system, method, and storage medium. Siyu Huang, Haoyi Xiong, Dejing Dou. Filed, CN111680623A
A text-guided person image generation algorithm. Xingran Zhou, Siyu Huang, Bin Li, Yingming Li, Zhongfei Zhang. Granted, CN110021051B
A one-dimensional sequence learning based video summarization algorithm. Siyu Huang, Xi Li, Zhongfei Zhang. Granted, CN107729821A
A pedestrian body appearance structure based crowd counting algorithm. Siyu Huang, Xi Li, Zhongfei Zhang. Granted, CN106815563B

Invited Talks and Presentations

Conference Presentation: "Parameter-Free Style Projection for Arbitrary Style Transfer".
International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Virtual. May 2022.
Conference Presentation: "Semi-Supervised Active Learning with Temporal Output Discrepancy".
International Conference on Computer Vision (ICCV). Virtual. Oct 2021.
Invited Talk: “Visual Understanding and Prediction Techniques”.
UESTC International Forum for Young Scholars. Virtual, Sept 2021.
Conference Presentation: "Generating Person Images with Appearance-aware Pose Stylizer".
29th International Joint Conference on Artificial Intelligence (IJCAI). Virtual. Jan 2021.
Open Course: “Automated Deep Learning: Theory and Applications”.
Baidu World Congress, Branch Forum. Beijing, Sept 2020.
Conference Tutorial: “A Tutorial on Neural Architecture Search”.
IEEE International Conference on Data Mining (ICDM) Tutorial on Automated Deep Learning: Theory, Algorithms, Platforms, and Applications. Beijing, Nov 2019.
Open Course: “NAS with RL and Differentiable NAS in AutoDL”.
Baidu Create 2019 - Baidu AI Developer Conference. Beijing, July 2019.
Invited Talk: “Deep Cross-Modal Knowledge Mining”.
Forum for Talented Young Scholar in Computer Science. Zhejiang University, Hangzhou, May 2019.
Invited Talk: "Text Guided Person Image Synthesis".
Baidu Research. Beijing, China. Mar 2019.
Conference Presentation: "GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning".
ACM International Conference on Multimedia (ACM MM). Seoul, Korea. Oct 2018. [photo]
Invited Talk: "Greedy Neural Architecture Search for Multi-Attribute Learning".
State University of New York (SUNY) at Binghamton, Binghamton, USA. Sept 2018.

Awards

Outstanding Research. Baidu Research. 2020.
Excellent Postgraduate Students' Award. Zhejiang University. 2019.
ACM MM Student Travel Award. ACM SIGMM. 2018.
National Scholarship for PhD Student. Ministry of Education of the P.R.C. 2017. Awarded to top 1% PhD students.
Postgraduate of Merit. Zhejiang University. 2017, 2018.
Award of Honor for Postgraduate. Zhejiang University. 2017, 2018.
Graduate of Chu Kochen Honors College. Zhejiang University. 2014.
Excellent Bachelor’s Thesis "Feature Learning and Its Applications". Zhejiang University. 2014.

Professional Services

Meta-reviewer:

Journal reviewer:

Conference reviewer:

Since Nov, 2018