Home Page
The Skyline of Hang
Let's explore the world of AI.

About Me
I am an assistant professor working in the
Department of Computer Science and Technology at Tsinghua University, working with Prof. Bo Zhang and Prof. Jun Zhu. My research interests lie in the development of computer vision and machine learning
algorithms for solving scientific and engineering problems. My current work involves both the foundations of interpretable machine learning and the
applications of image/video analysis. Before joining Tsinghua, I received my Ph. D. degree from Shanghai Jiaotong University and worked as a visiting scholar at Carnegie Mellon University.
Dr. Hang Su (苏 航)
Assist. Prof. @ THU
News BUZZ
July 2018- Our paper "Essay-Anchor Attentive Multi-Modal Bilinear Pooling for Textbook Question Answering" wins ICME2018 Platinum Best Paper Award!
- One paper on Video to Video translation is accepted by ACM Multimedia 2018.
June 2018
- One paper on Interpretable Machine Learning is accepted by ICML/IJCAI 2018 workshop on “Explainable Artificial Intelligence (XAI)”
- One paper on Deep Reinforcement Learning in the scenario of adversarial games is accepted by ICML2018 workshop on " Exploration in Reinforcement Learning"
- One paper on Deep Structured Generative model with applications on image synthesis is accepted by ICML2018 workshop on " Theoretical Foundations and Applications of Deep Generative Models"
May 2018
- One paper on adversarial samples in machine learning is accepted by ICML2018 workshop on " Geometry in Machine Learning"
Apr. 2018
- One paper on Chinese Character Generation with disentangled deep generative model is accepted by IJCAI2018.
- One paper on TextBook Question Answering by symbolic-neural reasoning is accepted by ICME2018 as oral.
-
One proposal on "Deep Reinforcement Learning with applications on Video Games " was funded by Tencent AI Lab Rhino-Bird Joint Research Program.
One paper on interpreting DNNs by identifying the critical data routing paths is accepted by CVPR2018 as spotlight.
One paper on joint reasoning over images and symbolic texts for TQA is accepted by CVPR2018 as spotlight.
One paper on boosting the performance of adversarial attacks with momentum is accepted by CVPR2018 as spotlight.
One paper on understanding crowd behaviors by imitating the decision-making process is presented in AAAI2018.
One paper on person re-identification based on graph correspondence transfer is presented in AAAI2018.
-
One proposal on "
Explainable Machine Learning" was funded by MSRA Joint Research.
-
One proposal on "
Interpretable
Deep Learning and Visual Relation
Understanding
" was funded by Intel Labs China.
- One paper on facial sketch retrieval by generating photorealistic faces with conditional GAN is accepted by ICASSP2018.