Zhibo Yang

I am a 5th-year PhD student at the Department of Computer Science, Stony Brook University, under the supervision of Dimitris Samaras. I work closely with Minh Hoai Nguyen and Gregory Zelinsky. I received my MPhil degree from the Department of Information Engineering at The Chinese University of Hong Kong under the supervision of Prof. Wing Cheong Lau and Prof. Chen Change Loy. Before that, I obtained my bachelor degree from Harbin Institute of Technology.

My research interests broadly include human vision understanding, metric learning, imitation learning and object detection. Currently, my work primarily focuses on building artificial neural network models of human vision system.

Email  /  CV  /  Google Scholar  /  Github

profile photo
News
  • [10/04/21] One paper is accepted to WACV 2022.
  • [09/18/21] One paper is accepted to Briefings in Bioinformatics (IF=11.6)!
  • [05/05/21] I am awarded the Outstanding Reviewer of CVPR 2021!
  • [04/16/21] One paper is accepted to Scientific Reports.
  • [01/04/21] One paper is accepted to IEEE TNSM.
Research
hps Characterizing Target-absent Human Attention
Yupei Chen, Zhibo Yang, Souradeep Chakraborty, Sounak Mondal, Seoyoung Ahn, Dimitris Samaras, Minh Hoai, Gregory Zelinsky
CVPR Workshops, 2022
supplement

We present COCO-FreeView, which complements COCO-Search18 dataset with free-viewing fixations for the same images, enabling joint analysis of search fixations and freeviewing fixations.

hps Hierarchical Proxy-based Loss for Deep Metric Learning
Zhibo Yang, Muhammet Bastan, Xinliang Zhu, Doug Gray, Dimitris Samaras
WACV, 2022
supplement / video / blog

We present a framework that leverages this implicit hierarchy by imposing a hierarchical structure on the proxies and can be used with any existing proxy-based loss.

drug_review Artificial Intelligence in Drug Discovery: Applications and Techniques
Jianyuan Deng, Zhibo Yang, Iwao Ojima, Dimitris Samaras, Fusheng Wang
Briefings in Bioinformatics, 2021

We conduct a comprehensive survey on AI-driven drug discovery. We also released a Github repository (link) for a collection of related papers in AI-driven Drug Discovery.

SR21 COCO-Search18 fixation dataset for predicting goal-directed attention control
Yupei Chen, Zhibo Yang, Seoyoung Ahn, Dimitris Samaras, Minh Hoai, Gregory Zelinsky
Scientific Reports, 2021
dataset

We introduce COCO-Search18, the first dataset of laboratory-quality goal-directed behavior large enough to train deep-network models.

vp21 Mosaic: Advancing User Quality of Experience in 360-Degree Video Streaming with Machine Learning
Sohee Park, Arani Bhattacharya, Zhibo Yang, Samir R. Das and Dimitris Samaras,
IEEE Transactions on Network and Service Management, 2021

We develop a comprehensive approach called Mosaic that combines a powerful neural network-based viewport prediction with a rate control mechanism such that the 360-degree video quality of experience is optimized subject to a given network capacity.

SMILES20 Towards Better Opioid Antagonists Using Deep Reinforcement Learning
Jianyuan Deng*, Zhibo Yang*, Yao Li, Dimitris Samaras, Fusheng Wang
arXiv, 2020

We develop a deep reinforcement learning framework to discover potential lead compounds as better opioid antagonists with enhanced brain retention ability.

irl_cvpr20 Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning
Zhibo Yang, Lihan Huang, Yupei Chen, Seoyoung Ahn, Zijun Wei, Gregory Zelinsky, Dimitris Samaras and Minh Hoai
CVPR (Oral), 2020, Best Paper Nomination
supplement / code / dataset / talk

We propose the first inverse reinforcement learning (IRL) model to learn the internal reward function and policy used by humans during visual search.

iccvw19 Benchmarking Gaze Prediction for Categorical Visual Search
Gregory Zelinsky, Zhibo Yang, Lihan Huang, Yupei Chen, Seoyoung Ahn, Zijun Wei, Hossein Adeli, Dimitris Samaras and Minh Hoai
CVPR Workshops (Oral), 2019
code / dataset

We present a carefully created dataset of search fixations for two target categories, microwaves and clocks, curated from the COCO2014 dataset

tip19 HiQ: Robust and Fast Decoding of High-Capacity QR Codes
Zhibo Yang, Huanle Xu, Jianyuan Deng, Chen Change Loy and Wing Cheong Lau
IEEE Transactions on Image Processing, 2018
code / dataset / video

We put forth and implement a framework for high-capacity color QR codes equipped with our methods, called HiQ. A fast color QR code decoding algorithm is also presented.

Services

Reviewer for CVPR, ICCV, ECCV, AAAI, WACV, BMVC, TIP, TPAMI; Student volunteer for ISIT15, Infocom15


Design and code stolen from Jon Barron.