Xubin Zhong

I am now a Ph.D candidate student at South China University of Technology (SCUT), under the supervision of Prof. Dacheng Tao and Prof. Changxing Ding at present. I was an intern at Baidu NLP Group from 2023.07 to 2023.10. Before this, I got my bachelor's degree in 2019 and was recommended to study for my doctor's degree at SCUT.

Email  /  Google Scholar  /  Github

I'm interested in computer vision, multi-modality learning, large language model, multi-task learning and human-object interaction detection. Representative papers are listed below.

To the best of our knowledge, DIR is the first approach that enables the one-stage HOI detection models to extract disentangled interaction representations.

To the best of our knowledge, HQM is the first approach that promotes the robustness of DETR-based models from the perspective of hard example mining.

We propose an efficient knowledge distillation model, named Distillation using Oracle Queries (DOQ), which shares parameters between teacher and student networks

We propose a novel one-stage method, namely Glance and Gaze Network (GGNet), which adaptively models a set of action-aware points (ActPoints) via glance and gaze steps.

Through deciphering the visual polysemy of verbs, our approach is demonstrated to outperform state-of-the-art methods by significant margins on the HICO-DET, V-COCO, and HOIVP databases

We propose a novel Polysemy Deciphering Network (PD-Net), which decodes the visual polysemy of verbs for HOI detection

GAC Enterprise Scholarship at SCUT, 2021

Third prize of National Advanced Mathematics Competition, 2018

International Special Prize in Asia Pacific Mathematical Modeling Contest, 2017

National Special Prize in National Energy Conservation and Emission Reduction Competition, 2017

This pape is built upon Jon Barron's website. ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩ ✩
Also, consider using Leonid Keselman's Jekyll fork of this page.