Dan Xu - Homepage

Dan Xu

Assistant Professor
Department of Computer Science and Engineering
Hong Kong University of Sciences and Technology (HKUST)

Address: Clear Water Bay, Kowloon, Hong Kong (MAP)
Office: Room 3505 (Lift 25-26), Academic Building
Homepage: https://www.danxurgb.net or http://www.cse.ust.hk/~danxu
Personal: [Curriculum Viate] and [Google Scholar] and [GitHub] and [LinkedIn] and [Twitter]
Email: danxu at cse.ust.hk or danxuhk at gmail.com

New Events

I am looking for self-motivated Ph.D./MPhil. students, RAs, PostDocs, and Visiting scholars to join my group. Please drop me an email with your CV if you are interested.

Jul. 22, 2021: Two papers including one ORAL (3% acceptance rate) have been accepted by ICCV 2021. The papers and the code will be released soon.

Jul. 03, 2021: One paper on weakly-supervised video action localization has been accepted by ACM MM 2021.

Jun. 30, 2021: One paper on deep visual SLAM has been accepted by IROS 2021.

Mar. 01, 2021: Two works have been accepted by CVPR 2021.

Feb. 25, 2021: I have been invited to serve as Area Chair (AC) for ACM MM 2021.

Nov. 25, 2020: Our work "Probabilistic Graph Attention Networks for Pixel-Wise Dense Prediction" has been accepted by TPAMI 2021 as a regular paper.

Sep. 09, 2020: I am appointed to serve as an Associate Editor (AE) for Springer Journal of the Visual Computer, International Journal of Computer Graphics.

Jun. 15, 2020: Two papers (1 Oral and 1 Poster) are accepted by CVPR 2020. The papers will come out soon.

May. 25, 2020: I am invited to serve as an Area Chair (AC) for ACM MM 2020.

May. 10, 2020: I am invited to serve as an Area Chair (AC) for WACV 2021.

Mar. 10, 2020: I am invited to serve as Programme Committee member of NeurIPS 2020.

Feb. 07, 2020: I am invited to serve as an Area Chair (AC) for ICPR 2020.

Aug. 18, 2019: Our "Dynamic Graph Message Passing Networks" has been Arxived! It outperforms Non-Local Model with much lower FLOPs!

Aug. 10, 2019: Our work of using cycled networks for unsupervised binocular depth estimation has been accepted by TPAMI as a regular paper.

Jul. 22, 2019: We have two papers accepted by ICCV 2019. The papers will come out soon.

Jul. 3, 2019: Our work ''Geometry-Aware Video Object Detection for Static Cameras'' has been accepted at BMVC 2019 as an ORAL.

Jul. 3, 2019: Our "Cycle in Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation" is acepted at ACM MM 2019 as an ORAL.

Mar. 3, 2019: Our work on Semantic Guided Cross-View Traslation is accepted at CVPR 2019 as an oral. The project page and GitHub code are available now.

Aug. 1, 2018: The training and testing code for Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation is available.

Jun. 18, 2018: The code for Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification is available.

Jun. 1, 2018: One paper is accepted at ACM MM 2018 as an oral.

Mar. 11, 2018: One paper is accepted at TPAMI 2018 as a regular paper.

Feb. 02, 2018: Four papers including one oral and one spotlight are accepted at CVPR 2018.

Sep. 04, 2017: One paper is accepted at NIPS 2017 which will be held in Long Beach, USA.

Jul. 10, 2017: We published the code for continuous CRFs as sequential neural network associated with our CVPR 2017 spotlight paper on GitHub.

Mar. 10, 2017: The code for learned Top-K Global Pooling published at CVPR 2017 is available on GitHub.

Feb.27th, 2017: One spotlight and two posters are accepted at CVPR 2017.

Dec. 6th, 2016: Our paper received the Best Scientific Paper Award at ICPR 2016.

About Me

Greetings! My name is Dan Xu. I am currently an Assistant Professor in the Department of Computer Science and Engineering at HKUST. I was a Postdoctoral Research Fellow in the Visual Geometry Group (VGG) in the Department of Engineering Science at the University of Oxford, under the supervision of Prof. Andrea Vedaldi and Prof. Andrew Zisserman. I received my Ph.D. in Computer Science from the University of Trento in 2018, under the supervision of Prof. Nicu Sebe in Multimedia and Human Understanding Group (MHUG). I was a student research assistant in MMLab and the Department of Electronic Engineering at the Chinese University of Hong Kong under the supervision of Prof. Xiaogang Wang. My research foucuses on computer vision, multimedia and machine learning. Specifically, I am interested in deep learning, multi-modal and structured representation learning, statistical modelling within deep learning, as well as their applications in 2D/3D scene understanding, involving topics such as scene depth prediction, visual SLAM, object detection and scene parsing.

Selected Awards and Honors

Best Paper Award Nominee, at ACM Multimedia 2018

Best Scientific Paper Award, at IAPR International Conference on Pattern Recognition 2016

Orals/Spotlights (usually below 8% acceptance rate) 5 years consecutively presented at top venues including ICCV 2021, CVPR20, CVPR19, CVPR18, CVPR17

Top 30% highest-scoring reviewers at NIPS 2018.

Student Travel Grant, awarded by SIGMM and ACM Multimedia 2016

Teaching

COMP 4971A: Independent Work on Multi-View Deep Stereo, Summer 2021.

COMP 4971A: Independent Work on Self-Supervised Depth Estimation, Spring 2021.

COMP 5421: Computer Vision, Spring 2021.