​Dan Xu 

Postdoctoral Researcher 
Visual Geometry Group (VGG)
Department of Engineering Science
University of Oxford

​
Address:  Parks Road, Oxford, OX1 3PJ, United Kindom (MAP)
Homepage: http://www.robots.ox.ac.uk/~danxu
Personal:  [Curriculum Viate] and [Google Scholar] and [GitHub] and [LinkedIn]
Email: danxu at robots.ox.ac.uk or danxuhk at gmail.com

---

New Events

• 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. 
• 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 is awarded ​Best Scientific Paper at ICPR 2016. 
• ​Aug. 15th, 2016: Our paper is accepted at ACCV 2016.
• Aug. 11th, 2016: Our paper is accepted at ACM MM 2016 as an oral presentation.​
• Jul. 12, 2015: Attend International Computer Vision Summer School (ICVSS 2015) held in Sicily, Italy.
• Jul. 03, 2015: Our paper is accepted at BMVC 2015 as an oral presentation.
• Jun.28, 2015: My research homepage is online.

---

 

About Me

Greetings! My name is Dan Xu. I am currently a Postdoc 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 research assistant in the Department of Electronic Engineering at the Chinese University of Hong Kong under the supervision of Prof. Xiaogang Wang. My research is focusing on computer vision, multimedia and machine learning. Specifically, I am interested in deep learning and its applications in 2D and 3D scene understanding involving various topics such as scene depth prediction, visual SLAM, object contour detection, pedestrian detection and scene parsing. 

---

 

Selected Publications

Conference:

GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Hao Tang, Wei Wang, Dan Xu, Yan Yan, Nicu Sebe
ACM International Conference on Multimedia (ACM MM 2018), Seoul, Korea ​
(Oral Presentation, 4.85% acceptance rate, Best Paper Candidate!!!)

BibTex-PDF -Project

@inproceedings{hao2018Geaturegan,
	  title={GestureGAN for Hand Gesture-to-Gesture Translation in the Wild},
	  author={Tang, Hao and Wang, Wei and Xu, Dan and Yan, Yan and Sebe, Nicu},
	  booktitle={ACM MM},
	  year={2018}
	}

Unsupervised Adversarial Depth Estimation using Cycled Generative Networks
Andrea Pilzer*, Dan Xu*, Mihai Puscas*, Elisa Ricci, Nicu Sebe
International Conference on 3D Vision (3DV 2018), Verona, Italy. (*Equal Contribution)​

BibTex-PDF -GitHub Code

@inproceedings{xu2018unsupervised,
  title={Unsupervised Adversarial Depth Estimation using Cycled Generative Networks},
  author={Pilzer, Andrea and Xu, Dan and Puscas, Mihai and Ricci, Elisa and Sebe, Nicu},
  booktitle={3DV},
  year={2018}
}

PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
Dan Xu, Wanli Ouyang, Xiaogang Wang, Nicu Sebe
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA​

BibTex-PDF -Project

@inproceedings{xu2018PAD-Net,
  title={PAD-Net: Multi-Tasks Guided Prediciton-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing},
  author={Xu, Dan and Ouyang, Wanli and Wang, Xiaogang and Sebe, Nicu},
  booktitle={CVPR},
  year={2018}
}

Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
Dan Xu, Wei Wang, Hao Tang, Hong Liu, Nicu Sebe, Elisa Ricci
​IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA
(Spotlight Presentation)

BibTex-PDF -Training & Testing Code

@inproceedings{xu2018structured,
  title={Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation},
  author={Xu, Dan and Wang, Wei and Tang, Hao and Liu, Hong and Sebe, Nicu and Ricci, Elisa},
  booktitle={CVPR},
  year={2018}
}

Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification
Dapeng Chen, Dan Xu, Hongsheng Li, Nicu Sebe, Xiaogang Wang
​IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA
(Oral Presentation)

BibTex-PDF -Code

@inproceedings{xu2018group,
  title={Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification},
  author={Chen, Dapeng and Xu, Dan and Li, Hongsheng and Sebe, Nicu and Wang, Xiaogang},
  booktitle={CVPR},
  year={2018}
}

Every Smile is Unique: Landmark-Guided Diverse Smile Generation
​Wei Wang, Xavier Alameda-Pineda, Dan Xu, Pascal Fua, Elisa Ricci, Nicu Sebe
​IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA

BibTex-PDF

@inproceedings{wang2018Every,
  title={Every Smile is Unique: Landmark-Guided Diverse Smile Generation},
  author={Wei, Wang and Alameda-Pineda, Xavier and Xu, Dan and Fua, Pascal and Ricci, Elisa and Sebe, Nicu},
  booktitle={CVPR},
  year={2018}
}

Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
Dan Xu, Wanli Ouyang, Xavier Alameda-Pineda, Elisa Ricci, Xiaogang Wang, Nicu Sebe
The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, USA

BibTex-PDF -Project

@inproceedings{xu2017learning,
  title={Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction},
  author={Xu, Dan and Ouyang, Wanli and Alameda-Pineda, Xavier and Ricci, Elisa and Wang, Xiaogang and Sebe, Nicu},
  booktitle={NIPS},
  year={2017}
}

Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
Dan Xu, Elisa Ricci, Wanli Ouyang, Xiaogang Wang, Nicu Sebe
​IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Hawaii, USA
(Spotlight Presentation, 8% acceptance rate)

BibTex-PDF -CODE-Presentation

@inproceedings{xu2017multi,
  title={Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation},
  author={Xu, Dan and Ricci, Elisa and Ouyang, Wanli and Wang, Xiaogang and Sebe, Nicu},
  booktitle={CVPR},
  year={2017}
}

Learning Cross-Modal Deep Representations for Robust Pedestrian Detection
Dan Xu, Wanli Ouyang, Elisa Ricci, Xiaogang Wang, Nicu Sebe
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Hawaii, USA

BibTex-PDF

@inproceedings{xu2017learning,
  title={Learning Cross-Modal Deep Representations for Robust Pedestrian Detection},
  author={Xu, Dan and Ouyang, Wanli and Ricci, Elisa and Wang, Xiaogang and Sebe, Nicu},
  booktitle={CVPR},
  year={2017}
}

Viraliency: Pooling Local Virality 
Xavier Alameda-Pineda, Andrea Pilzer, Dan Xu, Elisa Ricci, Nicu Sebe
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Hawaii, USAi​

BibTex-PDF-CODE

@inproceedings{alameda2017viraliency,
  title={Viraliency: Pooling Local Virality},
  author={Alameda-Pineda, Xavier and Pilzer, Andrea and Xu, Dan and Ricci, Elisa and Sebe, Nicu},
  booktitle={CVPR},
  year={2017}
}

Search Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking 
Nannan Li, Dan Xu, Zhenqiang Ying, Zhihao Li, Ge Li
Asian Conference on Computer Vision (ACCV 2016), Taibei, Tanwan

BibTex-PDF

@inproceedings{li2016searching,
  title={Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking},
  author={Li, Nannan and Xu, Dan and Ying, Zhenqiang and Li, Zhihao and Li, Ge},
  boottitle={arXiv preprint arXiv:1608.06495},
  year={2016}
}

Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition
Dan Xu, Jingkuan Song, Xavier Alameda-Pineda, Elisa Ricci, Nicu Sebe
23rd International Conference on Pattern Recognition (ICPR 2016), Cancun, Mexico
(Oral, Best Scientific Paper Award)

BibTex-PDF -CODE

@inproceedings{xu2016multipaced,
  title={Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition},
  author={Xu, Dan and Song, Jingkuan and Alameda-Pineda Xavier and Ricci, Elisa and Sebe, Nicu},
  booktitle={the 23rd International Conference on Pattern Recognition (ICPR)},
  year={2016}
}

Academic Coupled Dictionary Learning for Sketch Based Image Retrieval
Dan Xu, Xavier Alameda-Pineda, Jingkuan Song, Elisa Ricci, Nicu Sebe
ACM International Conference on Multimedia (ACM MM 2016), Amsterdam, Netherland
​(Oral, long paper, 22% acceptance rate)

BibTex-PDF -Project

@inproceedings{xu2016academic,
  title={Academic Coupled Dictionary Learning for Sketch-based Image Retrieval},
  author={Xu, Dan and Alameda-Pineda, Xavier and Song, Jingkuan and Ricci, Elisa and Sebe, Nicu},
  booktitle={Proceedings of the 2016 ACM on Multimedia Conference},
  pages={1326--1335},
  year={2016},
  organization={ACM}
}

Learning Deep Representations of Appearance and Motion for Anomalous Event Detection
Dan Xu, Elisa Ricci, Yan Yan, Jingkuan Song, Nicu Sebe
British Machine Vision Conference (BMVC 2015), Swansea, UK
​(Oral, 7% acceptance rate) 

BibTex-PDF -ROC Data

@article{xu2015learning,
  title={Learning deep representations of appearance and motion for anomalous event detection},
  author={Xu, Dan and Ricci, Elisa and Yan, Yan and Song, Jingkuan and Sebe, Nicu},
  journal={British Machine Vision Conference (BMVC)},
  year={2015}
}

A Novel Hand Posture Recognition System Based on Sparse Representation Using Color and Depth Images
Dan Xu, Yen-Lun Chen, Xinyu Wu, Wei Feng, Huihuan Qian and Yangsheng Xu
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), Tokyo, Japan
​(Oral)

BibTex-PDF

@inproceedings{xu2013novel,
  title={A novel hand posture recognition system based on sparse representation using color and depth images},
  author={Xu, Dan and Chen, Yen-Lun and Wu, Xinyu and Feng, Wei and Qian, Huihuan and Xu, Yangsheng},
  booktitle={2013 IEEE/RSJ International Conference on Intelligent Robots and Systems},
  pages={3765--3770},
  year={2013},
  organization={IEEE}
}

Hierarchical Activity Discovery within Spatio-Temporal Context for Video Anomaly Detection
Dan Xu, Xinyu Wu, Dezhen Song, Nannan Li and Yen-Lun Chen
IEEE International Conference on Image Processing (ICIP 2013), Melbourne, Australia.

BibTex-PDF

@inproceedings{xu2013hierarchical,
  title={Hierarchical activity discovery within spatio-temporal context for video anomaly detection},
  author={Xu, Dan and Wu, Xinyu and Song, Dezhen and Li, Nannan and Chen, Yen-Lun},
  booktitle={2013 IEEE International Conference on Image Processing},
  pages={3597--3601},
  year={2013},
  organization={IEEE}
}

Journal:

• Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep Networks,

          Dan Xu, Elisa Ricci, Wanli Ouyang, Xiaogang Wang, Nicu Sebe,
          IEEE Transactions on Pattern Analysis and Machine Intelligence(T-PAMI) (in press),  2018. [PDF]

• Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval,

          Dan Xu, Xavier Alameda-Pineda, Jingkuan Song, Elisa Ricci, Nicu Sebe,
          IEEE Transactions on Image Processing (T-IP) (in press), 2018. [PDF]

• Supervised Local Descriptor Learning for Human Action Recognition, 

​          Xiantong Zhen, Feng Zheng, Ling Shao, Xianbin Cao, Dan Xu,
          IEEE Transactions on Multimedia (T-MM), 10.1109/TMM.2017.2700204. [PDF]

• Detecting Anomalous Events in Videos by Learning Deep Representations of Appearance and Motion,

​​          Dan Xu, Yan Yan, Elisa Ricci, and Nicu Sebe, 
          Computer Vision and Image Understanding (CVIU),10.1016/j.cviu.2016.10.010. [PDF]

---

Awards and Honors

• Best Paper Award Nominee, at ACM Multimedia 2018
• Best Scientific Paper Award, at International Conference on Pattern Recognition 2016
• Student Travel Grant, awarded by SIGMM and ACM Multimedia 2016

---

​Professional Activity

Journal/Conference reviewer

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)​
• International Journal of Computer Vision (IJCV)​
• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)​
• IEEE Transactions on Image Processing (TIP)​
• ​​IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)​
• Elsevier Journal of Computer Vision and Image Understanding (CVIU)
• IEEE Transactions on Multimedia (TMM)
• IEEE Transactions on Industrial Informatics (TII)
• IEEE Transactions on Multimedia Computing Communications and Applications (TOMM)
• World Wide Web Journal (WWW)​
• IEEE Access​
• PLoS One
• Elsevier Journal of Neurocomputing (Neurocomputing)
• Springer Journal of Multimedia Tools and Applications (MTA)
• Springer Journal of Machine Vision and Applications (MVA)​
• IEEE International Conference on Computer Vision 2019 (CVPR 2019)​
• International Joint Conference on Artificial Intelligence 2019 (IJCAI 2019)​
• Internatial Conference on Machine Learning 2019 (ICML 2019)​
• Conference on Neural Information Processing Systems 2018 (NIPS 2018)​
• ACM International Conference on Multimedia 2017 (ACM MM 2017)
• IEEE International Conference on Computer Vision (ICCV 2017)
• ACM International Conference on Multimedia Retrieval (ICMR 2017)
• IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016)
• IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013)

---

© 2015 by Dan Xu. All Rights Reserved. Last Modified: 08/07/2015