About ME

Zhaofan Qiu (邱钊凡)

Google Scholar
zhaofanqiu@gmail.com

I am currently a Ph.D student in School of Information Science and Technology in the University of Science and Technology of China, advised by Dr. Tao Mei.

I joined the multimedia search and mining group at Microsoft Research as a research intern during 2014-2018, advised by Dr. Tao Mei and Dr. Ting Yao. I also visited Video Retrieval Group (VIREO) at City University of Hong Kong as a research assistant in 2015, advised by Prof. Chong-Wah Ngo.

News

  • 2019.6. Our team (JD-AI) wins the 1st place in Trimmed Action Recognition (Kinetics-700) task of ActivityNet Challenge @ CVPR 2019. Report and Slides are available.

  • 2019.6. "Learning spatio-temporal representation with local and global diffusion" is accepted by CVPR 2019.

  • 2019.6. "Gaussian Temporal Awareness Networks for Action Localization" is accepted by CVPR 2019.

  • 2019.6. "Customizable Architecture Search for Semantic Segmentation" is accepted by CVPR 2019.

  • 2018.9. Our team (VARMS) wins the 1st place in Openset Classification task and Detection task of Visual Domain Adaptation Challenge @ ECCV 2018.

  • 2017.10. The code&model for Pseudo-3D Residual Networks (ICCV'17) have been released on github!

  • 2017.10. Our team (MSRA-MSM) wins the 1st place in Segmentation task of Visual Domain Adaptation Challenge @ ICCV 2017.

  • 2017.7. Our team (MSRA-MSM) wins the 1st place in Dense-Captioning task and 2rd place in Temporal Action Proposal task of ActivityNet Challenge @ CVPR 2017.

Publications

Learning Spatio-Temporal Representation with Local and Global Diffusion

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Xinmei Tian, and Tao Mei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Customizable Architecture Search for Semantic Segmentation

Yiheng Zhang, Zhaofan Qiu, Jingen Liu, Ting Yao, Dong Liu, Tao Mei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Gaussian Temporal Awareness Networks for Action Localization

Fuchen Long, Ting Yao, Zhaofan Qiu, Xinmei Tian, Jiebo Luo, Tao Mei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (oral)

Recurrent Tubelet Proposal and Recognition Networks for Action Detection

Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao, Tao Mei
European Conference on Computer Vision (ECCV), 2018

Fully Convolutional Adaptation Networks for Semantic Segmentation

Yiheng Zhang, Zhaofan Qiu, Ting Yao, Dong Liu, Tao Mei
IEEE International Conference on Computer Vision (CVPR), 2018

Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks

Zhaofan Qiu, Ting Yao, Tao Mei
IEEE International Conference on Computer Vision (ICCV), 2017

Boosting Image Captioning with Attributes

Ting Yao, Yingwei Pan, Yehao Li, Zhaofan Qiu, Tao Mei
IEEE International Conference on Computer Vision (ICCV), 2017

Deep Semantic Hashing with Generative Adversarial Networks

Zhaofan Qiu, Yingwei Pan, Ting Yao, Tao Mei
ACM conference on Research and Development in Information Retrieval (SIGIR), 2017 (oral)

Deep Quantization: Encoding Convolutional Activations with Deep Generative Model

Zhaofan Qiu, Ting Yao, Tao Mei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

To Create What You Tell: Generating Videos from Captions

Yingwei Pan*, Zhaofan Qiu*, Ting Yao, Houqiang Li, Tao Mei (*equal contribution)
ACM Multimedia (MM), 2017 (brave new idea, oral)

Learning Deep Spatio-Temporal Dependency for Semantic Video Segmentation

Zhaofan Qiu, Ting Yao, Tao Mei
IEEE Transactions on Multimedia (TMM), 2018

Learning Hierarchical Video Representation for Action Recognition

Qing Li*, Zhaofan Qiu*, Ting Yao, Tao Mei, Yong Rui, Jiebo Luo (*equal contribution)
International Journal of Multimedia Information Retrieval (IJMIR), 2017

Action Recognition by Learning Deep Multi-Granular Spatio-Temporal Video Representation

Qing Li*, Zhaofan Qiu*, Ting Yao, Tao Mei, Yong Rui, Jiebo Luo (*equal contribution)
ACM International Conference on Multimedia Retrieval (ICMR), 2016 (best paper candidate)

Workshops

Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019

Zhaofan Qiu, Dong Li, Yehao Li, Qi Cai, Yingwei Pan, Ting Yao
In CVPR ActivityNet Challenge Workshop, 2019 (1nd place in Trimmed Action Recognition (Kinetics-700) task)

Seeing Bot

Yingwei Pan, Zhaofan Qiu, Ting Yao, Houqiang Li, Tao Mei
ACM conference on Research and Development in Information Retrieval (SIGIR), 2017 (demo)

MSR Asia MSM at ActivityNet Challenge 2017

Ting Yao, Yehao Li, Zhaofan Qiu, Fuchen Long, Yingwei Pan, Dong Li, Tao Mei
In CVPR ActivityNet Challenge Workshop, 2017 (1nd place in Dense-Captioning task and 2rd place in Temporal Action Proposal task)

MSR Asia MSM at ActivityNet Challenge 2016

Zhaofan Qiu, Dong Li, Chuang Gan, Ting Yao, Tao Mei, Yong Rui
In CVPR ActivityNet Challenge Workshop, 2016 (3nd place in Untrimmed Video Classification task)

MSR Asia MSM at THUMOS Challenge 2015

Zhaofan Qiu, Qing Li, Ting Yao, Tao Mei, Yong Rui
In CVPR THUMOS Challenge Workshop, 2015 (2nd place in Action Classification task)

VIREO-TNO @ TRECVID 2015: Multimedia Event Detection

Hao Zhang, Yi-Jie Lu, Maaike de Boer, Frank ter Haar, Zhaofan Qiu, Klamer Schutte, Wessel Kraaij, Chong-Wah Ngo
NIST TRECVID Workshop (TRECVID'15), 2015

Awards

  • Microsoft Research Asia Fellowship, 2017

  • National Scholarship, 2017

  • SIGIR Student Travel Grant, 2017

  • Excellent Graduate in Anhui Province, 2015

  • Outstanding Undergraduate Thesis, 2015

  • Outstanding Student Cadres, 2014

  • National Scholarship, 2013

  • Outstanding Student Scholarship (Gold Award), 2012