Bio

Yingwei Pan is currently a researcher in Vision and Multimedia Lab at JD AI Research, Beijing, China. He received Ph.D. degree from the University of Science and Technology of China in 2018, advised by Prof. Houqiang Li.

He joined the multimedia search and mining group at Microsoft Research as a research intern during 2013-2017, advised by Dr. Ting Yao and Dr. Tao Mei. He also visited Video Retrieval Group (VIREO) at City University of Hong Kong as a research assistant in 2013, advised by Prof. Chong-Wah Ngo.

His research interests include vision and language, video analytics, large scale visual search, and click-through data analysis.



Highlights
  • Three papers are accepted by CVPR 2019 with one oral paper.

  • Rank 1 in both Openset Classification task and Detection task of Visual Domain Adaptation Challenge (VisDA-2018) at ECCV 2018.

  • Rank 1 in COCO Image Captioning Challenge.

  • One paper is accepted by AAAI 2019.

  • One papers is accepted by ECCV 2018.

  • Two papers are accepted by CVPR 2018.



Publications

  • Yingwei Pan, Ting Yao, Yehao Li, Yu Wang, Chong-Wah Ngo, Tao Mei, “Transferrable Prototypical Networks for Unsupervised Domain Adaptation,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral). [pdf][arxiv]
  • Qi Cai, Yingwei Pan, Chong-Wah Ngo, Xinmei Tian, Lingyu Duan, Ting Yao, “Exploring Object Relation in Mean Teacher for Cross-Domain Detection,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [pdf][arxiv]
  • Yehao Li, Ting Yao, Yingwei Pan, Hongyang Chao, Tao Mei, “Pointing Novel Objects in Image Captioning,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [pdf][arxiv]
  • Jingwen Chen, Yingwei Pan, Yehao Li, Ting Yao, Hongyang Chao, Tao Mei, “Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning,” AAAI Conference on Artificial Intelligence (AAAI), 2019 (Oral). [pdf]
  • Ting Yao, Yingwei Pan, Yehao Li, Tao Mei, “Exploring Visual Relationship for Image Captioning,” European Conference on Computer Vision (ECCV), 2018. [pdf]
  • Yehao Li, Ting Yao, Yingwei Pan, Hongyang Chao, Tao Mei, “Jointly Localizing and Describing Events for Dense Video Captioning,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (Spotlight). [pdf]
  • Qi Cai, Yingwei Pan, Ting Yao, Chenggang Yan, Tao Mei, “Memory Matching Networks for One-Shot Image Recognition,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [pdf]
  • Yingwei Pan*, Zhaofan Qiu*, Ting Yao, Houqiang Li, Tao Mei, “To Create What You Tell: Generating Videos from Captions,” ACM Multimedia (MM), 2017 (Oral, Brave New Idea). [pdf]
  • Ting Yao, Yingwei Pan, Yehao Li, Zhaofan Qiu, Tao Mei, “Boosting Image Captioning with Attributes,” IEEE International Conference on Computer Vision (ICCV), 2017. [pdf][arxiv]
  • Zhaofan Qiu*, Yingwei Pan*, Ting Yao, Tao Mei, “Deep Semantic Hashing with Generative Adversarial Networks,” ACM conference on Research and Development in Information Retrieval (SIGIR), 2017 (Oral). [pdf]
  • Yingwei Pan, Ting Yao, Houqiang Li, Tao Mei, “Video Captioning with Transferred Semantic Attributes,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [pdf]
  • Ting Yao, Yingwei Pan, Yehao Li, Tao Mei, “Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [pdf]
  • Yingwei Pan, Tao Mei, Ting Yao, Houqiang Li, Yong Rui, “Jointly Modeling Embedding and Translation to Bridge Video and Language,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral). [pdf]
  • Yingwei Pan*, Yehao Li*, Ting Yao, Tao Mei, Houqiang Li, Yong Rui, “Learning Deep Intrinsic Video Representation by Exploring Temporal Coherence and Graph Structure,” International Joint Conference on Artificial Intelligence (IJCAI), 2016. [pdf]

  • Yingwei Pan, Ting Yao, Houqiang Li, Chong-Wah Ngo, Tao Mei, “Semi-supervised Hashing with Semantic Confidence for Large Scale Visual Search,” ACM conference on Research and Development in Information Retrieval (SIGIR), 2015 (Oral). [pdf]
  • Ting Yao, Yingwei Pan, Chong-Wah Ngo, Houqiang Li, Tao Mei, “Semi-supervised Domain Adaptation with Subspace Learning for Visual Recognition,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [pdf]
  • Yingwei Pan*, Ting Yao*, Tao Mei, Houqiang Li, Chong-Wah Ngo, Yong Rui, “Click-through-based Cross-view Learning for Image Search,” ACM conference on Research and Development in Information Retrieval (SIGIR), 2014 (Oral). [pdf]


Workshops
  • Yao Ting, Yehao Li, Zhaofan Qiu, Fuchen Long, Yingwei Pan, Dong Li, Tao Mei, “MSR Asia MSM at ActivityNet Challenge 2017: Trimmed Action Recognition, Temporal Action Proposals and Dense-Captioning Events in Videos,” CVPR ActivityNet Challenge Workshop, 2017. [pdf]
  • Yingwei Pan, Zhaofan Qiu, Ting Yao, Houqiang Li, Tao Mei, “Seeing Bot,” ACM conference on Research and Development in Information Retrieval (SIGIR), 2017 (Demo). [pdf]
  • Yingwei Pan, Ting Yao, Xinmei Tian, Houqiang Li, Chong-Wah Ngo, “Click-through-based Subspace Learning for Image Search,” in ACM Multimedia (MM), 2014 (Multimedia Grand Challenge). [pdf]
  • Yingwei Pan, Ting Yao, Kuiyuan Yang, Houqiang Li, Chong-Wah Ngo, Jingdong Wang, Tao Mei, “Image Search by Graph-based Label Propagation with Image Representation from DNN,” in ACM Multimedia(MM), 2013 (Multimedia Grand Challenge). [pdf]


Awards

  • Microsoft Research Asia PhD Fellowship 2015
  • National Scholarship 2017, 2014
  • SIGIR Student Travel Award 2017, 2015, 2014
  • Huawei Scholarship (the second grade) 2015
  • Rank 1 in the Dense-Captioning Events in Videos of ActivityNet Challenge @ CVPR 2017
  • Rank 1 in the COCO Image Captioning Challenge
  • Rank 3 in MSR-Bing Image Retrieval Challenge @ ACM Multimedia 2014
  • Rank 5 in MSR-Bing Image Retrieval Challenge @ ACM Multimedia 2013