Xinpeng Chen (陈新鹏)

Email : jschenxinpeng [AT] gmail [DOT] com

Bio : CV

Work Experience

Nov. 2016 - Feb. 2017, Research Intern, NLP Group, Hitachi Central Research Laboratory, Tokyo
Mentor: Dr. Bin Tong
Topic: Video captioning; Image paragraph description; Reinforcement learning for image captioning.

Mar. 2017 - Nov. 2018, Research Intern, CV Group, Tencent AI Lab, Shenzhen
Mentors: Dr. Lin Ma, Dr. Wenhao Jiang, and Dr. Wei Liu
Topic: Image and video captioning; Large video classification; Referring expression comprehension.

Dec. 2018 - Present, Senior Algorithm Engineer, CityBrain, DAMO Academy, Alibaba Group, Hangzhou
Topic: Optical Character Recognition in CCTV cameras (CityOCR); Attribute Prediction.

Publications (Google Scholar)

Real-Time Referring Expression Comprehension by Single-Stage Grounding Network
Xinpeng Chen, Lin Ma, Jingyuan Chen, Zequn Jie, Wei Liu, Jiebo Luo
arXiv preprint arXiv:1812.03426
[PDF]
Localizing Natural Language in Videos
Jingyuan Chen, Lin Ma, Xinpeng Chen, Zequn Jie, Jiebo Luo
The AAAI Conference on Artificial Intelligence (AAAI), Hawaii, USA, 2019.
[PDF]
Temporally Grounding Natural Sentence in Video
Jingyuan Chen, Xinpeng Chen, Lin Ma, Zequn Jie, Tat-Seng Chua
Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium, 2018.
[PDF]
Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
Xinpeng Chen, Lin Ma, Wenhao Jiang, Jian Yao, Wei Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018.
[PDF] [Supplementary Material] [Code] [Poster] [Video]
Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-World Dataset
Xinpeng Chen, Jingyuan Chen, Lin Ma, Jian Yao, Wei Liu, Jiebo Luo, Tong Zhang
International World Wide Web Conference (WWW), The Big Web Track, Lyon, France, 2018.
[PDF]

Important notice:
We are sorry that we are unable to release the FVAD dataset for some commercial considerations.
Learning to Guide Decoding for Image Captioning
Wenhao Jiang, Lin Ma, Xinpeng Chen, Fumin Shen, Hanwang Zhang, Wei Liu
The AAAI Conference on Artificial Intelligence (AAAI), Louisiana, USA, 2018.
[PDF]
Aggregating Frame-level Features for Large-Scale Video Classification
Shaoxiang Chen, Xi Wang, Yongyi Tang, Xinpeng Chen, Zuxuan Wu, Yugang Jiang
YouTube-8M Large-Scale Video Understanding Challenge (CVPR Workshop), Hawaii, USA, 2017.
[PDF]

Professional Activities

  • Reviewer for IEEE Trans. Multimedia (TMM), 2019.
  • Reviewer for AAAI, 2018.
  • Reviewer for Pattern Recognition (PR), 2017.

Miscellaneous

  • Master thesis (Chinese): Research on Image Semantic Caption Generation Based on Encoder-Decoder Framework. [PDF]
  • Tensorflow implementation of the paper: A Hierarchical Approach for Generating Descriptive Image Paragraphs. [Code]
  • Tensorflow implementation of the paper: Sequence to Sequence - Video to Text. [Code]
  • Tensorflow implementation of the paper: Optimization of Image Description Metrics Using Policy Gradient Methods. [Code]
  • Personal project: Detecting the text in natural images by SSD (Single Shot Detection). [Code]

Last Updated on 20-th Dec., 2018

Published with GitHub Pages