Chenyou Fan
Ph.D.


Contact
fanchenyou-at-gmail.com

I obtained my Ph.D. degree of Computer Science from School of Informatics and Computing, Indiana University.
My research topics include first-person videos, image captioning, video question answering, federated learning and time series analysis.


Google Scholar here


Publications

  • Chenyou Fan, Ping Liu. "Federated Generative Adversarial Learning." Chinese Conference on Pattern Recognition and Computer Vision (PRCV'20) [pdf]
  • Tianyi Lin, Chenyou Fan, Mengdi Wang, M.I.Jordan. "Improved Sample Complexity for Stochastic Compositional Variance Reduced Gradient." American Control Conference 2020 (ACC'20) [pdf]
  • Chenyou Fan, Heng Huang. "Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering." IEEE Conference on Computer Vision and Pattern Recognition 2019 (CVPR'19, 25.2% acceptance rate) [pdf] [code]
  • Chenyou Fan, Heng Huang. "Multi-Horizon Time Series Forecasting with Temporal Attention Learning." SIGKDD Conference on Knowledge Discovery and Data Mining 2019 (KDD'19, 20% acceptance rate)
  • Chenyou Fan, Zehua Zhang, David J. Crandall. "DeepDiary: Lifelogging Image Captioning and Summarization." 2018. Journal of Visual Communication and Image Representation (Impact Factor: 2.591). [link]
  • Mingze Xu, Chenyou Fan, Yuchen Wang, Michael S. Ryoo, David J. Crandall. "Joint Person Segmentation and Identification in Synchronized First-and Third-person Videos. European Conference on Computer Vision 2018 (ECCV'18). [project]
  • Mingze Xu, Chenyou Fan, John Paden, Geoffrey Fox, and David J. Crandall. "Multi-Task Spatiotemporal Neural Networks for Structured Surface Reconstruction." IEEE Winter Conference on Applications of Computer Vision 2018 (WACV’18). [pdf]
  • Chenyou Fan, Jangwon Lee, Mingze Xu, K.K. Singh, Y.J. Lee, David J. Crandall, Michael S. Ryoo, "Identifying first-person camera wearers in third-person videos", IEEE Conference on Computer Vision and Pattern Recognition 2017 (CVPR'17, 29.0% acceptance rate). [pdf] [data & project page]
  • AJ Piergiovanni, Chenyou Fan, and Michael S. Ryoo, "Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters", the 31st AAAI Conference on Artificial Intelligence (AAAI), February 2017. [pdf] [source_code]

Resources

  • Chenyou Fan. "Survey of Convolutional Neural Network" pdf

Workshops

  • Chenyou Fan. "EgoVQA - An Egocentric Video Question Answering Benchmark Dataset". International Workshop on Egocentric Perception, Interaction and Computing (EPIC@ICCV), Octorber 2019. [pdf] [code & data] [poster]
  • Chenyou Fan, Jangwon Lee and Michael S. Ryoo. "Forecasting Hand and Object Locations in Future Frames". European Conference Workshop on Anticipating Human Behavior (AHB@ECCV), August 2018. [pdf]
  • Chenyou Fan and David J. Crandall, "Deepdiary: Automatically Captioning Lifelogging Image Streams". European Conference Workshop on Egocentric Perception, Interaction, and Computing (EPIC@ECCV), October 2016. [pdf and source_code]

Datasets


Patent

  • 利用动态时间上下文学习进行多界限时间序列预测的系统和方法. [CN201910803743.5]
  • System and method for multi-horizon time series forecasting with dynamic temporal context learning. [US20200074274A1]

Projects of Personal Interest

  • Transformer models for NLP src
  • RL src

Teaching

  • B551: Elements of Artificial Intelligence
  • B555: Algorithm Design and Analysis

Updated 07/10/2020