AJ Piergiovanni

I am a PhD student in Computer Science at Indiana University advised by Dr. Michael Ryoo. I work on computer vision, machine learning and robotics. I'm interested in the activity detection tasks, and especially enjoy applications to sports videos.

I am currently an intern at Google Brain.

In 2015, I received a BS in Computer Science and Mathematics from Rose-Hulman Institute of Technology. In my free time, I climb mountains.

ajpiergi@indiana.edu | GitHub | Google Scholar

Publications

  • AJ Piergiovanni, A. Angelova, A. Toshev, and M. S. Ryoo, "Evolving Space-Time Neural Architectures for Videos", International Conference on Computer Vision (ICCV), October 2019. [arXiv][github code] [project page]
  • AJ Piergiovanni, A. Wu, and M. S. Ryoo, "Learning Real-World Robot Policies by Dreaming", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 2019. [arXiv][project_page]
  • AJ Piergiovanni and M. S. Ryoo, "Early Detection of Injuries in MLB Pitchers from Video", CVPR Workshop on Computer Vision in Sports (CVsports), June 2019. [arXiv]
  • Alan Wu, AJ Piergiovanni, and M. S. Ryoo, "Model-Based Robot Imitation with Future Image Similarity", International Journal of Computer Vision (IJCV), October 2019. [paper][github dataset/code]
  • Alan Wu, AJ Piergiovanni, and M. S. Ryoo, "Model-based Behavioral Cloning with Future Image Similarity Learning", Conference on Robot Learning (CoRL), October 2019. [arXiv][github dataset/code]
  • AJ Piergiovanni and M. S. Ryoo, "Temporal Gaussian Mixture Layer for Videos", International Conference on Machine Learning (ICML), June 2019. [arXiv] [github code]
  • AJ Piergiovanni, and M. S. Ryoo, "Representation Flow for Action Recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. [arXiv] [github code] [project page]
  • AJ Piergiovanni, A. Angelova and M. S. Ryoo, "Evolving Losses for Unlabeled Video Representation Learning", CVPR Workshop on Learning from Unlabeled Videos, June 2019. [arXiv]
  • M. S. Ryoo, AJ Piergiovanni, M. Tan, A. Angelova, "AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures", arXiv:1905.13209, May 2019. [arXiv]
  • AJ Piergiovanni, A. Angelova and M. S. Ryoo, "Learning Differentiable Grammars for Continuous Data", arXiv:1902.00505, February 2019. [arXiv]
  • AJ Piergiovanni and M. S. Ryoo, "Learning Multimodal Representations for Unseen Activities", IEEE Winter Conference on Applications of Computer Vision (WACV) arXiv:1806.08251, March 2020. [arXiv]
  • AJ Piergiovanni and M. S. Ryoo, "Fine-grained Activity Recognition in Baseball Videos", CVPR Workshop on Computer Vision in Sports (CVsports), June 2018. [arXiv] [github code]
  • AJ Piergiovanni and M. S. Ryoo, "Learning Latent Super-Events to Detect Multiple Activities in Videos", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018. [arXiv] [github code]
  • AJ Piergiovanni*, C. Fan*, and M. S. Ryoo, "Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters", the 31st AAAI Conference on Artificial Intelligence (AAAI), February 2017. [arXiv] [github code]

Datasets

MLB-YouTube: A dataset for activity recogntion in continuous and segmented baseball videos. Also included is dense text annotations from the commentators to allow for video captions and learning video and language relationships.