Project

Current Projects

Action Recognition

1. Y. Zhu and S. Newsam, “DenseNet for optical flow,” IEEE International Conference on Image Processing (ICIP), 2017. [pdf]
2. Y. Zhu, Z. Lan, S. Newsam, and A. Hauptmann, “Guided optical flow learning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR): Workshop on Workshop on Brave New Motion Representations (BNMR), 2017. [pdf]
3. Z. Lan, Yi. Zhu, A. Hauptmann, and S. Newsam, “Deep local video feature for action recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR): Workshop on Open Domain Action Recognition (ODAR), 2017. [pdf]
4. Y. Zhu and S. Newsam, “Efficient action detection in untrimmed videos via multi-task learning,” IEEE Winter Conference on Applications of Computer Vision (WACV), 2017. [pdf]

Ground-Level Image for Land Use Classification

1. Y. Zhu and S. Newsam, “Spatio-temporal sentiment hotspot detection using geotagged photos,” ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS), 2016. (Best fast forward presentation runner up.) [pdf]
2. Y. Zhu and S. Newsam, “Land use classification using convolutional neural networks applied to ground-level images,” ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS), 2015. (Winner best poster award.) [pdf]

Previous Projects

NSF Award on Integrating Image and Non-Image Geospatial Data

NSF Award on New Tools for Characterizing Protein Dynamics