I recently moved to CMU after spending 8 wonderful years as a faculty at UC-Irvine
. A more formal bio is here
My research focuses on computer vision, often motivated by the task of understanding people from visual data. My work tends to make heavy use of machine learning techniques, often using the human visual system as inspiration. For example, temporal processing is a key component of human perception, but is still relatively unexploited in current visual recognition systems. Machine learning from big (visual) data allows systems to learn subtle statistical regularities of the visual world. But humans have the ability to learn from very few examples. Here's a recent talk
(from 2015) that discusses some thoughts on these issues.
Current students and postdoctoral fellows
- Postdoctoral fellow
Past students and postdoctoral fellows
- Postdoctoral fellow
- James Supancic Long-Term Tracking by Decision-Making, 2017, Blizzard
- Mohsen Hejrati Recognizing and Reconstructing Objects in 3D, 2015, Google
- Dennis Park Tracking People and Their Poses, 2014, Vicarious
- Xiangxin Zhu Sharing Information Across Object Templates, 2014, Google
- Yi Yang Articulated Human Pose Estimation with Mixtures of Parts, 2013, Baidu
- Chaitanya Desai Relational Models for Human-Object Interactions and their Affordances, 2012, Sarnoff-SRI
- Hamed Pirsiavash Scalable Action Recognition in Continuous Video Streams, 2012, UMBC
- Vivek Krishnan Tinkering under the Hood: Interactive Zero-Shot Learning with Net Surgery, 2016, Microsoft
- Carl Vondrick Crowdsourcing Video Annotation, 2011, MIT
- Goutham Patnaik A Joint Model for Tracking and Recognizing Human Actions in Video, 2009, Google
- Program Chair, CVPR 2018
- Editorial Board, IJCV
- Associate Editor, IEEE TPAMI
- NSF Award for "Probabilistic Hierarchical Models for Multi-Task Visual Recognition" (2016-2018).
- IARPA Award for "Sparse Heterogeneous Representations and
Domain Adaptive Matching for Unconstrained Face Recognition" (2014-2018).
- Google Research Award for "Multi-Task Visual Recognition with Bidirectional Reasoning" (2016).
- Facebook Research Award (2016).
For a complete list, please see my Google Scholar
For pre-prints, please see my ArXiv
For older work, please see here
- P. Hu, D. Ramanan. Finding Tiny Faces, CVPR 2017.
- C. Chen, D. Ramanan. 3D Human Pose Estimation = 2D Pose Estimation + Matching, CVPR 2017.
- S. Huang, D. Ramanan. Expecting the Unexpected: Training Detectors for Unusual Pedestrians With Adversarial Imposters, CVPR 2017.
- A. Dave, O. Russakovsky, D. Ramanan. Predictive-Corrective Networks for Action Detection, CVPR 2017.
- R. Girdhar, D. Ramanan, A. Gupta, J. Sivic, B. Russell. ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification, CVPR 2017.
- Y. Wang, D. Ramanan, M. Hebert. Growing a Brain: Fine-Tuning by Increasing Model Capacity, CVPR 2017.
- P. Hu, D. Ramanan. Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians, CVPR 2016.
- M. Hejrati, D. Ramanan. Categorizing Cubes: Revisiting Pose Normalization, WACV 2016. (Best Paper Award).
- L. Zhang, X. Wang, D. Kalashnikov, S. Mehrotra, D. Ramanan. Query-Driven Approach to Face Clustering and Tagging, IEEE Trans on Image Processing, 2016.