A 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 talk
(from 2015) that discusses some thoughts on these issues.
I am currently a principle scientist at Argo AI and the director of the CMU Argo AI Center for Autonomous Vehicle Research
. We have several post-doctoral and research staff positions. Please contact me if you are interested.
Current students and postdoctoral fellows
- Postdoctoral fellow
- Masters / undergraduate
- Sean Cha (joint with Aswin Sankaranarayanan)
- Aaron Huang (joint with John Dolan)
- Jessica Lee
- Krishna Uppala (joint with Aswin Sankaranarayanan)
- Haochen Wang
Past students and postdoctoral fellows
- Postdoctoral fellow
- Peiyun Hu Robust and Scalable Perception for Autonomy, 2021,
- Ravi Mallupdai Dynamic Model Specialization for Efficient Inference, Training, and Supervision, 2021,
- Achal Dave Open-World Object Detection and Tracking, 2021,
- Aayush Bansal Unsupervised Learning of the 4D Audio-Visual World,2020, Facebook Reality Labs
- Rohit Girdhar Learning to Understand People via Local, Global, and Temporal Reasoning, 2019, Facebook AI
- Phuc Nguyen Visual Recognition with Limited Annotations, 2018, Google
- James Supancic Long-Term Tracking by Decision-Making, 2017, Blizzard
- Mohsen Hejrati Recognizing and Reconstructing Objects in 3D, 2015, Genentech
- Dennis Park Tracking People and Their Poses, 2014, Toyota Research Institute
- Xiangxin Zhu Sharing Information Across Object Templates, 2014, Google
- Yi Yang Articulated Human Pose Estimation with Mixtures of Parts, 2013, DeepMind
- Chaitanya Desai Relational Models for Human-Object Interactions and their Affordances, 2012, Amazon
- Hamed Pirsiavash Scalable Action Recognition in Continuous Video Streams, 2012, UMBC
- William Qi Representation Learning for Safe Autonomous Movement , 2020, Argo AI
- Siva Mynepalli Recognizing Tiny Faces, 2019, Nimble Robotics
- Ishan Nigam Learning with Auxillary Supervision, 2019, UT Austin
- Vivek Krishnan Tinkering under the Hood: Interactive Zero-Shot Learning with Net Surgery, 2016, Microsoft
- Carl Vondrick Crowdsourcing Video Annotation, 2011, Columbia
- Goutham Patnaik A Joint Model for Tracking and Recognizing Human Actions in Video, 2009, Google
- 16-720 Spring 2021, Graduate Computer Vision (Canvas)
- 16-720 Spring 2020, Graduate Computer Vision (Canvas)
- 16-720 Spring 2017, Graduate Computer Vision
- 16-899 Fall 2016, Seminar on Human Activity Analysis
- 16-720 Spring 2016, Graduate Computer Vision
- Program Chair, CVPR 2018
- Editorial Board, IJCV
- Associate Editor, IEEE TPAMI
- IARPA Award for "Deep Intermodal Video Analytics" (2018-2021).
- DARPA Award for "Agile Dimorphic Execution for Dispersed Computing" (2017-2019).
- Intel Science and Tech. Center for Visual Cloud Systems (2016-2019).
- 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).
- NIST Award for "Center for Statistics and Applications in Forensic Evidence" (2015-2019)
- NSF Award for "The Intelligent Workcell - Enabling Robots and People to Work Together Safely in Manufacturing Environments" (2012-2017).
For a complete list, please see my Google Scholar
For pre-prints, please see my ArXiv
For older work, please see here
- C. Thavamani, M, Li, N. Cebron, D. Ramanan. FOVEA: Foveated Image Magnification for Autonomous Navigation, ICCV 2021.
- T. Khurana, A. Dave, D. Ramanan. Detecting Invisible People, ICCV 2021.
- S. Kong, D. Ramanan. OpenGAN: Open-Set Recognition via Open Data Generation, ICCV 2021.
- R. Mullapudi, F. Poms, W. Mark, D. Ramanan, K,. Fatahalian. Learning Rare Category Classifiers on a Tight Labeling Budget, ICCV 2021.
- F. Poms, V. Sarukkai, R. Mullapudi, N. Sohoni, W. Mark, D. Ramanan, K. Fatahalian. Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories, ICCV 2021.
- G. Yang, D. Ramanan. Learning to Segment Rigid Motions from Two Frames, CVPR 2021.
- P. Hu, A. Huang, J. Dolan, D. Held, D. Ramanan. Safe Local Motion Planning with Self-Supervised Freespace Forecasting. CVPR 2021.
- G. Yang, D. Sun, V. Jampani, D. Vlasic, F. Cole, H. Chang, D. Ramanan, W. Freeman, C. Liu. LASR: Learning Articulated Shape Reconstruction from a Monocular Video. CVPR 2021.
- R. Mullapudi, F. Poms, W. Mark, D. Ramanan, K. Fatahalian. Background Splitting: Finding Rare Classes in a Sea of Background. CVPR 2021.
- K. Deng, A. Bansal, D. Ramanan. Unsupervised Audiovisual Synthesis via Exemplar Autoencoders, ICLR 2021.
- M. Li, Y. Wang, D. Ramanan. Towards Streaming Perception, ECCV 2020. (Best Paper, Honorable Mention).
- A. Dave, T. Khurana, P. Tokmakov, C. Schmid, D. Ramanan. TAO: A Large-scale Benchmark for Tracking Any Object, ECCV 2020.
- J. Zhang, S. Pepose, H. Joo, D. Ramanan, J. Malik, A. Kanazawa. Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild, ECCV 2020.
- G. Yang, D. Ramanan. Upgrading Optical Flow to 3D Scene Flow through Optical Expansion, CVPR 2020.
- P. Hu, D. Held, D. Ramanan. What You See Is What You Get: Exploiting Visibility for 3D Object Detection, CVPR 2020.
- A. Bansal, M. Vo, Y. Sheikh, D. Ramanan, S. Narasimhan. 4D Visualization of Dynamic Events from Unconstrained Multi-View Videos. CVPR 2020.
- P. Hu, D. Held*, D. Ramanan*. Learning to Optimally Segment Point Clouds, IEEE Robotics and Automation Letters (RA-L), 2020.
- R. Girdhar, D. Ramanan. CATER: A Diagnostic Dataset for Compositional Actions & TEmporal Reasoning, ICLR 2020.
- W. Qi, R. Mullapudi, S. Gupta, D. Ramanan. Learning to Move with Affordance Maps, ICLR 2020.
- M. Li, E. Yumer, D. Ramanan. Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints, ICLR 2020.
- J. Lee, D. Ramanan, R. Girdhar. MetaPix: Few-Shot Video Retargeting, ICLR 2020.
- G. Yang, D. Ramanan. Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.
- R. Mullapudi, S. Chen, K. Zhang, D. Ramanan, K. Fatahalian. Online Model Distillation for Efficient Video Inference, ICCV 2019.
- Y. Wang, D. Ramanan, M. Hebert. Meta-Learning to Detect Rare Objects, ICCV 2019.
- R. Gridhar, D. Tran, L. Torresani, D. Ramanan. DistInit: Learning Video Representations without a Single Labeled Video, ICCV 2019.
- I. Nigam, P. Tokmakov, D. Ramanan. Towards Latent Attribute Discovery from Triplet Similarities, ICCV 2019.
- P. Nguyen, D. Ramanan, C. Fowlkes. Weakly-supervised Action Localization with Background Modeling, ICCV 2019.
- G. Yang, P. Hu, D. Ramanan. Inferring Distributions Over Depth From a Single Image, IROS 2019.
- A. Bansal, Y. Sheikh. D. Ramanan. Shapes and Context: In-the-Wild Image Synthesis & Manipulation, CVPR 2019. (Best Paper Award Finalist).
- G. Yang, J. Manela, M. Happold, D. Ramanan. Hierarchical Deep Stereo Matching on High Resolution Images, CVPR 2019.
- M. Chang, J. Lambert, P. Sangkloy, S. Singh, S. Bak, A. Hartnett, D. Wang, P. Carr, S. Lucey, D. Ramanan, J. Hayes. Argoverse: 3D Tracking and Forecasting with Rich Maps, CVPR 2019.
- P. Hu, Z. Lipton, A. Anandkumar, D. Ramanan. Active Learning with Partial Feedback, ICLR 2019.
- M. Li, Z. Lin, R. Mech, E. Yumer, D. Ramanan. Photo-Sketching: Inferring Contour Drawings from Images , WACV 2019.
- A. Bansal, S. Ma, D. Ramanan, Y. Sheikh. Recycle-GAN: Unsupervised Video Retargeting, ECCV 2018.
- L. Gui, Y. Wang, D. Ramanan, J. Moura. Few-Shot Human Motion Prediction via Meta-Learning, ECCV 2018.
- P. Nguyen, D. Ramanan, C. Fowlkes. Active Testing, ICML 2018.
- A. Bansal, Y. Sheikh, D. Ramanan. PixelNN: Example-based Image Synthesis, ICLR 2018.
- M. Li, L. Jeni, D. Ramanan. Brute-Force Facial Landmark Analysis With A 140,000-Way Classifier, AAAI 2018.
- Hang, R. Murphy, D. Ramanan. Learning Generative Models of Tissue Organization wih Supervised GANs, WACV 2018.
- J. Wang, O. Russakovsky, D. Ramanan. The More You Look, the More You See: Towards General Object Understanding Through Recursive Refinement WACV 2018.
- I. Nigam, C. Huang, D. Ramanan. Ensemble Knowledge Transfer for Semantic Segmentation, WACV 2018.