Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Deva Ramanan

Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details


Feb 01, 2021
Achal Dave, Piotr Dollár, Deva Ramanan, Alexander Kirillov, Ross Girshick


  Access Paper or Ask Questions

Learning to Segment Rigid Motions from Two Frames


Jan 11, 2021
Gengshan Yang, Deva Ramanan

* code will be released at https://github.com/gengshan-y/rigidmask 

  Access Paper or Ask Questions

Detecting Invisible People


Dec 15, 2020
Tarasha Khurana, Achal Dave, Deva Ramanan

* Project page: http://www.cs.cmu.edu/~tkhurana/invisible.htm 

  Access Paper or Ask Questions

Background Splitting: Finding Rare Classes in a Sea of Background


Aug 28, 2020
Ravi Teja Mullapudi, Fait Poms, William R. Mark, Deva Ramanan, Kayvon Fatahalian


  Access Paper or Ask Questions

What-If Motion Prediction for Autonomous Driving


Aug 24, 2020
Siddhesh Khandelwal, William Qi, Jagjeet Singh, Andrew Hartnett, Deva Ramanan

* 16 pages, 6 tables, 6 figures 

  Access Paper or Ask Questions

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild


Aug 19, 2020
Jason Y. Zhang, Sam Pepose, Hanbyul Joo, Deva Ramanan, Jitendra Malik, Angjoo Kanazawa

* In ECCV 2020. v2: Updated Related Work 

  Access Paper or Ask Questions

4D Visualization of Dynamic Events from Unconstrained Multi-View Videos


May 27, 2020
Aayush Bansal, Minh Vo, Yaser Sheikh, Deva Ramanan, Srinivasa Narasimhan

* Project Page - http://www.cs.cmu.edu/~aayushb/Open4D/ 

  Access Paper or Ask Questions

Towards Streaming Image Understanding


May 21, 2020
Mengtian Li, Yu-Xiong Wang, Deva Ramanan

* Project page is at https://www.cs.cmu.edu/~mengtial/proj/streaming/ 

  Access Paper or Ask Questions

TAO: A Large-Scale Benchmark for Tracking Any Object


May 20, 2020
Achal Dave, Tarasha Khurana, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan

* Project page: http://taodataset.org/ 

  Access Paper or Ask Questions

Learning Generative Models of Tissue Organization with Supervised GANs


Mar 31, 2020
Ligong Han, Robert F. Murphy, Deva Ramanan

* Accepted at WACV-18 

  Access Paper or Ask Questions

Learning to Move with Affordance Maps


Feb 14, 2020
William Qi, Ravi Teja Mullapudi, Saurabh Gupta, Deva Ramanan

* Published at ICLR 2020. For code, see https://github.com/wqi/A2L 

  Access Paper or Ask Questions

Unsupervised Any-to-Many Audiovisual Synthesis via Exemplar Autoencoders


Jan 13, 2020
Kangle Deng, Aayush Bansal, Deva Ramanan

* (1) Project summary is available at: https://www.youtube.com/watch?v=7BO0-Q3TLfI ; (2) Code is available at https://github.com/dunbar12138/Audiovisual-Synthesis ; and (3) A beta web-demo is available at: https://scs00197.sp.cs.cmu.edu/ 

  Access Paper or Ask Questions

Hierarchical Deep Stereo Matching on High-resolution Images


Dec 13, 2019
Gengshan Yang, Joshua Manela, Michael Happold, Deva Ramanan

* CVPR 2019 

  Access Paper or Ask Questions

Inferring Distributions Over Depth from a Single Image


Dec 12, 2019
Gengshan Yang, Peiyun Hu, Deva Ramanan

* IROS 2019 

  Access Paper or Ask Questions

What You See is What You Get: Exploiting Visibility for 3D Object Detection


Dec 10, 2019
Peiyun Hu, Jason Ziglar, David Held, Deva Ramanan


  Access Paper or Ask Questions

Learning to Optimally Segment Point Clouds


Dec 10, 2019
Peiyun Hu, David Held, Deva Ramanan


  Access Paper or Ask Questions

Are we asking the right questions in MovieQA?


Nov 08, 2019
Bhavan Jasani, Rohit Girdhar, Deva Ramanan

* Spotlight presentation at CLVL workshop, ICCV 2019. Project page: https://bhavanj.github.io/MovieQAWithoutMovies/ 

  Access Paper or Ask Questions

Argoverse: 3D Tracking and Forecasting with Rich Maps


Nov 06, 2019
Ming-Fang Chang, John Lambert, Patsorn Sangkloy, Jagjeet Singh, Slawomir Bak, Andrew Hartnett, De Wang, Peter Carr, Simon Lucey, Deva Ramanan, James Hays

* CVPR 2019 

  Access Paper or Ask Questions

Learning to Track Any Object


Oct 25, 2019
Achal Dave, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan

* To be presented at the Holistic Video Understanding workshop at ICCV 

  Access Paper or Ask Questions

CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning


Oct 10, 2019
Rohit Girdhar, Deva Ramanan

* Webpage: https://rohitgirdhar.github.io/CATER 

  Access Paper or Ask Questions

MetaPix: Few-Shot Video Retargeting


Oct 10, 2019
Jessica Lee, Deva Ramanan, Rohit Girdhar

* Short version accepted to NeurIPS'19 MetaLearn Workshop. Webpage: https://imjal.github.io/MetaPix/ 

  Access Paper or Ask Questions

Weakly-supervised Action Localization with Background Modeling


Aug 19, 2019
Phuc Xuan Nguyen, Deva Ramanan, Charless C. Fowlkes

* To appear at ICCV 2019 

  Access Paper or Ask Questions

Growing a Brain: Fine-Tuning by Increasing Model Capacity


Jul 18, 2019
Yu-Xiong Wang, Deva Ramanan, Martial Hebert

* CVPR 

  Access Paper or Ask Questions

Shapes and Context: In-the-Wild Image Synthesis & Manipulation


Jun 11, 2019
Aayush Bansal, Yaser Sheikh, Deva Ramanan

* CVPR 2019 
* Project Page: http://www.cs.cmu.edu/~aayushb/OpenShapes/ 

  Access Paper or Ask Questions

A systematic framework for natural perturbations from videos


Jun 05, 2019
Vaishaal Shankar, Achal Dave, Rebecca Roelofs, Deva Ramanan, Benjamin Recht, Ludwig Schmidt

* 16 pages, 5 tables, 6 figures. Paper Website: https://modestyachts.github.io/natural-perturbations-website/ 

  Access Paper or Ask Questions

Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints


May 12, 2019
Mengtian Li, Ersin Yumer, Deva Ramanan


  Access Paper or Ask Questions

Towards Segmenting Everything That Moves


Feb 11, 2019
Achal Dave, Pavel Tokmakov, Deva Ramanan


  Access Paper or Ask Questions

DistInit: Learning Video Representations without a Single Labeled Video


Jan 26, 2019
Rohit Girdhar, Du Tran, Lorenzo Torresani, Deva Ramanan


  Access Paper or Ask Questions