Kaustav Kundu |
|
---|---|
Location Seattle, WA, USA |
Email kaustavk-at-amazon-dot-com |
Background
- I am a Research Scientist at Amazon Web Services.
- I did my PhD in the Department of Computer Science at University of Toronto. I was advised by Professor Raquel Urtasun and Professor Sanja Fidler.
- I completed my MS in Toyota Technological Insitute at Chicago (Sept '12 - Dec '13).
- I completed my undergraduate studies, B.Tech (Hons.) (July '08 - May '12), at IIIT Hyderabad, India, majoring in Computer Science and Engineering. I did my Honours project at Centre for Visual Information Technology (CVIT) lab, under the guidance of Professor P.J. Narayanan.
Research
My research interests lie broadly in the field of Computer Vision and Machine Learning. In the last few years, I have been excited about the problem of visual scene understanding. During my PhD, I had explored ideas on how to combine geometric priors and semantic information for 3D scene understanding. At Amazon Go, I have been working towards the goal of building efficient temporal representations across multiple cameras for real-time action detection.
Publications
-
Positive-congruent training: Towards regression-free model updates
Sijie Yan, Yuanjun Xiong, Kaustav Kundu, Shuo Yang, Siqi Deng, Meng Wang, Wei Xia, Stefano Soatto
IEEE Conference in Computer Vision and Pattern Recognition (CVPR), 2021
[Oral Presentation] [Blog Post]
-
Exploiting weakly supervised visual patterns to learn from partial annotations
Kaustav Kundu, Erhan Bas, Michael Lam, Hao Chen, Davide Modolo, Joseph Tighe
Neural Information Processing Systems (NeurIPS), 2020
-
Pose Estimation for Objects with Rotational Symmetry
Enric Corona, Kaustav Kundu, Sanja Fidler
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
-
SurfConv: Bridging 3D and 2D Convolution for RGBD Images
Hang Chu, Wei-Chiu Ma, Kaustav Kundu, Raquel Urtasun, Sanja Fidler
IEEE Conference in Computer Vision and Pattern Recognition (CVPR), 2018
-
3D Object Proposals using Stereo Imagery for Accurate Object Class Detection
Xiaozhi Chen*, Kaustav Kundu*, Yukun Zhu, Humin Ma, Sanja Fidler, Raquel Urtasun
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017
-
Annotating Object Instances with a Polygon-RNN
Lluís Castrejón, Kaustav Kundu, Raquel Urtasun, Sanja Fidler
IEEE Conference in Computer Vision and Pattern Recognition (CVPR), 2017
[Oral Presentation - Best Paper Honorable Mention Award]
-
Exploiting Semantic Information and Deep Matching for Optical Flow
Min Bai*, Wenjie Luo*, Kaustav Kundu, Raquel Urtasun
European Conference on Computer Vision (ECCV), 2016
-
Monocular 3D Object Detection for Autonomous Driving
Xiaozhi Chen, Kaustav Kundu, Ziyu Zhang, Humin Ma, Sanja Fidler, Raquel Urtasun
IEEE Conference in Computer Vision and Pattern Recognition (CVPR), 2016
-
3D Object Proposals for Accurate Object Class Detection
Xiaozhi Chen*, Kaustav Kundu*, Yukun Zhu, Andrew Berneshawi, Humin Ma, Sanja Fidler, Raquel Urtasun
Neural Information Processing Systems (NIPS), 2015
-
Rent3D: Floor-Plan Priors for Monocular Layout Estimation
Chenxi Liu*, Alexander Schwing*, Kaustav Kundu, Raquel Urtasun, Sanja Fidler
IEEE Conference in Computer Vision and Pattern Recognition (CVPR), 2015
[Oral Presentation] [Featured in Two Minute Papers]
-
Geometry Directed Browser For Personal Photographs
Aditya Deshpande, Siddharth Choudhary, P J Narayanan, Krishna Kumar Singh, Kaustav Kundu, Aditya Singh, Apurva Kumar
Indian Conference on Vision, Graphics and Image Processing (ICVGIP), 2012
[Oral Presentation]
Graduate Courses
- Computer Vision: Intro to Computer Vision, Visual Recognition with Text
- Machine Learning: Intro to Statistical Machine Learning, Probabilistic Graphical Models
- Optimization: Linear Programming, Convex Optimization
- Others: Mathematical Foundation, Mathematical Toolkit, Algorithms, Computational Linguistics
Work Experience & Services
- Full-time
- Amazon Web Services. (October 2019 - present)
- Amazon Go. (March 2018 - October 2019)
- Research Internships
- Apple Inc. (June - September 2016)
- Apple Inc. (May - August 2015)
- Teaching Assistant
- Inference Algorithms and Machine Learning (Spring '17)
- Intro to ML (Fall '16)
- Probabilistic Graphical Models (Spring '16)
- Neural Networks (Spring '15)
- Intro to Image Understanding (Fall '14, Fall '15)
- Mathematical Expression and Reasoning for Computer Science (Summer '14)
- Intro to Visual Computing (Spring '14)
Awards/Honors
- Won Best Paper Honorable Mention award for our Polygon-RNN paper at CVPR '17'.
- Mentioned among the Outstanding Reviewers at CVPR '18 and CVPR '21