| CARVIEW |
Karttikeya Mangalam
PhD Student in Computer Vision at Berkeley AI Research (BAIR)
University of California, Berkeley
About Me
I’m a PhD student in Computer Science at the Department of Electrical Engineering & Computer Sciences (EECS) at University of California, Berkeley advised by Prof. Jitendra Malik.
Earlier, I held a visiting researcher position at Meta AI where I spent two wonderful years collaborating with Dr. Christoph Feichtenhofer and team. Before my PhD, I was a Master’s student at Stanford CS advised by Prof. Juan Carlos Niebles at the Stanford Vision Lab. Earlier yet, I graduated summa cum laude from the Indian Institute of Technology, Kanpur majoring in Electrical Engineering and with a minor in ML.
In my research journey, I’ve had the good fortune of working with amazing mentors in computer vision labs across the world such as, Prof. Yoshua Bengio & Prof. Alain Tapp (MILA, Research Intern), Prof. Pascal Fua & Dr. Mathieu Salzmann (EPFL, Semester Exchange Student), Prof. Yoichi Sato (University of Tokyo, Research Intern), Dr. Adrien Gaidon & Dr. Kuan-Hui Lee (Toyota Research Institute, Research Intern) Prof. Tanaya Guha (University of Warwick, Undergraduate Thesis) and Prof. K S Venkatesh (IITK, Research Intern).
In addition to my academic endeavours, I like traveling, board games, philosophy of science and am always interested in a chat on different viewpoints of rationality & ethics in the light of recent developments in AI and its impact on work, society and on the broader human condition.
You can find my CV here. Feel free to drop me a mail at lastname@cs.berkeley.edu.
I’m looking for strong Master’s and senior undergrads to collaborate. Berkeley undergraduates interested in fifth year master’s program are encouraged to reach out. I also actively engage in mentorship, so feel free to drop a line if you are starting out in the field and are confused about publication expectations, PhD Admissions, or any associated topics.
Interests
- Vision Transformers
- Human Motion Analysis
- Video Understanding
- Computer Vision
- Artificial Intelligence
Education
-
PhD in Computer Science (Computer Vision)
University of California, Berkeley [Ongoing]
-
Master's in Computer Science (AI track)
Stanford University, USA [Dropout]
-
Master's Semester Exchange, 2018
EPFL, Switzerland
-
Btech. in Electrical Engineering (ML Minor), 2018
IIT Kanpur, India
Publications
♠ indicates equal technical contribution
Reversible Vision Transformers
Christoph Feichtenhofer♠, Jitendra Malik
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
Jitendra Malik, Christoph Feichtenhofer♠
Improved Multiscale Vision Transformers for Classification and Detection
Jitendra Malik, Christoph Feichtenhofer♠
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting
Multiscale Vision Transformers
Jitendra Malik, Christoph Feichtenhofer♠
LOKI: Long Term and Key Intentions for Trajectory Prediction
Karttikeya Mangalam, Chiho Choi
Overcoming Mode Collapse with Adaptive Multi Adversarial Training
Object-Region Video Transformers
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
Jitendra Malik, Adrien Gaidon
Long-term Human Motion Prediction with Scene Context
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision
Future Person Localization in First-Person Videos
Do deep neural networks learn shallow learnable examples first?
Bitwise Operations of Cellular Automaton on Gray-scale Images
Contact
Please feel free to reach to me for any query