Rohan M
Computer Science, Machine Learning, Computer Vision, Music, Philosophy, Applied Math
Reading for curiosity, not completion
Learning from recreational research
Recreating AlexNet from scratch in (old) Keras and understanding the math behind convolutions and pooling.
Are you disciplined if someone has to supervise you?
Right now, this is a home for my presentation on the motivation behind self supervised learning for pretraining computer vision models. The philosophy will follow soon...
Why we seem to lose interest in things over time?
We like new things. We like a new start. A fresh beginning gives us a chance to put everything else aside and lets us only focus on things ahead of us - the bright future. Being an amateur at anything...
Thoughts on surveillance and computer vision's part in it
I'm not a fan of surveillance. I've written papers on doing surveillance. Hypocritical? Perhaps yes. Does it make me blind to now see its negative impacts? No. A longer philo...
Published Papers/Longer Reads
-
Improving Visual Recognition using Ambient Sound for Supervision
-
Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision
-
Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity, Representation, Coverage and Importance
-
Vis-DSS: An Open-Source toolkit for Visual Data Selection and Summarization
-
Deployment of customized deep learning based video analytics on surveillance cameras