no code implementations • 26 May 2023 • Sathyanarayanan N. Aakur, Sanjoy Kundu, Shubham Trehan
Learning to infer labels in an open world, i. e., in an environment where the target ``labels'' are unknown, is an important characteristic for achieving autonomy.
no code implementations • 8 Mar 2023 • Anik Mallik, Sanjoy Kundu, Md. Ashikur Rahman
Traffic Congestion is one of the severe problems in heavily populated countries like Bangladesh where Automated Traffic Control System needs to be implemented.
no code implementations • CVPR 2023 • Sanjoy Kundu, Sathyanarayanan N. Aakur
Current approaches take a generation-by-classification approach where the scene graph is generated through labeling of all possible edges between objects in a scene, which adds computational overhead to the approach.
no code implementations • 30 Nov 2022 • Sanjoy Kundu, Sathyanarayanan N. Aakur
Current approaches take a generation-by-classification approach where the scene graph is generated through labeling of all possible edges between objects in a scene, which adds computational overhead to the approach.
no code implementations • 16 Sep 2020 • Sathyanarayanan N. Aakur, Sanjoy Kundu, Nikhil Gunti
Building upon the compositional representation offered by Grenander's Pattern Theory formalism, we show that attention and commonsense knowledge can be used to enable the self-supervised discovery of novel actions in egocentric videos in an open-world setting, where data from the observed environment (the target domain) is open i. e., the vocabulary is partially known and training examples (both labeled and unlabeled) are not available.