I am currently working as a scientist in the CSIR National Institute of Data Science and AI (formerly CSIR Fourth Paradigm Institute), where I primarily work on Multi-modal Large Language Models. I obtained my PhD degree in Computer Science from the Indian Statistical Institute. During the last few years, I mainly worked on data efficient deep learning approaches. Specifically I explored the different aspects of the problem Compositional Zero-Shot Learning (CZSL). Compositional Zero-Shot Learning focusses on recognizing new state-object compositions from limited training data. We worked on approaches using graph convolutional networks and transformer networks to tackle challenges in the closed-world, open-world, and partially supervised CZSL problems. Before my PhD, I completed my M. Tech degree in Computer Science from ISI, Kolkata. Prior to that I pursued my undergraduate studies in Electronics and Tele-Communication Engineering from Jadavpur University, Kolkata.
IEEE Transactions on Image Processings, 2026
In this work, we attempt to address the partially supervised Compositional Zero-Shot Learning (pCZSL) problem that requires to recognize unseen state–object combinations when each training image has either the state or the object label for an input image.
ACM Transactions on Multimedia Computing, Communications and Applications, 2024
In this work, we proposed a Knowledge-Guided Transformer Network to model the partial associations between visual features of state and object, to better tackle the intra-class variability in unseen state-objcet compositional images.
Pattern Recognition, 2024
In this work, we proposed Graph Convolutional Network based approach in attempt to solve the open-world CZSL problem.
IEEE Transactions on Emerging Topics in Computational Intelligence, 2023
In this work, we attempt to better tackle the intra-class variability in unseen state-objcet compositional images by using a Sequential Learning approach.
IEEE International Conference on Image Processing (ICIP), 2022
In this work, we attempt to disentangle the visual features of state and object in a state-objcet compositional images.
IEEE International Conference on Image Processing (ICIP), 2021
IEEE Symposium Series on Computational Intelligence (SSCI), 2017
IEEE Congress on Evolutionary Computation (CEC), 2016
Communicated to an IEEE Transaction
Communicated to an IEEE Transaction
Worked as anonymous reviewer/sub-reviewer for the following journals: IEEE TPAMI, IEEE TNNLS, IEEE TIP, IEEE TETCI, ACM Trans. on Multimedia Computing Communications and Applications and IEEE ICIP conference
Delivered lectures in miscellaneous deep-learning based topics in the Winter School on Deep Learning, for the years 2022, 2023 and 2024. Also delivered lectures in deep learning and machine learning based topics in different summer and winter schools organised by Technology Innovation Hub, Indian Statistical Institute (ISI) and also in Center for AI & ML (CAIML), ISI.
Performed the duty of Teaching Assistant for the Computing for Data Science subject for the students of the PGDBA course in ISI, Kolkata for the years 2022, 2023, 2024.
Supervised a group of participants in the Summer School organised by the Electronics and Communication Sciences Unit, ISI Kolkata in the year 2022, 2023 and 2024.