Aditya Panda

About Me

I am currently in my final year as a doctoral student at the Indian Statistical Institute. Over the past few years, I have primarily focused on data-efficient deep learning approaches. My research interest has been into various aspects of Compositional Zero-Shot Learning (CZSL), which aims to recognize new state-object compositions from limited training data. Before pursuing my Ph.D., I earned an M.Tech degree in Computer Science from ISI, Kolkata, and prior to that, I completed my undergraduate studies in Electronics and Tele-Communication Engineering from Jadavpur University, Kolkata.

Research Interests

Computer Vision: image recognition, image generation, video captioning

Publications[Google Scholar][DBLP]

Knowledge Guided Transformer Network for Compositional Zero-shot Learning

Aditya Panda, Dipti Prasad Mukherjee

ACM Transactions on Multimedia Computing, Communications and Applications, 2024.

PDF BibTex

Compositional Zero-Shot Learning using Multi-Branch Graph Convolution and Cross-layer Knowledge Sharing

Aditya Panda, Dipti Prasad Mukherjee

Pattern Recognition, 2024.

PDF BibTex

Isolating Features of Object and Its State for Compositional Zero-Shot Learning

Aditya Panda, Bikash Santra, Dipti Prasad Mukherjee

IEEE Transactions on Emerging Topics in Computational Intelligences, 2024.

PDF BibTex

Bi-Modal Compositional Network for Feature Disentanglement

Aditya Panda, Bikash Santra, Dipti Prasad Mukherjee

IEEE International Conference on Image Processing (ICIP), 2022.

PDF BibTex

Monocular 3D human pose estimation by multiple hypothesis prediction and joint angle supervision

Aditya Panda, Dipti Prasad Mukherjee

IEEE International Conference on Image Processing (ICIP), 2021

PDF BibTex

Particle swarm optimization with a modified learning strategy and blending crossover

Aditya Panda, Rammohan Mallipedd,Swagatam Das.

IEEE Symposium Series on Computational Intelligence (SSCI), 2017

PDF BibTex

Static learning particle swarm optimization with enhanced exploration and exploitation using adaptive swarm size

Aditya Panda, Srijan Ghoshal, Amit Konar, Bonny Banerjee, Atulya K Nagar.

IEEE Congress on Evolutionary Computation (CEC), 2016

PDF BibTex

Under Review Manuscripts

Prompt-Driven Network for Compositional Zero-Shot Learning

Aditya Panda, Dipti Prasad Mukherjee

Communicated to an IEEE Transaction.

Partially Supervised Compositional Zero-Shot Learning by Locality Preserving Neighbourhood Aggregation

Aditya Panda, Dipti Prasad Mukherjee

Communicated to an IEEE Transaction, 2024.

Services

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.