Ankit Jha

ankit.jha@lnmiit.ac.in

Date of joining:

01-07-2024

Department:

Computer Science Engineering

Summary

Ankit Jha is currently serving as an Assistant Professor in the Department of Computer Science and Engineering at The LNM Institute of Information Technology (LNMIIT), Jaipur, India. Prior to this, he worked as a Postdoctoral Researcher at INRIA, Grenoble, France. He completed his doctorate at the Center of Studies in Resources Engineering, Indian Institute of Technology Bombay, India. His research focuses on the application of deep learning in computer vision, particularly in multi-task learning (MTL), multimodal learning, multi-domain learning, vision-language prompt learning, and more.

Biography

Ankit Jha is an active researcher in the field of Computer Vision and Deep Learning and currently serving as an Assistant Professor in the Department of Computer Science and Engineering at The LNMIIT. He earned his Ph. D. from the Center of Studies in Resources Engineering (CSRE), Indian Institute of Technology Bombay, under the guidance of Prof. Biplab Banerjee, with a thesis titled "Learning Across Tasks and Domains in Remote Sensing." His research focuses on multimodal and multi-domain learning, particularly in remote sensing datasets. He also holds an M. Tech. in Modelling and Simulation from Defence Institute of Advanced Technology (DIAT-DU), Pune, and a B. Tech. in Electronics and Communication Engineering from Rajasthan Technical University, Kota. Following his PhD, Ankit worked as a Postdoctoral Researcher (Postdoc) at the National Institute for Research in Digital Science and Technology (INRIA), University Grenoble Alpes, under the supervision of Prof. Jocelyn Chanussot, focusing on multimodal learning for object detection and classification. Ankit's work has been recognized at top conferences such as CVPR, ECCV, BMVC, WACV, and ICVGIP, with accolades including Best Paper Awards at ECML-PKDD 2023 and ICVGIP 2023. His research has been published in the IEEE Transactions on Geoscience and Remote Sensing (TGRS) journal. He is actively involved in enhancing visual language models like CLIP, contributing to advancements in image recognition, semantic segmentation, and image retrieval tasks.

Research Area

Computer vision, deep learning, domain generalization and adaptation, remote sensing, prompt learning, federated learning, multi-task learning, multimodal learning, multidomain learning