Joseph K J

Research Scientist

Bangalore

Joseph actively works in developing machine learning models for computer vision, which can continually learn and think imaginatively as we humans do. He is equally interested in multi-modal generation and representation learning.

His research works have been published at top venues like TPAMI, NeurIPS, CVPR (3 times including one oral), ICCV (2 times), ECCV (2 times), AAAI, IJCAI, BMVC and WACV. He received the Excellence in Research Award from IIT Hyderabad twice (in 2020 and 2022) and his PhD studies were supported by the TCS PhD Fellowship. He was awarded the AI GameChangers award by NASSCOM in 2022.

He has been a student researcher with Google Research, visiting scholar at MBZUAI, UAE and a research intern at IIAI, UAE and University of Tokyo, Japan. 

Please see his personal website for more information and a complete list of publications.

Publications

CoPL: Contextual Prompt Learning for Vision-Language Understanding

Goswami, K., Karanam, S., Udhayanan, P., J, J., Srinivasan, B. (Feb. 22, 2024)

AAAI 2024

Iterative Multi-Granular Image Editing Using Diffusion Models

J, J., Udhayanan, P., Shukla, T., Agarwal, A., Karanam, S., Goswami, K., Srinivasan, B. (Jan. 4, 2024)

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

Agarwal, A., Karanam, S., J, J., Saxena, A., Goswami, K., Srinivasan, B. (Oct. 2, 2023)

International Conference on Computer Vision (ICCV)