| CARVIEW |
Biography
I’m currently a Chief Engineer at Samsung R&D Institute India-Bangalore (SRI-B). Previously, I was a Postdoctoral fellow at the University of Bristol, working with Prof. Dima Damen as a part of the EPSRC VisualAI Grant, and a Research Scientist at TensorTour Inc.
I obtained my Ph.D. from the Department of Computer Science and Engineering at Indian Institute of Technology Kanpur advised by Dr. Gaurav Sharma and Prof. Manindra Agarwal. I have completed my Master’s in Medical Imaging and Informatics from Indian Institute of Technology Kharagpur advised by Dr. Rajiv Ranjan Sahay and Prof. Pranab Kumar Dutta.
My research lies at the intersection of computer vision and machine learning, with a particular emphasis on multimodal perception. Specifically, I investigate the integration of audio and visual modalities to advance machine perception across diverse applications. Currently, my work focuses on audio generation conditioned on multimodal inputs, aiming to enhance cross-modal synthesis and representation learning.
News
Publications
-
HD-EPIC: A Highly-Detailed Egocentric Video Dataset
Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha, Omar Emara, Sam Pollard, Kranti Kumar Parida, Kaiting Liu, Prajwal Gatti, Siddhant Bansal, Kevin Flanagan, Jacob Chalk, Zhifan Zhu, Rhodri Guerrier, Fahd Abdelazim, Bin Zhu, Davide Moltisanti, Michael Wray, Hazel Doughty, Dima Damen,CVPR 2025
- Discriminative Semantic Transitive Consistency for Cross-Modal Learning
- Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention
- Beyond Image to Depth: Improving Depth Prediction using Echoes
- AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features From Multi-Modal Embeddings
- Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos
-
Simultaneous blur map estimation and deblurring of a single space-variantly defocused image
Latha H. Narayan, Kranti Kumar Parida, Rajiv Ranjan SahayNCC 2017
@inproceedings{narayan2017simultaneous, title={Simultaneous blur map estimation and deblurring of a single space-variantly defocused image}, author={Narayan, Latha H and Parida, Kranti K and Sahay, Rajiv R}, booktitle={2017 Twenty-third National Conference on Communications (NCC)}, pages={1--6}, year={2017}, organization={IEEE} }
Teaching Experience
IIT Kanpur
ESC101 : Introduction to Programming - Tutor (2019-20 I), with Prof. Piyush Rai
CS771 : Introduction to Machine Learning (2018-19 I), with Prof. Piyush Rai
CS671 : Introduction to Natural Language Processing (2017-18 II), with Prof. Harish Karnick
CS773 : Online Learning and Optimization (2016-17 II), with Prof. Purushottam Kar
ESC101 : Introduction to Programming - TA (2017-18 I, 2018-19 II)