Sumit Sarin

I currently work at Google.

I completed my MS in Computer Science at Columbia University in New York, working on computer vision and machine learning problems as a Research Assistant (RA) with Prof. Carl Vondrick.

During my undergrad at Netaji Subhas Institute (now University) of Technology (NSIT) in New Delhi, I worked with Prof. Smriti Srivastava on computer vision, biometrics and multimodal learning.

Google Scholar  /  Github  /  LinkedIn

profile photo

Research

Research.

3DSP How Video Meetings Change Your Expression
Sumit Sarin, Utkarsh Mall, Purva Tendulkar, Carl Vondrick
European Conference on Computer Vision (ECCV), 2024.

We present FacET, a general-purpose framework to discover interpretable, spatio-temporal trends between two domains, that works even in the presence of dominant biases.

3DSP CNN-based Multimodal Touchless Biometric Recognition System using Gait and Speech
Sumit Sarin, Antriksh Mittal, Anirudh Chugh, Smriti Srivastava
Journal of Intelligent & Fuzzy Systems, 2022.

We propose a novel touchless multimodal person identification model using deep learning techniques by combining the gait and speech modalities.

3DSP Multi-modal Automated Speech Scoring using Attention Fusion
Manraj Singh Grover, Yaman Kumar, Sumit Sarin, Payman Vafaee, Mika Hama, Rajiv Ratn Shah
Arxiv.

In this study, we propose a novel multi-modal end-to-end neural approach for automated assessment of non-native English speakers' spontaneous speech using attention fusion.

Teaching

Teaching Assistant: CSOR 4231 Analysis of Algorithms I (Spring 2023)


Website template: Jon Barron.