Samvit Jain

I am a machine learning scientist at Amazon Web Services (AWS) in Seattle, with a focus in computer vision.

I graduated with an M.S. in computer science from UC Berkeley in 2019, and a B.S.E. with highest honors in computer science from Princeton University in 2017.

At Berkeley, I was part of the RISE Lab, where I was advised by Professor Joseph Gonzalez. My research at Berkeley centered on efficient visual inference, spanning both computer vision and computer systems.

In past summers, I have interned at Microsoft Research and Databricks. While in undergrad, I co-founded LinkMeUp, a video link messaging service for iOS and Android with users in over 70 countries.

Email / LinkedIn / GitHub / Twitter
Publications
Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video
Samvit Jain, Xin Wang, Joseph Gonzalez.
CVPR 2019 [Oral presentation]
summary | arXiv | program | project page | code | video

We present Accel, a novel corrective fusion network that combines (1) optical flow-based feature warping with (2) lightweight, per-frame, temporal correction to achieve state-of-the-art accuracy and throughput on video semantic segmentation.

Scaling Video Analytics Systems to Large Camera Deployments
Samvit Jain, Ganesh Ananthanarayanan, Junchen Jiang, Yuanchao Shu, Joseph Gonzalez
HotMobile 2019
summary | arXiv | program

We discuss the potential of spatio-temporal correlations -- content correlations between geographically proximate cameras in wide-area enterprise camera deployments -- to improve cost efficiency and inference accuracy in large-scale video analytics operations. Our template application is real-time person re-identification and tracking.

Fast Semantic Segmentation on Video Using Motion Vector-Based Feature Interpolation
Samvit Jain, Joseph Gonzalez
ECCV 2018 International Workshop on Video Segmentation (IWVS)
summary | arXiv | program

We exploit video compression techniques (in particular, the block motion vectors in H.264 video) and feature similarity across frames to accelerate a classical image recognition task, semantic segmentation, on video.

Determining an Optimal Threshold on the Online Reserves of a Bitcoin Exchange
Samvit Jain, Edward Felten, Steven Goldfeder
Journal of Cybersecurity (JCS), 2018
summary | pdf | program

We investigate the fundamental tradeoff between exposure to online (network-based) and offline threats faced by a Bitcoin exchange that must store Bitcoin across online and offline storage, while guaranteeing availability to customers. Parameterizing deposit, withdrawal, and theft events as Poisson processes, we are able to model the financial dynamics of the exchange, and solve for the optimal threshold on online storage.


Technical Reports
Efficient Inference on Video, In Real-Time and At Scale
Samvit Jain
UC Berkeley Master's Thesis (Advisor: Joseph Gonzalez), 2019
Portal: Micropayments on the Paywalled Internet
Samvit Jain
Princeton Senior Thesis (Advisor: Brian Kernighan), 2017
summary | slides

Portal is a payment protocol and software system that enables one-click purchases of long-form news content on the Internet, without requiring a user to sign up for a subscription or login to a content provider's website.

Monetization on the Modern Web: Automated Micropayments From Bitcoin-Enabled Browsers
Samvit Jain
Princeton Junior Independent Work (Advisor: Arvind Narayanan), 2016
summary | pdf | github

We propose a Bitcoin micropayments-based revenue system for online businesses, which enables users to make small payments to access web content on a per-use basis, in lieu of viewing ads or signing up for a credit card subscription.

Recent Talks
CVPR 2019 Accel: A Corrective Fusion Network [video] Long Beach, CA June 20, 2019
RISE Retreat Scaling Video Analytics [video] Lake Tahoe, NV May 23, 2019
Amazon Toward Real-Time Perception Seattle, WA May 14, 2019
Tesla Toward Real-Time Perception Palo Alto, CA Apr 8, 2019
BAIR Retreat Accel: A Corrective Fusion Network Sonoma, CA Mar 25, 2019
HotMobile 2019 Scaling Video Analytics Santa Cruz, CA Feb 27, 2019
Apple Accelerating Semantic Segmentation on Video Cupertino, CA Jan 14, 2019
ECCV 2018 Accelerating Semantic Segmentation on Video Munich, Germany Sep 14, 2018