Agrim Gupta

I am a second year master's student at Stanford University. I am working as a teaching assistant for CS231n: Convolutional Networks for Visual Recognition this spring. I am also working with the Stanford Vision Lab headed by Prof. Fei-Fei Li. Previously, I was a research assistant with the SNAP group under Prof. Jure Leskovec. I am interested in deep learning and its applications to computer vision.

Publications and Preprints

Characterizing and Improving Stability in Neural Style Transfer
Agrim Gupta, Justin Johnson, Alexandre Alahi, & Li Fei-Fei


Pedestrian Attribute Detection using CNN
Agrim Gupta, & Jayanth Ramesh
[pdf] [poster]

Social Recommendation System Leveraging Heterogeneity of Relations in a Social Network
Pulkit Agrawal, Jayanth Ramesh, & Agrim Gupta
[pdf] [poster]

Community Detection based on Music Listening Habits
Agrim Gupta, Karan Rai, & Nehal Bhandari

Research Experience

Research Assistant, SNAP Group
As a research assistant I have been working on adding features to SNAP library (C++). Some of the projects I have worked on are:

  • Temporal Cascade Detection [pdf] [code]
  • Miner Bio Dataset [code]
  • 64-Bit SNAP : Making SNAP 64-bit compliant

Research Intern, University of Southern California
As a research intern I developed a parameterized Image Convolution architecture which was optimized for energy efficiency by using memory scheduling and reduction in latency by increased parallelism. [pdf]