Jay Gopal's Projects
Clustering the image embeddings from the latent space of a masked autoencoder to visualize how learned features separate classes, and as a proxy for accuracy.
Implementing video clickme to create explainable 3D computer vision models
Final Project for CLPS 1492 for Fall 2023. Group members: Jeremy Fleming and Jay Gopal
Official implementation of Character Region Awareness for Text Detection (CRAFT)
mock-typescript from Brown's CSCI 0320
Project for CSCI 2952G: Deep Learning in Genomics
A more interpretable way to regularize convolutional neural networks (CNNs) during training
The authors' official implementation of GANalyze, a framework for studying cognitive properties such as memorability, aesthetics, and emotional valence using genenerative models.
Automated diagnosis of glaucoma using machine learning
Efficient face emotion recognition in photos and videos
A personal website with a couple of details about me
LAVIS - A One-stop Library for Language-Vision Intelligence
[IJCAI 2022] Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition, Pytorch code
OpenMMLab Pose Estimation Toolbox and Benchmark.
Tool for measurement of digital biomarkers from video or audio of an individual’s behavior.
Transfer data from my computer to p node
Quantum Error Correction (QEC) is a critical step in implementing quantum computing at scale. We implement an algorithm and show it successfully reduces noise in various quantum circuits.
System to run video classification experiments with Amazon's Mechanical Turk using Python Flask.
A behavioral decision making task and computational modeling to distinguish human discount factors. How much does a given participant devalue future reward?
This repository contains the ViewFool and ImageNet-V proposed by the paper “ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints” (NeurIPS2022).
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models