arijitray1993 Goto Github PK

arijitray1993.github.io

Personal Webpage

caffeclassweightlayer

Weigh classes of a classification network in caffe differently

carla_tutorial

cola

COLA: Evaluate how well your vision-language model can Compose Objects Localized with Attributes!

convqa

Data and models for "Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation"

csrankings

A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.

cvpr2015

errormap_atteneval

Code for the paper: Pointing to Error-Inducing Regions to Improve Explanation Helpfulness

formal_methods1

frequentitemsetmining

python code for various ways of mining frequent item sets in a set of transactions.

helpfulness_evaluation

Evaluate helpfulness of heatmap-based explanations for predicting model performance

imagegen

Generate more enriched images

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

music_video_gen

Music Video Generation using a Deep Generative Adversarial Network

practical_tmux

Barebones practical tmux configuration with keyboard-based fast switching and resizing because mouse-mode sucks for copy-pasting

questioncaptionmatchmodels

Question- Question/Caption Similarity Models for Identifying True vs False Premise Questions in VQA

r2d3

raspberrypi_surveillance

rpi_alarm

WiFi-based alarm using Raspberry Pi

signup

Information about signing up for a free Epic Games account

socratis

A benchmark of diverse emotional reactions and explanations for image-caption pairs

tensorflowrbf

This repository explores the design of a Radial Basis Function and related functions (like K-Means) for use with TensorFlow.

utils

Common utils I use for multiple projects

visdial-amt-chat

Code for the chat interface used to collect the VisDial dataset on AMT

viske

visualattention

Data Analyses for the visual attention data

vqa_lstm_cnn

Train a deeper LSTM and normalized CNN Visual Question Answering model. This current code can get 58.16 on OpenEnded and 63.09 on Multiple-Choice on test-standard.

vqarelevance

Models and Codes for the paper Question Relevance in VQA: Identifying Non-Visual And False-Premise Questions