meera1hahn
Ph.D. Student in Computer Science School of Interactive Computing Georgia Institute of Technology
Pinned Repositories
WAY
Where are you? Dataset. Code for the Localization from Embodied Dialog Task using a LingUNet-Skip Model
clearnlp-qa
Question-Answering System.
CNN_sentence
CNNs for sentence classification
Computer_Vision_CS_6476
Graph_LED
Localization via embodied dialog on the navigation graph
Matterport3DSimulator
AI Research Platform for Reinforcement Learning from Real Panoramic Images.
NRNS
Official implementation of the NRNS paper
Visual-Assistant
Learning a visually grounded memory assistant
VLN-CE
Vision-and-Language Navigation in Continuous Environments using Habitat
word_embedding_cnn
sentiment analysis using a cnn and word embeddings
meera1hahn's Repositories
meera1hahn/NRNS
Official implementation of the NRNS paper
meera1hahn/Graph_LED
Localization via embodied dialog on the navigation graph
meera1hahn/Visual-Assistant
Learning a visually grounded memory assistant
meera1hahn/word_embedding_cnn
sentiment analysis using a cnn and word embeddings
meera1hahn/clearnlp-qa
Question-Answering System.
meera1hahn/CNN_sentence
CNNs for sentence classification
meera1hahn/Computer_Vision_CS_6476
meera1hahn/Matterport3DSimulator
AI Research Platform for Reinforcement Learning from Real Panoramic Images.
meera1hahn/VLN-CE
Vision-and-Language Navigation in Continuous Environments using Habitat
meera1hahn/computer_vision_gatech
Computer Vision (CS 6476) Georgia Tech Assignment/Project Solutions
meera1hahn/cs325
Artificial Intelligence.
meera1hahn/cs571
Natural Language Processing.
meera1hahn/ego_centric_vision
tools for FPV
meera1hahn/emory_datamining
meera1hahn/emorynlp
Core NLP tools developed by Emory University.
meera1hahn/gensim
Topic Modelling for Humans
meera1hahn/Simmons
meera1hahn/TaskToBLN
meera1hahn/touchdown
Cornell Touchdown natural language navigation and spatial reasoning dataset.
meera1hahn/unisal
Unified Image and Video Saliency Modeling (ECCV 2020)
meera1hahn/vilbert-multi-task
Multi Task Vision and Language
meera1hahn/vln-bert
Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)