Georgia Tech Visual Intelligence Lab's repositories
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.
abstract_scenes_v002
The second version of the interface for Abstract Scenes research project.
GuessWhich
Evaluating Visual Conversational Agents via Cooperative Human-AI Games
VQA-Website
Visual Question Answering Website
vqa_browser
The VQA dataset browser back-end code, using nginx, Django, an PostgreSQL (running in Docker containers).
torch-utilities
Utility functions for neural network implementations in Torch