Popular repositories Loading

1. VQA_LSTM_CNN VQA_LSTM_CNN Public

   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.

   Lua 379 133

2. VQA VQA Public

   Python 374 142

3. abstract_scenes_v002 abstract_scenes_v002 Public

   The second version of the interface for Abstract Scenes research project.

   JavaScript 22 18

4. GuessWhich GuessWhich Public

   Evaluating Visual Conversational Agents via Cooperative Human-AI Games

   Lua 21 6

5. vision_language_in_the_wild vision_language_in_the_wild Public

   Python 5 1

6. vqa_browser vqa_browser Public

   The VQA dataset browser back-end code, using nginx, Django, an PostgreSQL (running in Docker containers).

   Python 4 5