GT-Vision-Lab/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.
Lua
Stargazers
- abhshkdzFAIR, Meta AI
- ahirner@MoonVision
- avisingh599Google Deepmind
- bobbensWaseda University
- bshillingford
- carpedm20Seoul, Korea
- ccurroEstee Lauder, The Cooper Union
- dasguptarMicrosoft AI and Research
- deepnarainsinghGalvanizeU
- esafakArchipelago AI
- ffmpbgrnn
- forrestbingAlibaba Inc
- handong1587
- he0x
- hohoCodeUniversity of Maryland College Park
- ili3pOxford University
- jnhwkimNAVER AI Lab
- jowagnerDublin City University
- JulianZhangshanghai, china
- leotam
- leotywy
- lipijiNUAA
- madisonmay@IndicoDataSolutions
- npowToronto, ON
- ownership-xyz
- petrjanda
- puppet101
- salomartin@yummyshop
- samim23infinity
- shicaiHangzhou
- soumithMeta
- stephenjia
- tejaskhotAbnormal Security
- xshhhm
- xuanhan863Los Angeles, USA
- yassersouriMicrosoft