Jin-Hwa Kim

ban-vqa. Bilinear attention networks for visual question answering

MulLowBiVQA. Hadamard Product for Low-rank Bilinear Pooling

cbp. Multimodal Compact Bilinear Pooling for Torch7

nips-mrn-vqa. Multimodal Residual Learning for Visual QA (NIPS 2016)

ddx. Deep Learning Dashboard

orthoad. Semi-Orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation

Pensees. A collection of fragments for reading research papers.

validate.js. Lightweight JavaScript form validation library inspired by CodeIgniter.

PREA. PREA for the comparative evaluation to MGBR.

dropc-wan. Regularization of Neural Networks using DropConnect

rnn. Recurrent Neural Network library for Torch7's nn

AMMA. Attentional Multi-Modal learning for Animation.

academic-kickstart. HTML

ngp_pl. Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

tiny-cuda-nn. Lightning fast C++/CUDA neural network framework

Mask2Former. Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

nerf_pl. NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

spectral-lib. Lua

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.

skip-thoughts.torch. Porting of Skip-Thoughts pretrained models from Theano to PyTorch & Torch7

mid.metric. Python

bashrc-vimrc. bashrc and vimrc I'm using.

Eye-Tracking. Testbed for eye-tracking data of KidsVideo.

visdial. [CVPR 2017] Torch code for Visual Dialog

flownet. Lua

awesome-rnn. Recurrent Neural Network - A curated list of resources dedicated to RNN

pycvmpeg7. A port of the MPEG-7 visual descriptor library (MPEG7FexLib by Bilkent University) with slight tweaks to python