Stars
A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.
Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
DeepVis Toolbox
Efficient Image Captioning code in Torch, runs on GPU
Character-level Convolutional Networks for Text Classification
ddtm / caffe
Forked from BVLC/caffeCaffe: a fast open framework for deep learning.
yjxiong / convnet
Forked from TorontoDeepLearning/convnetA GPU implementation of Convolutional Neural Nets in C++
yjxiong / caffe
Forked from MMLab-CU/caffeA fork of Caffe with OpenMPI-based Multi-GPU (mainly data parallel) support for action recognition and more. More documentation please see the original readme.