DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients：https://github.com/ppwwyyxx/tensorpack/tree/master/examples/DoReFa-Net

Code for Stacked attention networks for image question answering：https://github.com/zcyang/imageqa-san

Newtonian Image Understanding: Unfolding the Dynamics of Objects in Statis Images：https://github.com/roozbehm/newtonian

Joint Unsupervised Learning of Deep Representations and Image Clusters：https://github.com/jwyang/joint-unsupervised-learning

Video detection library：https://github.com/myfavouritekk/vdetlib

Improving Localization Accuracy for Object Detection ：https://github.com/gidariss/LocNet

Domain Guided Dropout for Person Re-identification：https://github.com/Cysu/dgd_person_reid

Repository containing wrapper to obtain various object proposals easily ：https://github.com/batra-mlp-lab/object-proposals

The Hungarian-BP code：https://github.com/zzhang1987/HungarianBP

Segment-CNN: A Framework for Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs ：https://github.com/zhengshou/scnn

A Comparative Study for Single Image Blind Deblurring (CVPR 2016)https://github.com/phoenix104104/cvpr16_deblur_study

Code for "Large-Scale Location Recognition and the Geometric Burstiness Problem" ：https://github.com/tsattler/geometric_burstiness

A Caffe-based implementation of very deep convolution network for image super-resolution ：https://github.com/huangzehao/caffe-vdsr

Dynamically neural network structures for multi-domain question answering ：https://github.com/jacobandreas/nmn2

DPPnet: Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction ：https://github.com/HyeonwooNoh/DPPnet

Shallow and Deep Convolutional Networks for Saliency Prediction https://imatge.upc.edu/web/publications/shallow-and-deep-convolutional-networks-saliency-prediction ：https://github.com/imatge-upc/saliency-2016-cvpr

Main repository for Deep Metric Learning via Lifted Structured Feature Embedding ：https://github.com/rksltnl/Deep-Metric-Learning-CVPR16

Code release for Hu et al. Natural Language Object Retrieval, in CVPR, 2016 http://ronghanghu.com/text_obj_retrieval/：https://github.com/ronghanghu/natural-language-object-retrieval

Faster R-CNN features for Instance Search ：https://github.com/imatge-upc/retrieval-2016-deepvision

Code for cvpr2016 paper "Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs" ：https://github.com/zeakey/DeepSkeleton

Code for "Accumulated Stability Voting: A Robust Descriptor From Descriptors of Multiple Scales. - Tsun-Yi Yang, Yen-Yu Lin, Yung-Yu Chuang" Accumulated Stability Voting ：https://github.com/shamangary/ASV

Source code for Deep Saliency with Encoded Low Level Distance Map and High Level Features, CVPR 2016：https://github.com/gylee1103/SaliencyELD

Code for "Scale-Aware Alignment of Hierarchical Image Segmentation. - Yuhua Chen, Dengxin Dai, Jordi Pont-Tuset, Luc Van Gool" ：https://github.com/yuhuayc/alignhier

Code for "One-Shot Learning of Scene Locations via Feature Trajectory Transfer. - Roland Kwitt, Sebastian Hegenbart, Marc Niethammer" ：https://github.com/rkwitt/TrajectoryTransfer

The toolbox for the Google Refexp dataset proposed in this paper: http://arxiv.org/abs/1511.02283 ：https://github.com/mjhucla/Google_Refexp_toolbox

A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (DAVIS)：https://github.com/fperazzi/davis

Activation function used in "Learning to Assign Orientations to Feature Points. - Kwang Moo Yi, Yannick Verdie, Pascal Fua, Vincent Lepetit"：https://github.com/nyanp/tiny-cnn/pull/61

Dense image captioning in Torch - Code for "DenseCap: Fully Convolutional Localization Networks for Dense Captioning, Justin Johnson, Andrej Karpathy, Li Fei-Fei"：https://github.com/jcjohnson/denseca