Krepsi's repositories
action_recog
fork from https://github.com/yjxiong/caffe
100-tiramisu-keras
Keras implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)
ActionTubes
forked from https://github.com/gkioxari/ActionTubes
cnn-benchmarks
Benchmarks for popular CNN models
conv_arithmetic
A technical report on convolution arithmetic in the context of deep learning
duplicate-image-finder
Identifies similar pictures on your local computer
FC-DenseNet-TensorFlow
Fully Convolutional DenseNet (A.K.A 100 layer tiramisu) for semantic segmentation of images implemented in TensorFlow.
kinetics-i3d
Convolutional neural network model for video classification trained on the Kinetics dataset.
natural-language-object-retrieval
Code release for Hu et al. Natural Language Object Retrieval, in CVPR, 2016
PSPNet-Keras-tensorflow
original code : https://github.com/hszhao/PSPNet
pytorch-resnet3d
I3D ResNets in Pytorch
referring-expressions
Localize objects in images using referring expressions
Semantic_Human_Matting
Semantic Human Matting
siamese-fc
State-of-the-art performance in arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.
temporal-shift-module
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding.
text_objseg
Code release for Hu et al. Segmentation from Natural Language Expressions. in ECCV, 2016.
text_objseg_caffe
Caffe implementation for Hu et al. Segmentation for Natural Language Expressions in arXiv:1603.06180, 2016 http://ronghanghu.com/text_objseg
tf_semantic_human_matting
semantic human matting
Tiramisu-keras
Tiramisu — One hundred layers
video-nonlocal-net
Non-local Neural Networks for Video Classification