byeongyeonkang Goto Github PK

actiontubes

source code for Finding Action Tubes, CVPR 2015

asms

Scale adaptive mean-shift tracker

caffe

Caffe: a fast open framework for deep learning.

deep-goggle

Source code for "Understanding Deep Image Representations by Inverting Them", CVPR 2015

gpu_flow

GPU based optical flow extraction in OpenCV

mexconv3d

Matlab mex implementation of the basic operations for 3D (volume) Convolutional Neural Network

siamese-fc

State-of-the-art performance in arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.

siamfc-tf

State-of-the-art object tracking at high framerates, in TensorFlow.

systest

twostreamfusion

Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.

vot-toolkit

Visual Object Tracking (VOT) challenge evaluation toolkit