An Tran

awesome-optical-flow-algorithm. A curated list of resources dedicated to optical flow algorithms. Feel free to make PRs to contribute.

OpticalFlow-comparisons. Comparisons between available optical flow implementations using MATLAB.

road_visualizer. This software is a modification of Visualizer from Spacenet competition for road extraction. I made it work for DeepGlobe dataset also.

two-stream-fcan. The repository to contain codes and models for paper "Two-stream Flow-guided Convolutional Attention Networks for Action Recognition".

my-very-deep-caffe. This is an implementation of very deep two stream CNNs for action recognition. The implementation is inspired by Wang et. al., https://github.com/yjxiong/caffe. Some improvements from Wang's implementation include reading videos from LDMB database, faster testing using LDMB interface. The aim is to work better with big dataset such as UCF101, HMDB51, Sports1M and ActivityNet easily.

UCF-Sports-annotations. UCF Sports annotations: This repository provides human bounding box annotations of UCF Sports dataset and a function to read these annotations.

awesome-deep-map. A curated list of resources dedicated to computer vision and related algorithms for creating, correcting maps. Feel free to make PRs to contribute.

BoW_frameworks. This is a BoW implementation for action recognition problem in Matlab.

New-C3D-Caffe. This is a reimplementation of 3D CNN (http://vlg.cs.dartmouth.edu/c3d/). It is compatitable with Caffe 2016. The Caffe is forked from Caffe commit c1126aadb6eab5229203bfba9495bc2b06b4ae89. This is an obsolete code, I do not provide the support for the project.

extract-video-frames. Tools to extract frames from video based on OpenCV and FFMPEG.

clipping_ssbd_videos. Self-Stimulatory Behaviours Dataset (SSBD) dataset toolbox.

dense_flow. This is an modification of dense_flow software to extract flows and frames fro large dataset such HMDB51, UCF101, Sports1M

activitynet2017-nus. The repository to contain all codes and models for ActivityNet competition from NUS.

mySTRUCK. Making STRUCK working with the latest Opencv 2.4.11 and latest Eigen 3.2.4. We also provide a different main function to directly initilize a bounding box for the first frame.

ud120-projects. Introduction to Machine Learning course

sirius. Sirius: Speech and Vision Based Intelligent Personal Assistant

nus-vision-multimedia-reading-group. The collection of seminar presentations in NUS Vision Multimedia Reading Group

shopee_tf_object_detection_api_examples. Python

sports1m-crawler. Scripts to download Sports1M dataset.

ActivityNet. This repository is intended to host tools and demos for ActivityNet

pp-linknet. Python

caffe-segmentation. modified version of Caffe which support DeconvNet and DecoupledNet, and I add modifications to supports reconstruction tasks.

actionMBH. C++

OlympicsDataset. convert Olympic Sports dataset into avi file, split them into train and test folder

Stretchable-Models-for-Motion-Parsing. code for Benjamin Sapp, David Weiss and Ben Taskar. "Parsing Human Motion with Stretchable Models". CVPR. June 2011.