An Tran (@antran89)
  • Stars
    star
    322
  • Global Rank 84,059 (Top 3 %)
  • Followers 60
  • Following 23
  • Registered about 12 years ago
  • Most used languages
    C++
    37.5 %
    Python
    25.0 %
    MATLAB
    12.5 %
    DIGITAL Command Language
    6.3 %
    C
    6.3 %
    Shell
    6.3 %
    Java
    6.3 %
  • Location πŸ‡ΈπŸ‡¬ Singapore
  • Country Total Rank 523
  • Country Ranking
    DIGITAL Command Language
    1
    MATLAB
    47
    C++
    83
    Shell
    105
    C
    163
    Java
    171
    Python
    1,134

Top repositories

1

awesome-optical-flow-algorithm

A curated list of resources dedicated to optical flow algorithms. Feel free to make PRs to contribute.
142
star
2

OpticalFlow-comparisons

Comparisons between available optical flow implementations using MATLAB.
C++
32
star
3

two-stream-fcan

The repository to contain codes and models for paper "Two-stream Flow-guided Convolutional Attention Networks for Action Recognition".
Shell
22
star
4

road_visualizer

This software is a modification of Visualizer from Spacenet competition for road extraction. I made it work for DeepGlobe dataset also.
Java
21
star
5

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.
C++
21
star
6

UCF-Sports-annotations

UCF Sports annotations: This repository provides human bounding box annotations of UCF Sports dataset and a function to read these annotations.
MATLAB
14
star
7

BoW_frameworks

This is a BoW implementation for action recognition problem in Matlab.
C
11
star
8

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.
10
star
9

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.
C++
10
star
10

extract-video-frames

Tools to extract frames from video based on OpenCV and FFMPEG.
Python
8
star
11

dense_flow

This is an modification of dense_flow software to extract flows and frames fro large dataset such HMDB51, UCF101, Sports1M
C++
7
star
12

activitynet2017-nus

The repository to contain all codes and models for ActivityNet competition from NUS.
4
star
13

ud120-projects

Introduction to Machine Learning course
DIGITAL Command Language
3
star
14

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.
C++
3
star
15

nus-vision-multimedia-reading-group

The collection of seminar presentations in NUS Vision Multimedia Reading Group
2
star
16

clipping_ssbd_videos

Self-Stimulatory Behaviours Dataset (SSBD) dataset toolbox.
C++
2
star
17

shopee_tf_object_detection_api_examples

Python
1
star
18

sports1m-crawler

Scripts to download Sports1M dataset.
Python
1
star
19

pp-linknet

Python
1
star
20

OlympicsDataset

convert Olympic Sports dataset into avi file, split them into train and test folder
MATLAB
1
star