UntrimmedNet

Action recognition system

A system for recognizing and detecting actions in untrimmed videos using a weakly supervised learning approach.

Weakly Supervised Action Recognition and Detection

GitHub

162 stars
18 watching
47 forks
Language: Matlab
last commit: almost 8 years ago
Linked from 1 awesome list

action-detectionaction-recognitionweakly-supervised-learning

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
zhiwu-huang/lienetThis project uses deep learning and Lie group theory to recognize actions from skeleton data64
wanglimin/tddA tool for extracting features from videos using deep convolutional descriptors104
lukereichold/visualactionkitAn iOS framework for classifying human actions in videos using deep learning models24
wangguanzhi/ladnA deep learning-based framework for facial makeup transfer and removal using adversarial disentangling networks182
jingzhang617/cod-rank-localize-and-segmentDevelops a system to detect, segment, and rank camouflaged objects in images.74
naoto0804/cross-domain-detectionDevelops object detection algorithms to adapt to new domains with limited supervision422
guillaume-chevalier/har-stacked-residual-bidir-lstmsAn implementation of a deep neural network architecture for Human Activity Recognition using stacked residual bidirectional LSTM cells with TensorFlow.319
neuraxio/lstm-human-activity-recognitionAn LSTM-based human activity recognition system using smartphone sensor data.3
shahroudy/nturgb-dA large-scale dataset for human action recognition763
vowpalwabbit/vowpal_wabbitAn online learning system that enables fast and scalable machine learning with techniques like active learning and contextual bandits.8,495
xiaolonw/adversarial-frcnnA Caffe-based implementation of A-Fast-RCNN, a method for object detection using adversarial networks.482
meituan-automl/lennaAn AI-powered image detection system with language-based reasoning capabilities78
liushenwenyuan/matlab_orcA Matlab implementation of a handwritten digit recognition system using neural networks.50
juntang-zhuang/laddernetA deep learning implementation of a multi-path network architecture for medical image segmentation140
ma-shamshiri/human-activity-recognitionA human activity recognition project using accelerometer and gyroscope sensor data from phone and watch.101