benben0413 Goto Github PK

abnormal-event-detection

Abnormal event detection is a growing demand to process a plethora of surveillance videos. Our project helps detect the abnormality in videos with high accuracy, thus saving time for organizations and individuals who would have to go through the entire footage instead.

abnormal-event-detection-python-opencv-keras-tensorflow

abnormal-spatiotemporal-ae

Codes for "Abnormal Event Detection in Videos using Spatiotemporal Autoencoder".

abnormal_event_detection

Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder

abnormalbehaviordetection

abnormal behavior detection using CNN and RNN

abnormaldetection

abnormarcrowddetection

Abnormal Crowd Detection Implementation with Python

adversarial_video_summary

PyTorch Implementation of SUM-GAN from "Unsupervised Video Summarization with Adversarial LSTM Networks (CVPR 2017)"

ai---video-summary

Video summarization project computing the video's histogram per frame and applying K-means for finding relevant frames for the summarization process

aichallenger_sceneclassification_zjugive

TOP5 code for 2017 AI Challenger (Competition of Scene Classification)

al_cnn_crowd

Active learning CNN on Crowd density

anomaly-event-detection

Work in progress and needs a lot of changes for now. An implementation of paper Detecting anomalous events in videos by learning deep representations of appearance and motion on python, opencv and tensorflow. This paper uses the stacked denoising autoencoder for the the feature training on the appearance and motion flow features as input for different window size and using multiple SVM as a single classifier this is work under progress.

anomaly_detection

This repository contains all the codes related to the project 'Anomaly Detection in Surveillance Videos'. Codes related to model training, testing, summarization are present along with documentation. The project also uses an analysis method known as Grad-CAM which highlights regions of input, which played a role in the decision making of the model.

attentiondeepmil

Implementation of Attention-based Deep Multiple Instance Learning in PyTorch

audio-visual-video-caption

Pytorch implementation of audio-visual fusion video captioning model

aurora_detection

Detect the key-frame in the image series

awesome_computer_vision

Awesome Computer Vision

bilstm_cnn_crf_cws

BiLstm+CNN+CRF 法律文档（合同类案件）领域分词（100篇标注样本）

bsn-boundary-sensitive-network-master

Dense-Captioning Events in Videos-Proposal

c4-real-time-pedestrian-detection

Real-Time Human Detection Using Contour Cues

cancer-detector

Multi-Instance-Learning to check breast cancer. An implementation of Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification[arXiv:1504.07947] https://arxiv.org/abs/1504.07947

carpedestriandetection

ccm

citation-knn

CSC-522: Implemented Citation KNN which is one of the most popular algorithms for solving multiple-instance learning (MIL) problems. It is a lazy learning algorithm which tries to classify a bag of instances by using labelled bags of instances.

cl_cnn_crowd

CL_CNN_Crowd

cnn-lstm-bilstm-deepcnn-clstm-in-pytorch

In PyTorch Learing Neural Networks Likes CNN(Convolutional Neural Networks for Sentence Classification (Y.Kim, EMNLP 2014) 、LSTM、BiLSTM、DeepCNN 、CLSTM、CNN and LSTM

conditional-gan

this is the pytorch version of Conditional Generative Adversarial Nets

copy-move-forgery-detection-using-dog-and-orb

Copy–Move forgery or Cloning is a type of Image tampering where a part of the image is copied and pasted on another part of same image. Copy–move forgery detection technique using DoG (Difference of Gaussian) blob detector, with rotation invariant and resistant to noise feature called ORB (Oriented Fast and Rotated Brief) is poroposed.

copy-move_forgery_detection

Trabalho para cadeira de Processamento de Imagens

crowd-density-estimation