Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding (2018-01-07T00:00:00.000000Z)

TL;DR

Two robust encoder-decoder type neural networks that generate multi-scale feature encodings in different ways and can be trained end-to-end using only a few training samples are proposed.

Authors

H. Keles

5 papers

Long Ang Lim

2 papers

TL;DR

Authors

References44 items

End-to-end video background subtraction with 3d convolutional neural networks

A deep convolutional neural network for video sequence background subtraction

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Interactive deep learning method for segmenting moving objects

Background subtraction using encoder-decoder structured convolutional neural network

Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric

A Deep Convolutional Neural Network for Background Subtraction

Deep background subtraction with scene-specific convolutional neural networks

Deep Residual Learning for Image Recognition

Human Action Recognition Based on Fusion Features Extraction of Adaptive Background Subtraction and Optical Flow Model

Towards Benchmarking Scene Background Initialization

How Far Can You Get By Combining Change Detection Algorithms?

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Recurrent Convolutional Neural Networks for Text Classification

A Self-Adjusting Approach to Change Detection Based on Background Word Consensus

Translating Videos to Natural Language Using Deep Recurrent Neural Networks

Deep visual-semantic alignments for generating image descriptions

Show and tell: A neural image caption generator

Efficient object localization using Convolutional Networks

Fully convolutional networks for semantic segmentation

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

CDnet 2014: An Expanded Change Detection Benchmark Dataset

Recurrent Convolutional Neural Networks for Scene Labeling

Visualizing and Understanding Convolutional Networks

Learning Hierarchical Features for Scene Labeling

ImageNet classification with deep convolutional neural networks

Background subtraction: Experiments and improvements for ViBe

Evaluation of background subtraction techniques for video surveillance

ViBe: A Universal Background Subtraction Algorithm for Video Sequences

A survey on vision-based human action recognition

Learning from Imbalanced Data

Learning object motion patterns for anomaly detection and improved object detection

Improved adaptive Gaussian mixture model for background subtraction

Editorial: special issue on learning from imbalanced data sets

Robust techniques for background subtraction in urban traffic video

Multi-camera calibration, object tracking and query generation

Adaptive background mixture models for real-time tracking

Comparison of the predicted and observed secondary structure of T4 phage lysozyme.

Foreground Segmentation for Anomaly Detection in Surveillance Videos Using Deep Residual Networks

SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity

“Keras.”

Spatiotemporal Saliency in Dynamic Scenes

An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names