scholarly journals Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7508
Author(s):  
Zhen Ma ◽  
José J. J. Machado ◽  
João Manuel R. S. Tavares
Keyword(s):  
Anomaly Detection ◽  
Network Architecture ◽  
Vision Research ◽  
Large Scale ◽  
Three Dimensional ◽  
Neural Network Architecture ◽  
Temporal Features ◽  
Weakly Supervised ◽  
Lstm Network ◽  
High Computational Efficiency

Weakly supervised video anomaly detection is a recent focus of computer vision research thanks to the availability of large-scale weakly supervised video datasets. However, most existing research works are limited to the frame-level classification with emphasis on finding the presence of specific objects or activities. In this article, a new neural network architecture is proposed to efficiently extract the prominent features for detecting whether a video contains anomalies. A video is treated as an integral input and the detection follows the procedure of video-label assignment. The extraction of spatial and temporal features is carried out by three-dimensional convolutions, and then their relationship is further modeled using an LSTM network. The concise structure of the proposed method enables high computational efficiency, and extensive experiments demonstrate its effectiveness.

scholarly journals Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke

2021 ◽  
Vol 2099 (1) ◽  
pp. 012021
Author(s):  
A V Dobshik ◽  
A A Tulupov ◽  
V B Berikov
Keyword(s):  
Computed Tomography ◽  
Network Architecture ◽  
Semantic Segmentation ◽  
Training Data ◽  
Neural Network Architecture ◽  
Brain Images ◽  
Tomographic Images ◽  
Computed Tomography Images ◽  
Segmentation Accuracy ◽  
Weakly Supervised

Abstract This paper presents an automatic algorithm for the segmentation of areas affected by an acute stroke in the non-contrast computed tomography brain images. The proposed algorithm is designed for learning in a weakly supervised scenario when some images are labeled accurately, and some images are labeled inaccurately. Wrong labels appear as a result of inaccuracy made by a radiologist in the process of manual annotation of computed tomography images. We propose methods for solving the segmentation problem in the case of inaccurately labeled training data. We use the U-Net neural network architecture with several modifications. Experiments on real computed tomography scans show that the proposed methods increase the segmentation accuracy.

scholarly journals TDPP-Net: Achieving three-dimensional path planning via a deep neural network architecture

2019 ◽  
Vol 357 ◽  
pp. 151-162 ◽  
Author(s):  
Keyu Wu ◽  
Mahdi Abolfazli Esfahani ◽  
Shenghai Yuan ◽  
Han Wang
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Three Dimensional ◽  
Neural Network Architecture

scholarly journals Robust Negative Sampling for Network Embedding

2019 ◽  
Vol 33 ◽  
pp. 3191-3198 ◽  
Author(s):  
Mohammadreza Armandpour ◽  
Patrick Ding ◽  
Jianhua Huang ◽  
Xia Hu
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Embedding Problem ◽  
Network Embedding ◽  
Neural Network Architecture ◽  
Suitable Candidate ◽  
Computationally Expensive ◽  
Large Scale Networks ◽  
Method R

Many recent network embedding algorithms use negative sampling (NS) to approximate a variant of the computationally expensive Skip-Gram neural network architecture (SGA) objective. In this paper, we provide theoretical arguments that reveal how NS can fail to properly estimate the SGA objective, and why it is not a suitable candidate for the network embedding problem as a distinct objective. We show NS can learn undesirable embeddings, as the result of the “Popular Neighbor Problem.” We use the theory to develop a new method “R-NS” that alleviates the problems of NS by using a more intelligent negative sampling scheme and careful penalization of the embeddings. R-NS is scalable to large-scale networks, and we empirically demonstrate the superiority of R-NS over NS for multi-label classification on a variety of real-world networks including social networks and language networks.

scholarly journals EDC-Net: Edge Detection Capsule Network for 3D Point Clouds

2021 ◽  
Vol 11 (4) ◽  
pp. 1833 ◽  
Author(s):  
Dena Bazazian ◽  
M. Eulàlia Parés
Keyword(s):  
Edge Detection ◽  
Network Architecture ◽  
Large Scale ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
3D Point Clouds ◽  
Abstract Shape ◽  
Edge Points ◽  
Weakly Supervised ◽  
Edge Features

Edge features in point clouds are prominent due to the capability of describing an abstract shape of a set of points. Point clouds obtained by 3D scanner devices are often immense in terms of size. Edges are essential features in large scale point clouds since they are capable of describing the shapes in down-sampled point clouds while maintaining the principal information. In this paper, we tackle challenges of edge detection tasks in 3D point clouds. To this end, we propose a novel technique to detect edges of point clouds based on a capsule network architecture. In this approach, we define the edge detection task of point clouds as a semantic segmentation problem. We built a classifier through the capsules to predict edge and non-edge points in 3D point clouds. We applied a weakly-supervised learning approach in order to improve the performance of our proposed method and built in the capability of testing the technique in wider range of shapes. We provide several quantitative and qualitative experimental results to demonstrate the robustness of our proposed EDC-Net for edge detection in 3D point clouds. We performed a statistical analysis over the ABC and ShapeNet datasets. Our numerical results demonstrate the robust and efficient performance of EDC-Net.

scholarly journals Deep-learning Reconstruction of Three-dimensional Galaxy Distributions with Intensity Mapping Observations

2021 ◽  
Vol 923 (1) ◽  
pp. L7
Author(s):  
Kana Moriwaki ◽  
Naoki Yoshida
Keyword(s):  
Deep Learning ◽  
Emission Line ◽  
Network Architecture ◽  
Large Scale ◽  
Three Dimensional ◽  
Line Emission ◽  
Correlation Coefficients ◽  
Emission Lines ◽  
Generative Adversarial Network ◽  
Intensity Mapping

Abstract Line-intensity mapping is emerging as a novel method that can measure the collective intensity fluctuations of atomic/molecular line emission from distant galaxies. Several observational programs with various wavelengths are ongoing and planned, but there remains a critical problem of line confusion; emission lines originating from galaxies at different redshifts are confused at the same observed wavelength. We devise a generative adversarial network that extracts designated emission-line signals from noisy three-dimensional data. Our novel network architecture allows two input data, in which the same underlying large-scale structure is traced by two emission lines of H α and [Oiii], so that the network learns the relative contributions at each wavelength and is trained to decompose the respective signals. After being trained with a large number of realistic mock catalogs, the network is able to reconstruct the three-dimensional distribution of emission-line galaxies at z = 1.3−2.4. Bright galaxies are identified with a precision of 84%, and the cross correlation coefficients between the true and reconstructed intensity maps are as high as 0.8. Our deep-learning method can be readily applied to data from planned spaceborne and ground-based experiments.

Eigenfaces for Recognition

1991 ◽  
Vol 3 (1) ◽  
pp. 71-86 ◽  
Author(s):  
Matthew Turk ◽  
Alex Pentland
Keyword(s):  
Real Time ◽  
Network Architecture ◽  
Three Dimensional ◽  
Feature Space ◽  
Recognition Problem ◽  
Neural Network Architecture ◽  
Face Images ◽  
Characteristic Views ◽  
The Face ◽  
Small Set

We have developed a near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals. The computational approach taken in this system is motivated by both physiology and information theory, as well as by the practical requirements of near-real-time performance and accuracy. Our approach treats the face recognition problem as an intrinsically two-dimensional (2-D) recognition problem rather than requiring recovery of three-dimensional geometry, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as "eigenfaces," because they are the eigenvectors (principal components) of the set of faces; they do not necessarily correspond to features such as eyes, ears, and noses. The projection operation characterizes an individual face by a weighted sum of the eigenface features, and so to recognize a particular face it is necessary only to compare these weights to those of known individuals. Some particular advantages of our approach are that it provides for the ability to learn and later recognize new faces in an unsupervised manner, and that it is easy to implement using a neural network architecture.

scholarly journals USING LSTM NETWORK FOR SOLVING THE MULTIDIMENTIONAL TIME SERIES FORECASTING PROBLEM

2021 ◽  
Vol 2 (68) ◽  
pp. 43-48
Author(s):  
M. Obrubov ◽  
S. Kirillova
Keyword(s):  
Time Series ◽  
Recurrent Neural Networks ◽  
Network Architecture ◽  
Time Series Prediction ◽  
Prediction Problem ◽  
Neural Network Architecture ◽  
The Neural Network ◽  
Multidimensional Time Series ◽  
Lstm Network

The article discusses using of the recurrent neural networks technology to the multidimensional time series prediction problem. There is an experimental determination of the neural network architecture and its main hyperparameters carried out to achieve the minimum error. The revealed network structure going to be used further to detect anomalies in multidimensional time series.

Sign in / Sign up

Export Citation Format

Share Document