Harnessing high-level concepts, visual, and auditory features for violence detection in videos

Peixoto, Bruno Malveira; Lavi, Bahram; Dias, Zanoni; Rocha, Armando Freitas da

doi:10.1016/j.jvcir.2021.103174

Cited by 18 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, the learning video can help those in need optimize learning outcomes with the help of Video as a learning medium. According to (Y.-N. Peixoto et al, 2021), Video usefulness in question is academic and non-academic uses in the educational field. The material must be useful to improve students' abilities.…”

Section: Resultsmentioning

confidence: 99%

Higher-Order Thinking Skills Profile of Islamic Boarding School Students on Geometry through the STEM–based Video Approach

Pujiastuti

Haryadi

2023

ijses

View full text Add to dashboard Cite

The Indonesia government has begun to focus and pay attention to the quality of education in Islamic Boarding School. Education is a provision for the future to create quality human resources. Education is strongly linked to the 21st century, where education has rapidly developed in science and technology to generate worldwide competitiveness. Students' higher-order thinking skills are fundamental, where this thinking ability is an ability to understand and find solutions to problems in varied and different ways. An appropriate learning approach must support Higher-order thinking skills. Higher-order thinking skills are intelligence with specific knowledge that leads to reasoning, analytical skills, problem-solving, and critical and creative thinking skills. Higher-order thinking skills are the major objective of educational institutions in implementing education that uses a quasi-experiment. Participants consisted of Islamic Boarding School students, ten male- and ten female students. A STEM-based video is a learning approach that can help students analyze, solve problems, investigate a phenomenon, create skills in students, and produce higher-order thinking skills. This study's STEM-based Video approach process is designed to solve functional mathematics problems in real life concerning geometry.

show abstract

Section: Resultsmentioning

confidence: 99%

Higher-Order Thinking Skills Profile of Islamic Boarding School Students on Geometry through the STEM–based Video Approach

Pujiastuti

Haryadi

2023

ijses

View full text Add to dashboard Cite

show abstract

“…Bruno M. Peixoto et al present a system where violence detection is based on different mechanics based on machine learning [1]. This proposed system breaks into different understood levels of violence (i.e., fights, explosions, blood, and gunshots) and combines all of them for a more detailed understanding of particular scene detection.…”

Section: Literature Reviewmentioning

confidence: 99%

“…These types of systems work well for less crowded areas. With the introduction of data mining and deep learning techniques, autonomous violence detection techniques are widely used for video surveillance [1]. A lot of work has been carried out in recent years on recognition of human actions using vision and acoustic technologies.…”

Section: Introduction 11 Motivationsmentioning

confidence: 99%

Autonomous Anomaly Detection System for Crime Monitoring and Alert Generation

Kukade

Soner

Pandya

2023

JAMRIS

View full text Add to dashboard Cite

Nowadays violence in society impacts more than any weapon used by people. Over the last few years, autonomous vehicles have been used to observe and recognize the abnormality in the behavior of people and classifying them as a crime or not. Detecting crime on live stream is a classification of any event in a crime or not a crime and generating alerts to designated authorities which in turn can take required actions and ensure the security assessment of the city. Such kind of effective techniques for live video stream processing in computer vision is the need of the hour. There are many techniques that can be used, while Long Short-Term Memory (LSTM) networks and OpenCV provide the most accurate prediction for this task. OpenCV is used for the task of object detection in computer vision which will take the input from either drone or any autonomous vehicle. LSTM is used to classify any event or behavior in crime or not. This live stream is also encrypted for more security. To make this system more secure with the use of a security algorithm. This system uses the Elliptic curve algorithm to protect data from any kind of manipulation. Through its ability to sense its surroundings, an autonomous vehicle is able to operate itself and execute critical activities without the need for human interaction. Video surveillance of computer vision technology can be used to take care of the security of the city by observing the crowd as well as individual activities. Much crowd-based crimes like mob lynching and individual crimes like murder, burglary, terrorism can be protected with advanced deep learning-based Anamoly detection techniques. Machine learning model use dataset for learning is taken from different sources specific for crime detection with the 90% accuracy.

show abstract

“…23,24 Sudhakaran and Lanz 7 used convolutional LSTM networks to identify violent behaviors and abnormal events in surveillance videos, and Hanson et al 14 constructed a bidirectional convolutional LSTM architecture to detect violence in long-time sequence data. Peixoto et al 11 applied two deep neural network frameworks to learn the spatiotemporal information in different scenes and then aggregated the spatiotemporal information of different scenes by training a shallow neural network. Singh et al 2 proposed a hybrid deep learning architecture using decentralized networks for detecting violent behaviors in drone videos.…”

Section: Video Violence Detectionmentioning

confidence: 99%

“…8 Wu et al 9 proposed an HL-Net network for multi-modal violence detection based on visual and audio features, and Pang et al 10 focused on exploring methods for fusing visual and audio features instead of concatenating them as input features on HL-Net. Peixoto et al 11 applied visual and auditory features for violence detection in videos and fused them to product-detected outputs. And Reinolds et al 12 proposed audio classifiers and video classifiers with neural networks for real-time violence detection.…”

Section: Introductionmentioning

confidence: 99%

VioNets: efficient multi-modal fusion method based on bidirectional gate recurrent unit and cross-attention graph convolutional network for video violence detection

Liang

Xiao

2023

J. Electron. Imag.

View full text Add to dashboard Cite

.Recent research on video violence detection has made great progress with the development of multi-modal fusion techniques. However, existing approaches still pose huge challenges in real-time violence detection due to fusion features being fixed and not able to be further fine tuned. We aim to address this challenge by exploring the multi-modal fusion method for analyzing multiple modal violent information, i.e., audio, optical flows, and RGB images. We propose a unified network called VioNets, which contains both a cross-attention graph convolutional network (GCN) module and a bidirectional gate recurrent unit (Bi-GRU) module for fusing different modalities of information. First, the cross-attention GCN module is utilized to extract the cross-modal spatial–temporal features. The Bi-GRU module is then applied to accurately capture both past and future context features for each time step of the single-modal features. As a result, the model retains important single-modal information in the extracted features while using the cross-modal features to improve the detection accuracy. Experiments conducted on the XD-Violence dataset show that the proposed method achieves an average precision of 80.59% and an inference time of 0.16 s with 1.82 M parameters.

show abstract

Harnessing high-level concepts, visual, and auditory features for violence detection in videos

Cited by 18 publications

References 12 publications

Higher-Order Thinking Skills Profile of Islamic Boarding School Students on Geometry through the STEM–based Video Approach

Higher-Order Thinking Skills Profile of Islamic Boarding School Students on Geometry through the STEM–based Video Approach

Autonomous Anomaly Detection System for Crime Monitoring and Alert Generation

VioNets: efficient multi-modal fusion method based on bidirectional gate recurrent unit and cross-attention graph convolutional network for video violence detection

Contact Info

Product

Resources

About