0% Complete
فارسی
Home
/
یازدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Vi-Net: A Deep Violent Flow Network for Violence Detection in Video Sequences
Authors :
Tahereh Zarrat Ehsan
1
Seyed Mehdi Mohtavipour
2
1- دانشگاه گیلان
2- دانشگاه علم و صنعت ایران
Keywords :
deep learning, computer vision, convolutional neural network, action detection, violence detection
Abstract :
Video surveillance cameras are widely used due to security concerns. Analyzing these large amounts of videos by a human operator is a difficult and time-consuming job. To overcome this problem, automatic violence detection in video sequences has become an active research area of computer vision in recent years. Early methods focused on hand-engineering approaches to construct hand-crafted features, but they are not discriminative enough for complex actions like violence. To extract complex behavioral features automatically, it is required to apply deep networks. In this paper, we proposed a novel Vi-Net architecture based on the deep Convolutional Neural Network (CNN) to detect actions with abnormal velocity. Motion patterns of targets in the video are estimated by optical flow vectors to train the Vi-Net network. As violent behavior comprises fast movements, these vectors are useful for the extraction of distinctive features. We performed several experiments on Hockey, Crowd, and Movies datasets and results showed that the proposed architecture achieved higher accuracy in comparison with the state-of-the-art methods.
Papers List
List of archived papers
An OWA-Powered Dynamic Customer Churn Modeling in the banking industry Based on Customer Behavioral Vectors
Masoud Alizadeh - Mohammad Soleymannejad - Behzad Moshiri
Challenges of Specification Mining-based Test Oracle for Cyber-Physical Systems
Maryam Raiyat Aliabadi - Dr Mojtaba Vahidi - Dr Ramak Ghavamizadeh
A Model-Driven Approach for Automatic Generation of Android Tourism Applications
Sara Adib - Bahman Zamani
نظرکاوی در سطح مفهوم با استفاده از رویکردی ترکیبی
سیدرضا قادریان خیرآبادی سیدرضا قادریان خیرآبادی -
A Novel Decentralized Privacy Preserving Federated Learning Model for Healthcare Applications
Saba Ameri - Reza Ebrahimi Atani
A New Sentence Ordering Method Using BERT Pretrained Model
Melika Golestanipour - Seyedeh Zahra Razavi - Dr Heshaam Faili
Movable Antenna Design for UAV-Aided Federated Learning via Deep Reinforcement Learning
MOHSEN Ahmadzadeh - Saeid Pakravan - Ghosheh Abed Hodtani
ElectroCNN: Regressive CNN-based Energy Consumption Forecasting Leveraging Weather Data
Dharmi Patel - Mann Patel - Krisha Darji - Rajesh Gupta - Sudeep Tanwar - Jitendra Bhatia - Hossein Shahinzadeh
An efficient hybrid approach for performance-based alternative design evaluation in systems engineering
Abbas Chaman Para - Maryam Nooraei Abadeh - Sondos Bahadori
Architectural Insights: Comparing Weight Stationary and Output Stationary Systolic Arrays for Efficient Computation
Mahdi Kalbasi
more
Samin Hamayesh - Version 41.3.1