2,515 Hits in 4.5 sec


Chang Yun, Philip Trevino, William Holtkamp, Zhigang Deng
2010 Proceedings of the 5th ACM SIGGRAPH Symposium on Video Games - Sandbox '10  
In this paper, we present a novel methodology to improve gaming experiences by automatically adjusting the game difficulty throughout the game play using a Profile-based Adaptive Difficulty System (PADS  ...  Utilizing this profile and a performancebased algorithm, the PADS customizes the game's difficulty levels to accommodate each individual.  ...  Hunicke and Chapman [2004] developed a framework for DDA called Hamlet where a probabilistic method is used to determine when the player needs help.  ... 
doi:10.1145/1836135.1836140 fatcat:wshhaylqpfdzfbpoumrhcwj5b4

Automatic Traffic Abnormality Detection in Traffic Scenes: An Overview

Xiangyang Liu, Mingyu Nie, Shuming Jiang, Zhiqiang Wei, Fengjiao Li
2017 DEStech Transactions on Engineering and Technology Research  
automatic detection technology based on video has become a research focus in the intelligent transportation field.  ...  In recent years, with the continuous improvement of the computer's ability of data processing, and the rapid development of image processing and pattern recognition technology, the traffic information  ...  Reference [47] presents a SIFT-Bag based generative-to discriminative framework for video event recognition in unconstrained news videos.  ... 
doi:10.12783/dtetr/ismii2017/16639 fatcat:s5n256b77rfi3aqi3v7nonuigq

Incorporating Contextual Audio for an Actively Anxious Smart Home

S. Moncrieff, S. Venkatesh, G. West, S. Greenhill
2005 2005 International Conference on Intelligent Sensors, Sensor Networks and Information Processing  
We use the concept of anxiety as a measure of normality modelled with a probabilistic approach. The anxiety is associated with a hazardous device using a fusion of multi-model data.  ...  Consequently, to detect abnormality we model normality, that is, the normal activities associated with a user's interaction with the environment.  ...  CONCLUSION In this paper we have proposed a method for hazard detection in smart environments using a fusion of multi-modal data within an emotive computing framework.  ... 
doi:10.1109/issnip.2005.1595608 fatcat:l5cv3u2d2vaetagerr4zprhpbq

Unusual Event Detection via Multi-camera Video Mining

Hanning Zhou, D. Kimber
2006 18th International Conference on Pattern Recognition (ICPR'06)  
This paper describes a framework for detecting unusual events in surveillance videos.  ...  Our framework combines multiple video streams in the inference level, with a coupled hidden Markov Model (CHMM).  ...  To detect events of such distributed nature, we propose a framework for unusual event detection using multiple surveillance video streams. We first define the term "unusual".  ... 
doi:10.1109/icpr.2006.1149 dblp:conf/icpr/ZhouK06 fatcat:x5jfkoabhva6jcorhffflr4iqy

Spatio-Temporal Adversarial Learning for Detecting Unseen Falls [article]

Shehroz S. Khan, Jacob Nogas, Alex Mihailidis
2020 arXiv   pre-print
To realize such a classifier, we use an adversarial learning framework, which comprises of a spatio-temporal autoencoder for reconstructing input video frames and a spatio-temporal convolution network  ...  In terms of machine learning, it presents a severely class imbalance problem with very few or no training data for falls owing to the fact that falls occur rarely.  ...  This final layer uses a stride of 1 × 1 × 1 and padding. For hidden layers, the activation function f is set to ReLU.  ... 
arXiv:1905.07817v2 fatcat:mf7daegfffcufavcsw7xkzvnli

Understanding vehicular traffic behavior from video: a survey of unsupervised approaches

Brendan Tran Morris, Mohan Manubhai Trivedi
2013 Journal of Electronic Imaging (JEI)  
Recent emerging trends for automatic behavior analysis and understanding from infrastructure video are reviewed.  ...  , and to detect an abnormal event.  ...  The authors would like to thank the reviewers for their useful comments and members of the CVRR laboratory for their support.  ... 
doi:10.1117/1.jei.22.4.041113 fatcat:ftd2elgj5vd4vaada3hxfsfiby

A Bayesian Deep Learning Framework for End-To-End Prediction of Emotion from Heartbeat [article]

Ross Harper, Joshua Southern
2019 arXiv   pre-print
We further propose a Bayesian framework for modelling uncertainty over valence predictions, and describe a procedure for tuning output according to varying demands on confidence.  ...  These results lay the foundation for applications of affective computing in real-world domains such as healthcare, where a high premium is placed on non-invasive collection of data, and predictive certainty  ...  ACKNOWLEDGMENTS The authors would like to thank Nadia Berthouze and Bjrn Schuller for helpful discussions.  ... 
arXiv:1902.03043v1 fatcat:y7iiem4rurgk5cgpfobxbrx27i

Deep Structured Models For Group Activity Recognition [article]

Zhiwei Deng, Mengyao Zhai, Lei Chen, Yuhao Liu, Srikanth Muralidharan, Mehrsan Javan Roshtkhari, Greg Mori
2015 arXiv   pre-print
This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes.  ...  This refinement step mimics a message-passing step similar to inference in a probabilistic graphical model.  ...  In this paper, our main goal is to address the problem of group activity understanding and scene classification in complex surveillance videos using a deep learning framework.  ... 
arXiv:1506.04191v1 fatcat:43bmyn46zbgthliyctn67h2que

A framework for determining overlap in large scale networks

Anton van den Hengel, Henry Detmold, Christopher Madden, Anthony Dick, Alex Cichowski, Rhys Hill
2009 2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC)  
Such a framework is a key enabler for efficient network-wide surveillance, e.g. inter-camera tracking, especially in large surveillance networks.  ...  This paper presents a novel framework designed for calculating the topology of overlapping cameras in large surveillance systems.  ...  Data flow between correlator components and nature of data at each stage of the pipeline, when time padding is enabled for cell system B but not cell system A. Rectangles indicate data.  ... 
doi:10.1109/icdsc.2009.5289363 dblp:conf/icdsc/HengelDMDCH09 fatcat:pt6fxcap6ffrfea3twdpco7cmm

Classifying Behaviours in Videos with Recurrent Neural Networks

Javier Abellan-Abenza, Alberto Garcia-Garcia, Sergiu Oprea, David Ivorra-Piqueres, Jose Garcia-Rodriguez
2017 International Journal of Computer Vision and Image Processing  
To do this, a system is developed where a video is input, and produces as output the possible activities happening in the video.  ...  This article describes how the human activity recognition in videos is a very attractive topic among researchers due to vast possible applications.  ...  Motion recognition is the fundament for detecting human activities or behaviours. Motion is decomposed in a series of poses through time.  ... 
doi:10.4018/ijcvip.2017100101 fatcat:heywstulmnaypikhjcv4q5ravu

A Resource-Efficient CNN-Based Method for Moving Vehicle Detection

Zakaria Charouh, Amal Ezzouhri, Mounir Ghogho, Zouhair Guennoun
2022 Sensors  
Four state-of-the-art CNN-based detection architectures were benchmarked as base models of the detection cores to evaluate the proposed framework.  ...  In this paper, we propose a framework to reduce the complexity of CNN-based AVS methods, where a BS-based module is introduced as a preprocessing step to optimize the number of convolution operations executed  ...  DL for Background Generation In [10] , the authors proposed a deep probabilistic background-modeling framework using an unsupervised deep learning-based autoencoder architecture.  ... 
doi:10.3390/s22031193 pmid:35161938 pmcid:PMC8839159 fatcat:zcr7tiqwprcwlpog3mmw2v4d7a

Anomaly Detection, Localization and Classification for Railway Inspection

Riccardo Gasparini, Andrea D'Eusanio, Guido Borghi, Stefano Pini, Giuseppe Scaglione, Simone Calderara, Eugenio Fedeli, Rita Cucchiara
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Moreover, due to the absolute lack of publiclyreleased datasets collected in the railway context for anomaly detection, we introduce a new multi-modal dataset, acquired from a rail drone, used to evaluate  ...  The ability to detect, localize and classify objects that are anomalies is a challenging task in the computer vision community.  ...  ACKNOWLEDGMENTS We thank Ivan Mazzoni (RFI), Marco Plano (RFI) e Mattia Bevere (RFI) for the technical support.  ... 
doi:10.1109/icpr48806.2021.9412972 fatcat:yqaar54zfjhh3gz63ufy5dgzmy

A Robust Abnormal Behavior Detection Method Using Convolutional Neural Network [chapter]

Nian Chi Tay, Tee Connie, Thian Song Ong, Kah Ong Michael Goh, Pin Shen Teh
2018 Lecture Notes in Electrical Engineering  
For example, people running in a field is considered normal but is deemed abnormal if it takes place in a mall.  ...  range of diverse unusual human activities.  ...  The proposed CNN framework for abnormal behavior detection.  ... 
doi:10.1007/978-981-13-2622-6_4 fatcat:tuisjy4kunawdfuirivut634yu

Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks [article]

Anh Nguyen, Dimitrios Kanoulas, Luca Muratore, Darwin G. Caldwell, Nikos G. Tsagarakis
2017 arXiv   pre-print
We present a new method to translate videos to commands for robotic manipulation using Deep Recurrent Neural Networks (RNN).  ...  Our framework first extracts deep features from the input video frames with a deep Convolutional Neural Networks (CNN).  ...  [10] introduced a framework that represents the continuous human actions as "semantic event chains" and solved the problem as an activity detection task.  ... 
arXiv:1710.00290v1 fatcat:lcyflvhlx5gw3ap5mqqvh3epkq

Federated Dynamic GNN with Secure Aggregation [article]

Meng Jiang and Taeho Jung and Ryan Karl and Tong Zhao
2020 arXiv   pre-print
Given video data from multiple personal devices or street cameras, can we exploit the structural and dynamic information to learn dynamic representation of objects for applications such as distributed  ...  surveillance, without storing data at a central server that leads to a violation of user privacy?  ...  Specifically, this paper addresses the data security issues in the federated learning for the GNN, which is a promising deep learning framework for time-series video datasets.  ... 
arXiv:2009.07351v1 fatcat:7j6bklorfbegdddgqj42lsknwe
« Previous Showing results 1 — 15 out of 2,515 results