A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
[article]
2020
arXiv
pre-print
Preserved Fulltext
This sequence is used as the input for a novel asynchronous RNN-like architecture, the Input-filtering Neural ODEs (INODE). This is inspired by the dynamical systems and filtering literature. ...
In this work, we instead propose to directly use events from a DVS camera, a stream of intensity changes and their spatial coordinates. ...
Acknoledgements The authors are grateful to Christian Osendorfer for his valuable input and feedback and to everyone at NNAISENSE for contributing to an inspiring R&D environment. ...
arXiv:2004.03156v1
fatcat:spus7jl5wbhjxkfwio3ce723eq
Deep Sensing of Urban Waterlogging
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The use of an efficient large-scale waterlogging sensing and information system can provide valuable real-time disaster information to facilitate disaster management and enhance awareness of the general ...
The use of a deep sensing system in the monsoon season in Taiwan was demonstrated, and waterlogging events were predicted on the island-wide scale. ...
ACKNOWLEDGMENT We are indebted to Water Resources Agency (WRA) and Directorate General of Highways (DGH) in Taiwan for their video streaming. ...
arXiv:2103.05927v3
fatcat:7y7l2lxnxjez7jtozitvdxxlpu
Deep Sensing of Urban Waterlogging
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The use of an efficient large-scale waterlogging sensing and information system can provide valuable near real-time disaster information to facilitate disaster management and enhance awareness of the general ...
The use of a deep sensing system in the monsoon season in Taiwan was demonstrated, and waterlogging events were predicted on the island-wide scale. ...
ACKNOWLEDGMENT The authors are indebted to Water Resources Agency (WRA) and Directorate General of Highways (DGH) in Taiwan for their video streaming. ...
doi:10.1109/access.2021.3111623
fatcat:vrh3cwtwujcr5pkrsiccqk5sry
Anomaly Detection in Residential Video Surveillance on Edge Devices in IoT Framework
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The experimental results indicate the proposed method is feasible and achieves satisfactory results in real-life scenarios. ...
Therefore, we propose anomaly detection for intelligent surveillance using CPU-only edge devices. A modular framework to capture object-level inferences and tracking is developed. ...
Hardware accelerators like, Movidius Neural Compute Stick (MNCS) are very useful to achieve higher processing speed for real-time applications. ...
arXiv:2107.04767v2
fatcat:xnwbgcxd7zfq7epjx362t7mewi
ReActNet: Temporal Localization of Repetitive Activities in Real-World Videos
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
These distances are computed on frame representations obtained with a convolutional neural network. ...
On top of this representation, we design, implement and evaluate ReActNet, a lightweight convolutional neural network that classifies a given frame as belonging (or not) to a repetitive video segment. ...
From a prac- pose the use of Short Term Fourier Transform (STFT) on
tical point of view, many real-world applications such as the volume of the input video. ...
arXiv:1910.06096v1
fatcat:vkp43gxzpzhyxjiuzfhzbbfyoe
Automated Event Detection and Classification in Soccer: The Potential of Using Multiple Modalities
2021
Machine Learning and Knowledge Extraction
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We also analyze how the tolerance for delays in classification and spotting time, and the tolerance for prediction accuracy, influence the results. ...
Our experiments show that using multiple modalities improves event detection performance for certain types of events. ...
We also acknowledge the use of video data from Norsk Toppfotball (NTF).
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/make3040051
fatcat:zbsxxlp525dfheubyzprpfhyte
A Novel Approach for Robust Multi Human Action Recognition and Summarization based on 3D Convolutional Neural Networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This is followed by an analysis of each sequence to detect and recognize the corresponding actions using 3D convolutional neural networks (3DCNNs). ...
Action-based video summarization is performed by saving each person's action at each time of the video. ...
In addition, the proposed approach can be improved to be used to recognize multiple human actions in real-time. ...
arXiv:1907.11272v4
fatcat:gxg77wheffdqdguo52zhwvkppi
Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
estimation, event analysis, modeling and anomaly detection. ...
This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated ...
Jason Pacheco, Larry Head, and Junsuo Qu from their thoughtful comments on this paper. Special thanks go to Greg Leeming from Intel for his insightful comments and continued support of this project. ...
arXiv:2203.10939v1
fatcat:h4o5zghhhfezncn7luy56yjusm
Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The recent discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications. ...
Furthermore, spike timing plays an important role in information representation, but conventional rate-based spike coding models only consider spike trains statistically, and discard information carried ...
Time Series Classification Our work also shows advantages in time series classification. ...
arXiv:2003.02944v2
fatcat:shl4cvgwjreqzpv3uwbbm3yvna
Communicative Representation Learning on Attributed Molecular Graphs
2020
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Graph neural networks, especially message passing neural network (MPNN) and its variants, have recently made remarkable achievements in molecular graph modeling. ...
Herein, we propose a Communicative Message Passing Neural Network (CMPNN) to improve the molecular embedding by strengthening the message interactions between nodes and edges through a communicative kernel ...
Time Series Classification Our work also shows advantages in time series classification. ...
doi:10.24963/ijcai.2020/388
dblp:conf/ijcai/FangSZQ20
fatcat:bqzmhpw3wfhejaw7ufycm4fatu
Enhanced Accuracy for Multiclass Mental Workload Detection Using Long Short-Term Memory for Brain–Computer Interface
2020
Frontiers in Neuroscience
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Real-time four-level MWL states are assessed using fNIRS system, and initial classification is performed using three strong machine learning (ML) techniques, support vector machine (SVM), k-nearest neighbor ...
The brain activity signals are acquired using functional near-infrared spectroscopy (fNIRS) from the prefrontal cortex (PFC) region of the brain. ...
It is a supervised experiment; participants are observed with a live stream video camera placed in front of them from an adjacent room. ...
doi:10.3389/fnins.2020.00584
pmid:32655353
pmcid:PMC7324788
fatcat:3vfdh5qjmfbx3hlo6a3n3i6pfa
Review on Vehicle Detection Technology for Unmanned Ground Vehicles
2021
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This article firstly introduces commonly used sensors for vehicle detection, lists their application scenarios and compares the strengths and weakness of different sensors. ...
The advantages of the event camera are its high dynamic measurement range, sparse spatio-temporal data flow, short information transmission and processing time [48] , but its image pixel size is small ...
Event Camera An overview of event camera technology can be found in [44] . ...
doi:10.3390/s21041354
pmid:33672976
fatcat:ammlsccxbbhgpkx6r5vod7ciuy
A Review of Object Visual Detection for Intelligent Vehicles
2021
Journal of Informatics Electrical and Electronics Engineering (JIEEE)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Our survey starts with a short presentation on the historical backdrop of profound learning and its agent device, in particular, Convolutional Neural Network (CNN) and region-based convolutional neural ...
Post handling is the real commitment of the review paper for moving item identification issues. ...
The proposed calculation at first takes the video outlines as info individually gauges the normal stream vectors from them which brings about Optical stream vectors. ...
doi:10.54060/jieee/002.02.008
fatcat:lajgh5n76vdavieakskubfczgy
AI and Deep Learning for Urban Computing
[chapter]
2021
The Urban Book Series
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We first introduce the background, followed by listing key challenges from the perspective of computer science when AI techniques are applied. ...
Thus, we briefly introduce the deep-learning models that are widely used in various urban-computing tasks. ...
As the data are usually generated in real-time and new data keep on coming, the characteristic of velocity requires that the new streaming data can be processed in near real time. ...
doi:10.1007/978-981-15-8983-6_43
fatcat:uq7j3hvsvzfl5lq33omx64un3i
Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance
2018
Journal of Sports Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Twelve studies used a deep learning method as a form of Convolutional Neural Network algorithm and one study also adopted a Long Short Term Memory architecture in their model. ...
inputs. ...
Analysis of vision based systems to detect real time goal events
in soccer videos. Applied Artificial Intelligence, 27(7),656-667. ...
doi:10.1080/02640414.2018.1521769
pmid:30307362
fatcat:h3flbavuivbilbo6ekwvmnjg6i
« Previous
Showing results 1 — 15 out of 549 results