Filters








5,765 Hits in 6.1 sec

Optimising video summaries for mobile devices using visual attention modelling

Janko Calic, Neill Campbell
2006 Proceedings of the 2nd international conference on Mobile multimedia communications - MobiMedia '06  
In order to represent large video collections in the form of key-frame summary on small screen devices, this paper exploits methodology of the visual attention modelling and rapid serial visual presentation  ...  The system ranks importance of key-frame regions in the nal layout by exploiting visual attention modelling. A nal layout is created using an optimisation algorithm based on dynamic programming.  ...  The algorithm exploits visual attention modelling and creates visual summaries in an ecient and user centered way.  ... 
doi:10.1145/1374296.1374328 dblp:conf/mobimedia/CalicC06 fatcat:ggxmk6u6hjc3xeokiwtnerrx4q

Compact Visualisation of Video Summaries

Janko Ćalić, Neill W. Campbell
2007 EURASIP Journal on Advances in Signal Processing  
In addition, the system exploits visual attention modelling and rapid serial visual presentation to generate highly compact summaries on mobile devices.  ...  To represent large amounts of information in the form of a video key-frame summary, this paper studies the narrative grammar of comics, and using its universal and intuitive rules, lays out visual summaries  ...  However, in order to produce highly compact summaries for the mobile devices, salient image regions are extracted using a human visual attention model.  ... 
doi:10.1155/2007/19496 fatcat:gfottkm6knfnbi4ajubbmhfovq

Video Summarization Using Highlight Detection and Pairwise Deep Ranking Model

M. Sridevi, Mayuri Kharde
2020 Procedia Computer Science  
With mobile phones and camera enabled devices becoming pervasive and user-friendly, a large number of videos are being shot every day and uploaded to social media and video streaming websites.  ...  This work aims to generate a video summary, by modelling a two stream architecture consisting of deep convolutional neural network in each stream for extracting both spatial and temporal information of  ...  A shortest path algorithm is used to further detect video scenes. Using structure and attention information, video summary can be generated from the temporal graph.  ... 
doi:10.1016/j.procs.2020.03.203 fatcat:n3h32rudx5d7rkm5orazo6hqjy

Edge Intelligence: Architectures, Challenges, and Applications [article]

Dianlei Xu, Tong Li, Yong Li, Xiang Su, Sasu Tarkoma, Tao Jiang, Jon Crowcroft, Pan Hui
2020 arXiv   pre-print
Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence.  ...  We then aim for a systematic classification of the state of the solutions by examining research results and observations for each of the four components and present a taxonomy that includes practical problems  ...  Streiffer et al. appoint an edge server for mobile devices that requests video frame analytics [320] .  ... 
arXiv:2003.12172v2 fatcat:xbrylsvb7bey5idirunacux6pe

Examining Users' Concerns while Using Mobile Learning Apps

Senanu Okuboyejo, Ooreofe Koyejo
2021 International Journal of Interactive Mobile Technologies  
the internet done majorly on mobile handheld devices.  ...  By combining text mining techniques of topic modeling using Latent Dirichlet Algorithm (LDA) and sentiment analysis using Linguistic Inquiry Word Count (LIWC), we analyze these user reviews.  ...  Introduction Smartphones, being a form of handheld devices, have mobile apps that are installable according to user preference; mobile apps are software applications developed for mobile devices.  ... 
doi:10.3991/ijim.v15i15.22345 fatcat:komiqayolrf2hij7mhgg5xyqr4

Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks

Jasper S. Wijnands, Jason Thompson, Kerry A. Nice, Gideon D. P. A. Aschwanden, Mark Stevenson
2019 Neural computing & applications (Print)  
applications on mobile devices.  ...  Drowsiness detection methods have received considerable attention, but few studies have investigated the implementation of a detection approach on a mobile phone.  ...  The authors would like to acknowledge Katherine Scully for her assistance with the literature review, and the anonymous reviewers for their valuable feedback, which helped improve the quality of the original  ... 
doi:10.1007/s00521-019-04506-0 fatcat:77ux3q4edvhoxblmcyzd67nmke

Character index

2011 2011 IEEE International Conference on Multimedia and Expo  
OF ELECTRONIC AND AUDIO BOOKS VIA TTS ALIGNMENT AND SILENCE FILTERING Andrew Perkis VISUAL ATTENTION TUNED SPATIO-VELOCITY CONTRAST SENSITIVITY FOR VIDEO QUALITY ASSESSMENT GESTURE RECOGNITION ON A MOBILE  ...  Wei Jiang AUTOMATIC CONSUMER VIDEO SUMMARIZATION BY AUDIO AND VISUAL ANALYSIS Daniel Gonzalez Jimenez BUILT-IN FACE RECOGNITION FOR SMART PHOTO SHARING IN MOBILE DEVICES Feng Jin AUTOMATIC RESPIRATORY  ... 
doi:10.1109/icme.2011.6011827 fatcat:wjy7yvkmvbbf3hj4wbyjapx5gu

The City Brain: Practice of Large-Scale Artificial Intelligence in the Real World

Xiansheng Hua, xu shen, Jianfeng Zhang, jianqiang huang, Jingyuan Chen, Qin Zhou, Zhihang Fu, Yiru Zhao
2019 IET Smart Cities  
From cognition to optimisation, to decision-making, from search to prediction and ultimately, to intervention, City Brain improves the way to manage the city, as well as the way to live in it.  ...  City Brain is an end-to-end system whose goal is to glean irreplaceable values from big city data, specifically from videos, with the assistance of rapidly evolving artificial intelligence technologies  ...  In the decision and optimisation stage, based on the unified summaries of structured traffic data, intelligence algorithms are adopted for traffic signal optimisation, traffic organisation optimisation  ... 
doi:10.1049/iet-smc.2019.0034 fatcat:45qm7t5qgve7hgyvfzjl7huocq

Inferring Human Knowledgeability from Eye Gaze in Mobile Learning Environments [chapter]

Oya Celiktutan, Yiannis Demiris
2019 Lecture Notes in Computer Science  
camera of mobile devices in contrast to using specialised eye tracking devices.  ...  We focus on a mobile learning scenario where a user and a virtual agent play a quiz game using a hand-held mobile device.  ...  Finally, we optimised the trained model for deployment on mobile devices using Tensorflow Mobile.  ... 
doi:10.1007/978-3-030-11024-6_13 fatcat:siuzpfjqsfd7xhqutmgyrah444

Towards Real-time Drowsiness Detection for Elderly Care [article]

Boris Bačić, Jason Zhang
2020 arXiv   pre-print
To quantify yawning, eyelid and head movement over time, we extracted 3000 images from captured videos for training and testing of deep learning models integrated with OpenCV library.  ...  Visual inspection of head movement from videos with generated 3D coordinate overlays, indicated clear spatiotemporal patterns in collected data (yaw, roll and pitch).  ...  ACKNOWLEDGEMENT We wish to acknowledge contributors to the open source software community including OpenCV documentation and libraries, which were important success factors for us to complete this research  ... 
arXiv:2010.10771v1 fatcat:el56xmydsfevzla2m3zvnx7kcq

MARVEL - D4.1: Optimal audio-visual capturing, analysis and voice anonymisation – initial version

Elfi Fertl
2022 Zenodo  
The second section of the document is about devAIce SDK, a modular technology optimised to work on cross-platforms and contains several AI models such as the Voice Activity Detection (VAD) tool as well  ...  high-end edge devices.  ...  more accurate in-domain data that can be used for re-training the model.  ... 
doi:10.5281/zenodo.5833276 fatcat:nf3cr3jxtrdrliqpjg75r24htu

CollabAR – Investigating the Mediating Role of Mobile AR Interfaces on Co-Located Group Collaboration

Thomas Wells, Steven Houben
2020 Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems  
Using CollabAR, we study collaborative group practices through a range of virtual models with different levels of complexity.  ...  This paper presents a study which examines how a mobile AR (M-AR) interface for inspecting and discovering AR models of varying complexity impacts co-located group practices.  ...  ACKNOWLEDGEMENTS We thank our participants and anonymous reviewers for their comments and feedback on this manuscript.  ... 
doi:10.1145/3313831.3376541 dblp:conf/chi/WellsH20 fatcat:36ia6qedrjdwpamwxbxv4hecta

Handheld devices for applications using dynamic multimedia data

Binh Pham, On Wong
2004 Proceedings of the 2nd international conference on Computer graphics and interactive techniques in Austalasia and Southe East Asia - GRAPHITE '04  
This paper investigates the suitability and constraints of using handheld devices for such applications.  ...  We firstly analyse the capabilities and limitations of current models of handheld devices and advanced features offered by next generation models.  ...  This is already happening as the latest model of mobile phones comes with camera nowadays.  ... 
doi:10.1145/988834.988856 dblp:conf/graphite/PhamW04 fatcat:yhrhp6kecvgfheilz2aphuidaa

A methodology for User Interface adaptation of multi-device broadcast-broadband services

A. Dominguez, J. Florez, A. Lafuente, S. Masneri, I. Tamayo, M. Zorrilla
2020 IEEE Access  
of the screen area w 3 1.2 TABLE 8 . 8 Summary of the use cases USE CASE 1 7 Components Main Programme, Video 1, Video 2, Video 3, Video 4, Dynamic Data, Social 1 Device TV USE CASE 2  ...  Theoretically, model-based UI optimisation refers to the use of combinatorial methods to solve a UI design problem formulated as a search problem by using predictive models of human behaviour and experience  ... 
doi:10.1109/access.2020.3039616 fatcat:v6fui3emzjenhc36keycvdcxk4

MARVEL - D1.3: Architecture definition for MARVEL framework

Dragana Bajovic, Nikola Simic
2021 Zenodo  
Specifications of the architecture to the MARVEL use cases have also been provided together with initial components' customisations.  ...  The purpose of this deliverable is to provide a refined specification of the conceptual architecture for the MARVEL Edge-to-Fog-to-Cloud (E2F2C) ubiquitous computing framework.  ...  achieving good models used on edge devices for inference.  ... 
doi:10.5281/zenodo.5463896 fatcat:ekassky3trcwraipozxsiokwja
« Previous Showing results 1 — 15 out of 5,765 results