41,327 Hits in 3.3 sec

A Practical Video Digest Generation System Designed for Nursery Schools

Yu Wang, Tomoya Ishikawa, Jien Kato, Kenichiro Ishii, Shigeki Yokoi
2011 IAPR International Workshop on Machine Vision Applications  
One is RDIF log analysis, which quickly picks out videos that expect to have the target kids' appearance.  ...  The other is visual feature analysis, which recognizes events in raw video materials, select video segments for each event and construct the digest.  ...  is hard to define what is a "good digest" for the kid's daily life in nursery school; 3). different with the cooking video or sports video which have some kind of rules, the video of daily life is unconstrained  ... 
dblp:conf/mva/WangIKIY11 fatcat:wgdm6qcjrfa2rlf52r7wf6tnda

A Framework for Review, Annotation, and Classification of Continuous Video in Context [chapter]

Tobias Lensing, Lutz Dickmann, Stéphane Beauregard
2009 Lecture Notes in Computer Science  
Domain-specific approaches and alternative software solutions are referenced, then we briefly outline the concept and realization of our OS X-based software for experimental research on segmentation of  ...  continuous video using sensor context.  ...  A brief state-of-the-art discussion follows that characterizes multi-modal analysis of continuous video in the life-logging domain and references a similar framework suitable for the respective set of  ... 
doi:10.1007/978-3-642-02115-2_28 fatcat:hxksq4rd5nc4xcqc5nc7y6jvg4

A Survey on Recent Advances of Computer Vision Algorithms for Egocentric Video [article]

Sven Bambach
2015 arXiv   pre-print
) video to the mainstream.  ...  detection/recognition, video summarization.  ...  Life Logging Video Another area that is particularly of interest in the ubiquitous computing community and contains egocentric video is the idea of "life logging".  ... 
arXiv:1501.02825v1 fatcat:kkni4ccumbeapn2chqkhpr6frm

Multi-Speaker Video Dialog with Frame-Level Temporal Localization

Qiang Wang, Pin Jiang, Zhiyi Guo, Yahong Han, Zhou Zhao
So multi-speakers video dialogs are more applicable in real life. Besides, speakers always chat about a sub-segment of the long video fragment for a period of time.  ...  The experimental results further demonstrate that MSVD-TL enhances the applicability of video dialog in real life.  ...  L pred = max(0, ρ + log p(v, u, r) − log p(v , u, r)) (16) +max(0, ρ + log p (v, u, r) − log p(v, u , r)) (17) +max(0, ρ + log p(v, u, r) − log p(v, u, r )) (18) where the summation is over all the training  ... 
doi:10.1609/aaai.v34i07.6901 fatcat:3uverxaoureo5cdufahusgpulq

Automated video summarization using speech transcripts

Cuneyt M. Taskiran, Arnon Amir, Dulce B. Ponceleon, Edward J. Delp III, Minerva M. Yeung, Chung-Sheng Li, Rainer W. Lienhart
2001 Storage and Retrieval for Media Databases 2002  
Compact representations of video data can enable efficient video browsing.  ...  Our video summarization approach involves mainly two tasks: first, segmenting the video into small, coherent segments and second, ranking the resulting segments.  ...  Zygmunt Pizlo of the Department of Psychological Sciences of Purdue University for fruitful discussions and advice with regard to the user study.  ... 
doi:10.1117/12.451107 dblp:conf/spieSR/TaskiranAPD02 fatcat:jw4wk75ucneklahnatlmwdiwty

Browsing Audio Life-log Data Using Acoustic and Location Information

Kiichiro Yamano, Katunobu Itou
2009 2009 Third International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies  
of the life-log data.  ...  In this study, experiments were carried out on audio life-log. The audio life-log was divided into segments and clustered by spectrum envelopes according to rooms.  ...  In [5] , life-log videos comprising 1785 images per day are handled. First, the sequences of these images are divided into groups.  ... 
doi:10.1109/ubicomm.2009.57 fatcat:dvcjrxtc65fcxnaffhc5q735oe

Usage-based Summaries of Learning Videos [article]

Hyowon Lee, Mingming Liu, Michael Scriney, Alan F. Smeaton
2021 arXiv   pre-print
From these logs we score to each segment of each video based on the amount of playback it receives from across all students, whether the segment has been re-wound and re-played in the same student session  ...  contribute more to the video segment scores.  ...  by jumping to or repeatedly playing an obscure segment of video.  ... 
arXiv:2106.13504v1 fatcat:vro2cnrigvfvvflkfx72vckleq

Enhanced exploration of oral history archives through processed video and synchronized text transcripts

Michael G. Christel, Scott M. Stevens, Bryan S. Maher, Julieanna Richardson
2010 Proceedings of the international conference on Multimedia - MM '10  
A digital video library of over 900 hours of video and 18000 stories from The HistoryMakers was used by 266 students, faculty, librarians, and life-long learners interacting with a system providing multiple  ...  For life oral histories, an aligned text transcript is valued for both tasks, with the video rated significantly more useful for open-ended tasks over fact-finding.  ...  Special thanks go to CMU students Lee Byron, David Hora, Anna Ly, and Emily Tong who conducted the contextual inquiries and other HCI discount usability techniques informing the development of this work  ... 
doi:10.1145/1873951.1874215 dblp:conf/mm/ChristelSMR10 fatcat:qq7b4rl7frgtll5mgudilfeh4e

Information-theoretic temporal segmentation of video and applications: multiscale keyframes selection and shot boundaries detection

Bruno Janvier, Eric Bruno, Thierry Pun, Stéphane Marchand-Maillet
2006 Multimedia tools and applications  
The first step in the analysis of video content is the partitioning of a long video sequence into short homogeneous temporal segments.  ...  The novelty of our approach is to use color information to partition the video into segments dynamically homogeneous using a criterion inspired by compact coding theory.  ...  Acknowledgements This work is supported by the EU project M4 -Multimodal Meeting Manager and the Swiss National Center of Competence IM2 -Interactive Multimedia Information Management.  ... 
doi:10.1007/s11042-006-0026-2 fatcat:pdnamvsl5jaz3iuuz5kkllhd3m

Unusual Activity Analysis Using Video Epitomes and pLSA

Ayesha Choudhary, Manish Pal, Subhashis Banerjee, Santanu Chaudhury
2008 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing  
We use video epitomes for segmenting foreground objects from background and obtain an approximate shape, trajectory and temporal information in the form of space-time patches.  ...  We also extend pLSA to classify a novel video as usual or unusual.  ...  Figure 1 .Figure 2 . 12 Reconstruction of video from its epitome [3] Result of segmentation performed using video epitomes.  ... 
doi:10.1109/icvgip.2008.89 dblp:conf/icvgip/ChoudharyPBC08 fatcat:o45dpzqasrfudolavwtie3cplu

The Reading-Life Log -- Technologies to Recognize Texts That We Read

Takashi Kimura, Rong Huang, Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi, Koichi Kise
2013 2013 12th International Conference on Document Analysis and Recognition  
Reading life log is a type of techniques to automatically and unconsciously record people's reading intentions, interests and habits.  ...  In this paper, a reading-life log system is implemented by a head-mounted and unobtrusive video camera with a high resolution and a high shutter speed.  ...  OVERVIEW OF READING-LIFE LOG Reading-life log has initiated a lot of interests in the document analysis community due to the additional attention information. Campbell et al.  ... 
doi:10.1109/icdar.2013.26 dblp:conf/icdar/KimuraHUIOK13 fatcat:g5mejccwpnaxja4ogjhvppr23a

The ALFA (Activity Log Files Aggregation) Toolkit: A Method for Precise Observation of the Consultation

Simon de Lusignan, Pushpa Kumarapeli, Tom Chan, Bernhard Pflug, Jeremy van Vlymen, Beryl Jones, George K Freeman
2008 Journal of Medical Internet Research  
rectangle brings up the corresponding video segment Figure 16 : 16 Figure 16: An UML Sequence diagram of a consultation; three life lines represent the doctor, computer and the patient.  ...  -The time-stamp on the multi-channel video screen is then correlated to the UAR log files.  ...  Occurrence graph with video segments Objective To synthesise the consultation observations into an analysable process model of doctorcomputer-patient interactions, with features interpretable by clinical  ... 
doi:10.2196/jmir.1080 pmid:18812313 pmcid:PMC2629369 fatcat:ew6w3jdukndn3i7r3haofy4pny

Video summarization by learning submodular mixtures of objectives

Michael Gygli, Helmut Grabner, Luc Van Gool
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
It should thus be both, interesting and representative for the input video. Previous methods often used simplified assumptions and only optimized for one of these goals.  ...  We present a novel method for summarizing raw, casually captured videos. The objective is to create a short summary that still conveys the story.  ...  Indeed, our experiments show that our method obtains state of the art performance in summarizing hour long life-logging videos [15] , as well as short user videos [9] .  ... 
doi:10.1109/cvpr.2015.7298928 dblp:conf/cvpr/GygliGG15 fatcat:wrq4beltcrhvnernoai45n43aa

2D-to-3D Conversion Based on Motion and Color Mergence

Feng Xu, Guihua Er, Xudong Xie, Qionghai Dai
2008 2008 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video  
By considering the intensity of the estimated motion, we can classify the moving objects.  ...  In this paper, we present an efficient scheme to synthesize stereoscopic video from monoscopic video. We use the improved optical flow method to extract pixel-level motion for each frame.  ...  To minimize ( , ) J f λ , we get an equation set 2 2 1 log (1) log (1) 1 log (2) log (2) ( , ) 2( ) 0.  ... 
doi:10.1109/3dtv.2008.4547844 fatcat:3tysn4t6ivdrrf45d6uikq6loq

CloudMoV: A Mobile Social TV System using Cloud Services

Clarance Angel A, Gokulakisan S, Jaya Surya S, Keerthivasan Asokan, Daya Kanimozhi Rani M
2015 International Journal of Hybrid Information Technology  
users who can interact socially while sharing the video.  ...  The system effectively utilizes both PaaS (Platform-as-a-Service) and IaaS (Infrastructure-asa-Service) cloud services to offer the living-room experience of video watching to a group of disparate mobile  ...  The system also segments the video into multiple 60s segments so that burst size of the video increases.  ... 
doi:10.14257/ijhit.2015.8.3.28 fatcat:dk2fim5wpzf27btjftm23tm5q4
« Previous Showing results 1 — 15 out of 41,327 results