Filters








330 Hits in 7.0 sec

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

H. Luo, J. Fan, S. Satoh, J. Yang, W. Ribarsky
2008 Signal processing. Image communication  
Second, visual semantic items, such as human faces, text captions, video concepts, are extracted automatically by using our semantic video analysis techniques.  ...  First, automatic keyword extraction is performed on news closed captions and audio channels to detect the most interesting news topics (i.e., keywords for news topic interpretation), and the associations  ...  Department of Homeland Security Program led by Pacific Northwest National Laboratory.  ... 
doi:10.1016/j.image.2008.04.014 fatcat:uvfv6g76kzhfbhx7mosxks3yum

SBS Korea: A fully asset-management based digital news operation in action

Charles Bebert
2006 Journal of Digital Asset Management  
SBS uses Konan Cataloguer for scene change assisted by indexing tools change detection, speech-to-text, detection, face detection, and closed face detection captioning OCR; SBS does not use a  ...  Cataloguer: This is a tool for analyzing video clips and extracting key metadata, such as keyframes, closed captioning and face characters.  ... 
doi:10.1057/palgrave.dam.3640070 fatcat:4auioklinngxjotjx2owgssluq

Spoken content retrieval

Joachim Kohler, Martha Larson, Franciska de Jong, Wessel Kraaij, Roeland Ordelman
2008 SIGIR Forum  
At the workshop, talks and posters were presented covering a wide range of topics including vocabulary independent search, spoken term detection, combination of models/indexes, use of speech recognition  ...  create their own speech search applications or contribute to the indexability of their content.  ...  Davis discussed exploitation of linguistic approaches and integration of information from multiple sources including speech transcripts, closed captions and metadata.  ... 
doi:10.1145/1480506.1480518 fatcat:5bfyxsfrrrckzkjdeqkzpdkmxq

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners [article]

Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Derek Hoiem, Shih-Fu Chang, Mohit Bansal (+1 others)
2022 arXiv   pre-print
Our experiments demonstrate the power of language models in understanding videos on a wide variety of video-language tasks, including video captioning, video question answering, video caption retrieval  ...  The flexibility of prompting allows the model to capture any form of text input, such as automatic speech recognition (ASR) transcripts.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of DARPA, or the U.S.  ... 
arXiv:2205.10747v3 fatcat:rcvyfh2iunhlfi2rlfbp4mqp5y

Automatic person information extraction using overlay text in television news interview videos

Sanghee Lee, Kanghyun Jo
2017 2017 IEEE 15th International Conference on Industrial Informatics (INDIN)  
To make the automatic person indexing of interview video in the TV news program, this paper proposes the method to only detect the name text line among the whole overlay texts in one frame.  ...  Especially, the overlay text in news videos contains concise and direct description of the content. Therefore, it is most reliable clue for constructing a news video indexing system.  ...  As a result, the retrieval system to control effectively and automatically mass the interview videos in the news can be developed.  ... 
doi:10.1109/indin.2017.8104837 dblp:conf/indin/LeeJ17 fatcat:fovbyjlgezhv3jgkimy5rabytu

Multimodal Indexing of Multilingual News Video

Hiranmay Ghosh, Sunil Kumar Kopparapu, Tanushyam Chattopadhyay, Ashish Khare, Sujal Subhash Wattamwar, Amarendra Gorai, Meghna Pandharipande
2010 International Journal of Digital Multimedia Broadcasting  
Further, we focus on a set of techniques for automatic indexing of the news stories based on keywords spotted in speech as well as on the visuals of contemporary and domain interest.  ...  The problems associated with automatic analysis of news telecasts are more severe in a country like India, where there are many national and regional language channels, besides English.  ...  Many American and European channels broadcast transcript of the speech as closed captioned text, which can be used for convenient indexing of the news stream.  ... 
doi:10.1155/2010/486487 fatcat:2y63hlidvvfbxnkfkmkvuu4bv4

A spatial-temporal approach for video caption detection and recognition

Xiaoou Tang, Xinbo Gao, Jianzhuang Liu, Hongjiang Zhang
2002 IEEE Transactions on Neural Networks  
Then employing several new character segmentation and binarization techniques, we improve the Chinese video-caption recognition accuracy from 13% to 86% on a set of news video captions.  ...  Using a novel caption-transition detection scheme we locate both spatial and temporal positions of video captions with high precision and efficiency.  ...  Yang for many constructive comments and the Hong Kong TVB and Asian TV news stations for the news videos.  ... 
doi:10.1109/tnn.2002.1021896 pmid:18244491 fatcat:rg4zg33mzbhlta2i4tx2vrq3ga

Information Retrieval Challenges for Digital Libraries [chapter]

Edie Rasmussen
2004 Lecture Notes in Computer Science  
Much of the current research in information retrieval is potentially relevant to digital libraries, and digital libraries present a challenging environment in which to incorporate new information retrieval  ...  Information retrieval is an important component of digital libraries, and there is a high degree of synergy between the two research communities.  ...  Recent trends include the use of relevance feedback to add information to image documents, and the use of free text captioning, often by users of the collection.  ... 
doi:10.1007/978-3-540-30544-6_10 fatcat:q6ytnrhy5zbljns4idt46td2di

Complex event processing for content-based text, image, and video retrieval

Elizabeth K Bowman, Barbara D Broome, V Melissa Holland, Douglas Summers-Stay, Raghuveer M Rao, John Duselis, Jonathan Howe, Bhopinder K Madahar, Anne-Claire Boury-Brisset, Bruce Forrester, Peter Kwantes, Gertjan Burghouts (+2 others)
2016 2016 International Conference on Military Communications and Information Systems (ICMCIS)  
Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing the burden, to Department of Defense, Washington Headquarters Services  ...  Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any penalty for failing to comply with a collection of information if it does not display a currently  ...  provision of relevant program/project technical information.  ... 
doi:10.1109/icmcis.2016.7496546 fatcat:g4omhjgggfb6zdlskc2564jgam

The Use of Ontology in Retrieval: A Study on Textual, Multilingual and Multimedia Retrieval

Muhammad Nabeel Asim, Muhammad Wasim, Muhammad Usman Ghani Khan, Nasir Mahmood, Waqar Mahmood
2019 IEEE Access  
Ontological information retrieval systems retrieve data based on the similarity of semantics between the user query and the indexed data.  ...  INDEX TERMS Ontology, text retrieval, multimedia retrieval, cross lingual retrieval.  ...  in videos in the form of textual captions, names of performers and location of events etc [118] .  ... 
doi:10.1109/access.2019.2897849 fatcat:ei2zxyxdjndbvgzzue2indwqy4

Open video: A framework for a test collection

Laura Slaughter, Gary Marchionini, Gary Geisler
2000 Journal of Network and Computer Applications  
The future will bring widespread access to large digital libraries of video. Consequently, a great deal of research is focused on methods of browsing and retrieving digital video.  ...  This type of work requires that investigators acquire and digitize video for their studies since the video information retrieval community does not yet have a collection of video for research purposes.  ...  Finally, video retrieval researchers will need to upload results of experiments that themselves include large files (e.g. the results of segmenting or indexing a set of videos).  ... 
doi:10.1006/jnca.2000.0112 fatcat:oq54cwqvdbcrnjcb4ds2nvu5lq

D4.1 Report on Multimodal Machine Translation

Stig-Arne Grönroos, Umut Sulubacak, Jörg Tiedemann
2018 Zenodo  
In MeMAD, multimodal translation is of particular interest in facilitating cross-lingual multimodal content retrieval, and is one of the main focuses of WP4.  ...  Finally, to conclude our report, we discuss our plans of tackling video subtitle and audio description translations as the next steps in WP4.  ...  Acknowledgments This work has been supported by the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 780069, and by the Academy of Finland in the project 313988.  ... 
doi:10.5281/zenodo.3690761 fatcat:n3b34ooubfayxphgyf6bli6bya

A bias-correction for Cramér's and Tschuprow's

Wicher Bergsma
2013 Journal of the Korean Statistical Society  
, Times New Roman, Symbol, or use fonts that look similar. • Number the illustrations according to their sequence in the text.  ...  These will be used instead of standard icons and will personalize the link to your video data. For more detailed instructions please visit our video instruction pages.  ...  You can also check the status of your submitted article or find out when your accepted article will be published.  ... 
doi:10.1016/j.jkss.2012.10.002 fatcat:oom3dkmhtrawbpdbsw2yore6ea

Practical elimination of near-duplicates from web video search

Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
The results of 24 queries in a data set of 12,790 videos retrieved from Google, Yahoo!  ...  This paper outlines ways to cluster and filter out the nearduplicate video using a hierarchical approach. Initial triage is performed using fast signatures derived from color histograms.  ...  It is closely related to the New Event Detection (NED) [4] or First Story Detection (FSD) in Topic Detection and Tracking (TDT) [2] that investigates several aspects for the automatic organization  ... 
doi:10.1145/1291233.1291280 dblp:conf/mm/WuHN07a fatcat:vr6iqrapfvdwdjtqhwk3mrxx3a

Challenges in information retrieval and language modeling

James Allan, David J. Harper, Djoerd Hiemstra, Thomas Hofmann, Eduard Hovy, Wessel Kraaij, John Lafferty, Victor Lavrenko, David Lewis, Liz Liddy, R. Manmatha, Jay Aslam (+24 others)
2003 SIGIR Forum  
The potential use of language modeling techniques in these areas was also discussed. The workshop identified major challenges within each of those areas.  ...  The attendees of the workshop considered information retrieval research in a range of areas chosen to give broad coverage of topic areas that engage information retrieval researchers.  ...  In video, for example, moving images, speech, music, audio, and text (closed captions) can all contribute to effective retrieval.  ... 
doi:10.1145/945546.945549 fatcat:h6xsh2uzwzdfdi4g4ypw6ximrq
« Previous Showing results 1 — 15 out of 330 results