Filters








8 Hits in 5.0 sec

[Invited Paper] TRECVid Semantic Indexing of Video: A 6-Year Retrospective

George Awad, Cees G. M. Snoek, Alan F. Smeaton, Georges Quénot
<span title="">2016</span> <i title="Institute of Image Information and Television Engineers"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/grfxe6wamvda5l6autaohwjjue" style="color: black;">ITE Transactions on Media Technology and Applications</a> </i> &nbsp;
As with the previous High-Level Feature detection task which ran from 2002 to 2009, the semantic indexing task aims at evaluating methods and systems for detecting visual, auditory or multi-modal concepts  ...  The Semantic Indexing task has been run at TRECVid from 2010 to 2015 with the support of NIST and the Quaero project.  ...  The authors wish to thank Paul Over from NIST, now retired, for his work in setting up the TRECVid benchmark and for his help in managing the semantic indexing task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3169/mta.4.187">doi:10.3169/mta.4.187</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hcibmza4gzf3naiuvxwop7wgjm">fatcat:hcibmza4gzf3naiuvxwop7wgjm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20181102060258/https://www.jstage.jst.go.jp/article/mta/4/3/4_187/_pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2e/df/2edff452ee0c63b1cc083b1348eb3e2a5202a84f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3169/mta.4.187"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

ARGOS: French evaluation campaign for benchmarking of video content analysis methods

Jenny Benois-Pineau, Philippe Joly, Ewa Kijak, Georges Quénot, Alan Hanjalic, Raimondo Schettini, Nicu Sebe
<span title="2007-01-28">2007</span> <i title="SPIE"> Multimedia Content Access: Algorithms and Systems </i> &nbsp;
This project aims at developing the resources of a benchmark of content analysis methods and algorithms.  ...  The paper describes the type of the evaluated tasks, the way the content set has been produced, metrics and tools developed for the evaluations and results obtained at the end of the first phase.  ...  ACKNOWLEDGEMENTS The authors would like to thanks the persons in charge of the Technovision Program, all the partners (CLIPS, Eurecom, INA, IRIT, LABRI, LIP6, NOVELTIS, and SFRS) who are involved in the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.707939">doi:10.1117/12.707939</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/565uhz3vj5dqpjjtw7xuya2sea">fatcat:565uhz3vj5dqpjjtw7xuya2sea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809115950/http://mrim.imag.fr/publications/2007/QUE07/mcaas07.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d3/1d/d31d705d9aff648186b54acf8ad1e4932e5a2247.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.707939"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

D2.1 Libraries and tools for multimodal content analysis

Doukhan; David, Danny Francis, Benoit Huet, Sami Keronen, Mikko Kurimo, Jorma Laaksonen, Tiina Lindh-Knuutila, Bernard Merialdo, Mats Sjöberg, Umut Sulubacak, Jörg Tiedemann, Kim Viljanen
<span title="2018-12-31">2018</span> <i title="Zenodo"> Zenodo </i> &nbsp;
As part of this deliverable, the open source components have been gathered into a joint software collection of tools and libraries publicly available on GitHub.  ...  These tools have been further improved and developed during the first year of the project.  ...  EURECOM has, in the past few years addressed the issue of movie genre classification as part of a higher-level objective aimed at predicting media interestingness [47, 48] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3697989">doi:10.5281/zenodo.3697989</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bde5x3yggzb2jk2fh2mu6t5wxy">fatcat:bde5x3yggzb2jk2fh2mu6t5wxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306112439/https://zenodo.org/record/3697989/files/D2.1-Libraries_and_tools_for_multimodal_content_analysis.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4f/b5/4fb565b251e4bfb5e588691b03ab33db07f72d8e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3697989"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

The Argos Campaign: Evaluation of Video Analysis Tools

Philippe Joly, Jenny Benois-Pineau, Ewa Kijak, Georges Quenot
<span title="">2007</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4x2ph3aacbhaflopv3sj76tgpq" style="color: black;">2007 International Workshop on Content-Based Multimedia Indexing</a> </i> &nbsp;
The paper describes the type of the evaluated tasks, the way the content set has been produced, metrics and tools developed for the evaluations and some of the results obtained at the end of the first  ...  The Argos evaluation campaign supported by the French Techno-Vision program aimed at developing resources for a benchmarking of video content analysis and indexing methods.  ...  AKNOWLEDGEMENTS The authors would like to thank the persons in charge of the Technovision Program, all the partners (CLIPS, Eurecom, INA, IRIT, LABRI, LIP6, NOVELTIS, and SFRS) who are involved in the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cbmi.2007.385402">doi:10.1109/cbmi.2007.385402</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cbmi/JolyBKQ07.html">dblp:conf/cbmi/JolyBKQ07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bhx5iujaybc3li3q56m3to6jru">fatcat:bhx5iujaybc3li3q56m3to6jru</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190713051130/http://mrim.imag.fr:80/publications/2007/QUE07/cbmi07b.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5a/b0/5ab0ab7da8ef0b22cab63c7234b28ff08db51b84.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cbmi.2007.385402"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

The trecvid 2007 BBC rushes summarization evaluation pilot

Paul Over, Alan F. Smeaton, Philip Kelly
<span title="">2007</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lahlxihmo5fhzpexw7rundu24u" style="color: black;">Proceedings of the international workshop on TRECVID video summarization - TVS &#39;07</a> </i> &nbsp;
This paper provides an overview of a pilot evaluation of video summaries using rushes from several BBC dramatic series. It was carried out under the auspices of TRECVID.  ...  Twenty-two research teams submitted video summaries of up to 4% duration, of 42 individual rushes video files aimed at compressing out redundant and insignificant material.  ...  Ireland under grant number 03/IN.3/I361 and the team at Dublin City University for creating the ground truth, to several sites for mirroring the video data to allow distribution to participating groups  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1290031.1290032">doi:10.1145/1290031.1290032</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mm/OverSK07.html">dblp:conf/mm/OverSK07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yscn3od5rzhrjl3horbrzxpctq">fatcat:yscn3od5rzhrjl3horbrzxpctq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171109053609/https://core.ac.uk/download/pdf/11308290.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/06/cc/06cc6aca114c55c398ab8e9f18c1e0859ac6c937.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1290031.1290032"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

TRECVID 2019: An Evaluation Campaign to Benchmark Video Activity Detection, Video Captioning and Matching, and Video Search Retrieval [article]

George Awad, Asad A. Butt, Keith Curtis, Yooyoung Lee, Jonathan Fiscus, Afzal Godil, Andrew Delgado, Jesse Zhang, Eliot Godard, Lukas Diduch, Alan F. Smeaton, Yvette Graham (+2 others)
<span title="2020-09-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
TRECVID 2019 represented a continuation of four tasks from TRECVID 2018. In total, 27 teams from various research organizations worldwide completed one or more of the following four tasks: 1.  ...  TRECVID has been funded by NIST (National Institute of Standards and Technology) and other US government agencies.  ...  The Video-to-Text work has been partially supported by Science Foundation Ireland (SFI) as a part of the Insight Centre at DCU (12/RC/2289).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09984v1">arXiv:2009.09984v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pmjrd4eyqbgx3gtrvp6l7pa6cq">fatcat:pmjrd4eyqbgx3gtrvp6l7pa6cq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201119011901/https://arxiv.org/pdf/2009.09984v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5f/77/5f77c9680475e543ba1d80e5af023639c0b70781.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09984v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

D2.2 Implementations of methods adapted to enhanced human inputs

Doukhan, Francis, Harrando, Huet, Kaseva, Kurimo, Laaksonen, Lindh-Knuutila, Lisena, Pehlivan Tort, Reboud, Rouhe (+2 others)
<span title="2020-08-20">2020</span> <i title="Zenodo"> Zenodo </i> &nbsp;
Finally, the abstracts of five academic theses together with full texts of ten scientific publications appear at the end of the report.  ...  This deliverable describes the second development iteration of the joint collection of libraries and tools for multimodal content analysis from AALTO, EURECOM, INA, Lingsoft, LLS and Limecraft.  ...  SUN-397 [30] dataset consists of 108,754 images of 397 scene categories.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.4964298">doi:10.5281/zenodo.4964298</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6bbqa7q3xrctnm6nrf5fxh7f3q">fatcat:6bbqa7q3xrctnm6nrf5fxh7f3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210622012805/https://zenodo.org/record/4964299/files/D2.2%20Implementations%20of%20methods%20adapted%20to%20enhanced%20human%20inputs.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c1/05/c105dc9b7d918668ab1dfb2bd2231bb43b3ba118.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.4964298"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Speaker Diarization: A Review of Recent Research

Xavier Anguera Miro, S. Bozonnet, N. Evans, C. Fredouille, G. Friedland, O. Vinyals
<span title="">2012</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/zcz4ey2iwffxtgaodtf5jtebmy" style="color: black;">IEEE Transactions on Audio, Speech, and Language Processing</a> </i> &nbsp;
Over recent years, however, speaker diarization has become an important key technology for many tasks, such as navigation, retrieval, or higher-level inference on audio data.  ...  Speaker diarization is the task of determining "who spoke when?" in an audio or video recording that contains an unknown amount of speech and also an unknown number of speakers.  ...  During the development of this work X.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tasl.2011.2125954">doi:10.1109/tasl.2011.2125954</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/crjuy3f2fff3zdrldbghxqqf3i">fatcat:crjuy3f2fff3zdrldbghxqqf3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20151130022759/http://www1.icsi.berkeley.edu:80/~vinyals/Files/taslp2011a.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3e/e6/3ee6908208e288442b9effa24e6929dba01c2017.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tasl.2011.2125954"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>