[Corpora-List] Call for Papers: ACM Multimedia Workshop on Vision-Language Integration and Multimedia Fusion

Katerina Pastra kpastra at csri.gr
Wed May 11 14:21:49 CEST 2016


Apologies for multiple postings-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- ACMMultimedia 2016 WorkshopVisionand Language Integration Meets Multimedia FusionAmsterdam,The NetherlandsOctober15-16, 2016 http://liir.cs.kuleuven.be/Workshop_iv.html

TheACM Multimedia 2016 and The European Conference on Computer Vision(ECCV 2016) are both taking place in Amsterdam, and intersect on theweekend of October 15 and 16, when the workshop on Vision andLanguage Integration Meets Multimedia Fusion takes place.

Callfor papers Multimodalinformation fusion both at the signal and the semantics levels is acore part in most multimedia applications, including multimediaindexing, retrieval, summarization and others. Early or late fusionof modality-specific processing results has been addressed inmultimedia prototypes since their very early days, through variousmethodologies including rule-based approaches, information-theoreticmodels and machine learning. Vision and Language are two of thepredominant modalities that are being fused and which have attractedspecial attention in international challenges with a long history ofresults, such as TRECVid, ImageClef and others. During the lastdecade, vision-language semantic integration has attracted attentionfrom traditionally non-interdisciplinary research communities, suchas Computer Vision and Natural Language Processing. This is due tothe fact that one modality can greatly assist the processing ofanother providing cues for disambiguation, complementary informationand noise/error filtering. The latest boom of deep learning methodshas opened up new directions in joint modelling of visual andco-occurring verbal information in multimedia discourse. Theaim of the proposed workshop is to bring together the long-standingcommunity of multimedia fusion and search with the emerging,vision-language integration community. This interaction is envisagedto inform all involved on lessons learned and current trends onvision-language fusion for multimedia applications, and oncutting-edge methodologies for joint modelling of visual andco-occurring language information.

Wesolicit papers that comprise original research, review oropinions/positions related (but not limited) to: Modeling:

- Models of vision-language integration/fusion at the signal level

- Models of vision-language integration/fusion at the semantic level

- Reviews of vision-language integration/fusion models

- Reviews of vision-language integration/fusion methodologies

- Reviews of vision-language integration/fusion applications

- Position papers on challenges in vision-language integration/fusion Modellingmethodologies:

- Deep learning methods

- Cognitive modelling

- Distributional semantics

Integrationof the models in multimedia applications:

- Multimedia search, retrieval and question answering

- Multimodal and cross-modal querying and search

- Multimedia annotation and indexing

- Multimedia recommendation

- Multimedia summarization

- Multimodal translation between language and vision

- Human-computer interaction

- Human-robot interaction Coveringdifferent domains, e.g.:

- Cultural heritage

- E-commerce

- Education/learning

- Health

- Social media

Wefocus both on theoretical models for integration and fusion ofmultimodal data and more specifically language and vision data, andon practical applications of these models. Wesolicit full papers describing original research combining andintegrating multimodal processing with a focus on integratinglanguage and vision. Full papers should be 6-8 pages in length plusany number of additional pages containing references only. Inaddition to the long papers to be presented at the workshop, we alsoinvite abstracts for posters to be presented at the workshop's postersession. Abstracts will also be included in the proceedings andshould be up to 2 pages in length including references. In order toencourage the sharing of novel and emerging ideas we also welcomeboth full papers and abstracts describing new data-sets, grandchallenges, open problems, benchmarks and work in progress as well assurveys of models and applications. Allsubmissions must be written in English using the ACM Proceedingstemplates:http://www.acm.org/publications/article-templates/proceedings-template.html/,and submitted electronically in pdf format via the workshop’ssubmission system (EasyChair) found at:https://easychair.org/conferences/?conf=ivlmm2016 Eachsubmission will be reviewed by at least 3 members of the programcommittee. Extended versions of the accepted full papers will beinvited to be published in a special journal issue on integratingvision and language processing. Importantdates

- Deadline for submission of workshop papers and abstracts: 11 July 2016

- Acceptance notification of workshop papers: 2 August 2016

- Camera-ready submission of accepted workshop papers: 16 August 2016

- Workshop: October 15 or October 16, 2016

Organizers Marie-FrancineMoens, KU Leuven, BelgiumKaterinaPastra, Cognitive Systems Research Institute, GreeceKateSaenko, UMass Lowell, USATinneTuytelaars, KU Leuven, Belgium Thisworkshop is part of a series of workshops supported by the EU COSTaction on Integrating Vision and Language: CombiningComputer Vision and Language Processing for Advanced Search,Retrieval, Annotation and Description of Visual Data(iV&L Net:http://www.cost.eu/COST_Actions/ict/IC1307).

 ================================================== Katerina Pastra, PhD Director - Cognitive Systems Research Institute (CSRI)Senior Researcher - Athena Research Center/ILSPVisiting Associate Professor - University of Plymouth/CRNS7 Makedonomachou Prantouna Street, 11525, Athens, Greece tel. +30 211 0124543 (301) http://csri.gr/researchers/katerina-pastra Visit: www.poeticon.eu ================================================== -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 24694 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20160511/a9a8a702/attachment.txt>



More information about the Corpora mailing list