Subject: [AUDITORY] Second Call for Papers: TISMIR Special Collection on Multi-Modal Music Information Retrieval From: Igor Vatolkin <igor.vatolkin@xxxxxxxx> Date: Mon, 17 Jun 2024 19:10:56 +0200This is a multi-part message in MIME format. --------------j8sD7lfAtCFPYLCpl6omBYEY Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: quoted-printable X-MIME-Autoconverted: from 8bit to quoted-printable by edgeum3.it.mcgill.ca id 45HHC2Av116237 Dear list, a reminder: please consider a submission for our TISMIR Special Collection on Multi-Modal Music Information Retrieval. *Deadline for Submissions *01.08.2024* * *Scope of the Special Collection* Data related to and associated with music can be retrieved from a variety= of sources or=20 modalities: audio tracks; digital scores; lyrics; video clips and concert recordings;= artist photos=20 and album covers; expert annotations and reviews; listener social tags from the Internet; a= nd so on.=20 Essentially, the ways humans deal with music are very diverse: we listen to it, read reviews, a= sk friends for recommendations, enjoy visual performances during concerts, dance and per= form rituals, play musical instruments, or rearrange scores. As such, it is hardly surprising that we have discovered multi-modal data= to be so=20 effective in a range of technical tasks that model human experience and expertise. Former stud= ies have already confirmed that music classification scenarios may significantly benefit w= hen several=20 modalities are taken into account. Other works focused on cross-modal analysis, e.g., ge= nerating a=20 missing modality from existing ones or aligning the information between different modaliti= es. The current upswing of disruptive artificial intelligence technologies, d= eep learning, and=20 big data analytics is quickly changing the world we are living in, and inevitably = impacts MIR=20 research as well. Facilitating the ability to learn from very diverse data sources by means= of these=20 powerful approaches may not only bring the solutions to related applications to new levels of= quality,=20 robustness, and efficiency, but will also help to demonstrate and enhance the breadth and= interconnected=20 nature of music science research and the understanding of relationships between dif= ferent kinds of=20 musical data. In this special collection, we invite papers on multi-modal systems in al= l their=20 diversity. We particularly encourage under-explored repertoire, new connections between fields, and = novel research areas. Contributions consisting of pure algorithmic improvements, empirical stud= ies, theoretical=20 discussions, surveys, guidelines for future research, and introductions of new data se= ts are all=20 welcome, as the special collection will not only address multi-modal MIR, but also cover = multi-perspective=20 ideas, developments, and opinions from diverse scientific communities. *Sample Possible Topics* =E2=97=8F State-of-the-art music classification or regression systems whi= ch are based on several modalities =E2=97=8F Deeper analysis of correlation between distinct modalities and = features derived from them =E2=97=8F Presentation of new multi-modal data sets, including the possib= ility of formal analysis and theoretical discussion of practices for constructing better data sets in = future =E2=97=8F Cross-modal analysis, e.g., with the goal of predicting a modal= ity from another one =E2=97=8F Creative and generative AI systems which produce multiple modal= ities =E2=97=8F Explicit analysis of individual drawbacks and advantages of mod= alities for specific MIR=20 tasks =E2=97=8F Approaches for training set selection and augmentation techniqu= es for multi-modal classifier systems =E2=97=8F Applying transfer learning, large language models, and neural a= rchitecture search to multi-modal contexts =E2=97=8F Multi-modal perception, cognition, or neuroscience research =E2=97=8F Multi-objective evaluation of multi-modal MIR systems, e.g., no= t only focusing on the=20 quality, but also on robustness, interpretability, or reduction of the environment= al impact during the training of deep neural networks *Guest Editors* =E2=97=8F Igor Vatolkin (lead) - Akademischer Rat (Assistant Professor) a= t the Department of Computer Science, RWTH Aachen University, Germany =E2=97=8F Mark Gotham - Assistant professor at the Department of Computer= Science, Durham University, UK =E2=97=8F Xiao Hu - Associated professor at the University of Hong Kong =E2=97=8F Cory McKay - Professor of music and humanities at Marianopolis = College, Canada =E2=97=8F Rui Pedro Paiva - Professor at the Department of Informatics En= gineering of the=20 University of Coimbra, Portugal *Submission Guidelines* Please, submit through https://transactions.ismir.net, and note in your c= over letter that=20 your paper is intended to be part of this Special Collection on Multi-Modal MIR. Submissions should adhere to formatting guidelines of the TISMIR journal: https://transactions.ismir.net/about/submissions/. Specifically, articles= must not be=20 longer than 8,000 words in length, including referencing, citation and notes. Please also note that if the paper extends or combines the authors' previ= ously published=20 research, it is expected that there is a significant novel contribution in the submiss= ion (as a rule of=20 thumb, we would expect at least 50% of the underlying work - the ideas, concepts, m= ethods, results,=20 analysis and discussion - to be new). In case you are considering submitting to this special issue, it would gr= eatly help our=20 planning if you let us know by replying to igor.vatolkin@xxxxxxxx Kind regards, Igor Vatolkin on behalf of the TISMIR editorial board and the guest editors --=20 Dr. Igor Vatolkin Akademischer Rat Department of Computer Science Chair for AI Methodology (AIM) RWTH Aachen University Theaterstrasse 35-39, 52062 Aachen Mail:igor.vatolkin@xxxxxxxx Skype: igor.vatolkin https://www.aim.rwth-aachen.de https://sig-ma.de https://de.linkedin.com/in/igor-vatolkin-881aa78 https://scholar.google.de/citations?user=3Dp3LkVhcAAAAJ https://ls11-www.cs.tu-dortmund.de/staff/vatolkin --------------j8sD7lfAtCFPYLCpl6omBYEY Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-MIME-Autoconverted: from 8bit to quoted-printable by edgeum3.it.mcgill.ca id 45HHC2Av116237 <html> <head> <meta http-equiv=3D"content-type" content=3D"text/html; charset=3DUTF= -8"> </head> <body> <div class=3D"moz-forward-container">Dear list,<br> <p>a reminder: please consider a submission for our <br> TISMIR Special Collection on Multi-Modal Music Information Retrieval.<br> </p> <p><b>Deadline for Submissions<br> </b>01.08.2024<b><br> </b></p> <p><b>Scope of the Special Collection</b><br> Data related to and associated with music can be retrieved from a variety of sources or modalities:<br> audio tracks; digital scores; lyrics; video clips and concert recordings; artist photos and album covers;<br> expert annotations and reviews; listener social tags from the Internet; and so on. Essentially, the ways<br> humans deal with music are very diverse: we listen to it, read reviews, ask friends for<br> recommendations, enjoy visual performances during concerts, dance and perform rituals, play<br> musical instruments, or rearrange scores.</p> <p>As such, it is hardly surprising that we have discovered multi-modal data to be so effective in a range<br> of technical tasks that model human experience and expertise. Former studies have already<br> confirmed that music classification scenarios may significantly benefit when several modalities are<br> taken into account. Other works focused on cross-modal analysis, e.g., generating a missing modality<br> from existing ones or aligning the information between different modalities.</p> <p>The current upswing of disruptive artificial intelligence technologies, deep learning, and big data<br> analytics is quickly changing the world we are living in, and inevitably impacts MIR research as well.<br> Facilitating the ability to learn from very diverse data sources by means of these powerful approaches<br> may not only bring the solutions to related applications to new levels of quality, robustness, and<br> efficiency, but will also help to demonstrate and enhance the breadth and interconnected nature of<br> music science research and the understanding of relationships between different kinds of musical<br> data.</p> <p>In this special collection, we invite papers on multi-modal systems in all their diversity. We particularly<br> encourage under-explored repertoire, new connections between fields, and novel research areas.<br> Contributions consisting of pure algorithmic improvements, empirical studies, theoretical discussions,<br> surveys, guidelines for future research, and introductions of new data sets are all welcome, as the<br> special collection will not only address multi-modal MIR, but also cover multi-perspective ideas,<br> developments, and opinions from diverse scientific communities.</= p> <p><b>Sample Possible Topics</b><br> =E2=97=8F State-of-the-art music classification or regression sys= tems which are based on several<br> modalities<br> =E2=97=8F Deeper analysis of correlation between distinct modalit= ies and features derived from them<br> =E2=97=8F Presentation of new multi-modal data sets, including th= e possibility of formal analysis and<br> theoretical discussion of practices for constructing better data sets in future<br> =E2=97=8F Cross-modal analysis, e.g., with the goal of predicting= a modality from another one<br> =E2=97=8F Creative and generative AI systems which produce multip= le modalities<br> =E2=97=8F Explicit analysis of individual drawbacks and advantage= s of modalities for specific MIR tasks<br> =E2=97=8F Approaches for training set selection and augmentation techniques for multi-modal classifier<br> systems<br> =E2=97=8F Applying transfer learning, large language models, and = neural architecture search to<br> multi-modal contexts<br> =E2=97=8F Multi-modal perception, cognition, or neuroscience rese= arch<br> =E2=97=8F Multi-objective evaluation of multi-modal MIR systems, = e.g., not only focusing on the quality,<br> but also on robustness, interpretability, or reduction of the environmental impact during the<br> training of deep neural networks</p> <p><b>Guest Editors</b><br> =E2=97=8F Igor Vatolkin (lead) - Akademischer Rat (Assistant Prof= essor) at the Department of Computer<br> Science, RWTH Aachen University, Germany<br> =E2=97=8F Mark Gotham - Assistant professor at the Department of Computer Science, Durham<br> University, UK<br> =E2=97=8F Xiao Hu - Associated professor at the University of Hon= g Kong<br> =E2=97=8F Cory McKay - Professor of music and humanities at Maria= nopolis College, Canada<br> =E2=97=8F Rui Pedro Paiva - Professor at the Department of Inform= atics Engineering of the University of<br> Coimbra, Portugal</p> <p><b>Submission Guidelines</b><br> Please, submit through <a class=3D"moz-txt-link-freetext" href=3D"https://transactions.ismir.net" moz-do-not-send=3D"true= ">https://transactions.ismir.net</a>, and note in your cover letter that your paper is<br> intended to be part of this Special Collection on Multi-Modal MIR.<br> Submissions should adhere to formatting guidelines of the TISMIR journal:<br> <a class=3D"moz-txt-link-freetext" href=3D"https://transactions.ismir.net/about/submissions/" moz-do-not-send=3D"true">https://transactions.ismir.net/about/s= ubmissions/</a>. Specifically, articles must not be longer than<br> 8,000 words in length, including referencing, citation and notes.</p> <p>Please also note that if the paper extends or combines the authors' previously published research, it<br> is expected that there is a significant novel contribution in the submission (as a rule of thumb, we<br> would expect at least 50% of the underlying work - the ideas, concepts, methods, results, analysis and<br> discussion - to be new).</p> <p>In case you are considering submitting to this special issue, it would greatly help our planning if you<br> let us know by replying to <a class=3D"moz-txt-link-abbreviated moz-txt-link-freetext" href=3D"mailto:igor.vatolkin@xxxxxxxx" moz-do-not-send=3D"true">igor.vatolkin@xxxxxxxx</a>.<br> </p> <p>Kind regards,<br> Igor Vatolkin<br> on behalf of the TISMIR editorial board and the guest editors </p= > <pre class=3D"moz-signature" cols=3D"90">--=20 Dr. Igor Vatolkin Akademischer Rat Department of Computer Science Chair for AI Methodology (AIM) RWTH Aachen University Theaterstrasse 35-39, 52062 Aachen Mail: <a class=3D"moz-txt-link-abbreviated moz-txt-link-freetext" href=3D= "mailto:igor.vatolkin@xxxxxxxx" moz-do-not-send=3D"true">igor.vatol= kin@xxxxxxxx</a> Skype: igor.vatolkin <a class=3D"moz-txt-link-freetext" href=3D"https://www.aim.rwth-aachen.de= " moz-do-not-send=3D"true">https://www.aim.rwth-aachen.de</a> <a class=3D"moz-txt-link-freetext" href=3D"https://sig-ma.de" moz-do-not-= send=3D"true">https://sig-ma.de</a> <a class=3D"moz-txt-link-freetext" href=3D"https://de.linkedin.com/in/igo= r-vatolkin-881aa78" moz-do-not-send=3D"true">https://de.linkedin.com/in/i= gor-vatolkin-881aa78</a> <a class=3D"moz-txt-link-freetext" href=3D"https://scholar.google.de/cita= tions?user=3Dp3LkVhcAAAAJ" moz-do-not-send=3D"true">https://scholar.googl= e.de/citations?user=3Dp3LkVhcAAAAJ</a> <a class=3D"moz-txt-link-freetext" href=3D"https://ls11-www.cs.tu-dortmun= d.de/staff/vatolkin" moz-do-not-send=3D"true">https://ls11-www.cs.tu-dort= mund.de/staff/vatolkin</a></pre> </div> </body> </html> --------------j8sD7lfAtCFPYLCpl6omBYEY--