Important Dates

  • Jan 27, 2020: Deadline for Full / Short / BNI / Special Session Paper Submission

  • Mar 01, 2020: Deadline for Demo / Doctoral Consortium Paper Submission

  • Mar 08, 2020: Notification of Acceptance for Full / Short / BNI / Special Session Paper Papers

  • Mar 12, 2020: Deadline for Workshop Paper Submission

  • Mar 15, 2020: Notification of Acceptance for Demo / Doctoral Consortium Papers

  • Mar 28, 2020: Notification of Acceptance for Workshop Papers

  • Mar 31, 2020: Camera-Ready Conference Papers Due (all papers except workshops)

  • Apr 15, 2020: Camera-Ready Workshop Papers Due

  • Oct 26, 2020: ICMR 2020 Workshops Day

  • Oct 27-29, 2020: ICMR 2020 Main Conference


All papers must be formatted according to the ACM proceedings style. Click on the link to access Latex and Word templates for this format. Please ensure the appropriate length of your submission, namely:

Long research papers, are up to 8 pages, plus additional pages for the list of references. These type of papers will have oral and poster presentations at the conference. Authors of the best papers will be asked to extend their work for a Special Issue in Springer's International Journal of Multimedia Information Retrieval.

Short research papers and demonstrations are up to 4 pages, plus additional pages for the list of references. These type of papers will have only poster presentations at the conference. Papers submitted to a special session or brave new ideas track are limited to six pages per paper, plus references. Doctoral symposium papers are limited to four pages in length. Topics of Interest ICMR 2019 is a premier conference to display scientific achievements and innovative industrial products in the field of multimedia retrieval. We are seeking original high quality submissions addressing innovative research in the field. Contributions addressing the challenges of large-scale search and user behavior analysis are especially welcome.

Topics of Interest

  • Content and context based indexing, search and retrieval of multimedia data

  • Multimodal content analysis and retrieval

  • Deep learning for multimedia retrieval

  • Advanced descriptors and similarity metrics for multimedia data

  • Complex multimedia event detection and recounting

  • Learning and relevance feedback in multimedia retrieval

  • Query models, paradigms, and languages for multimedia retrieval

  • Hashing and indexing algorithms for large-scale retrieval

  • Cross-media retrieval

  • Fine-grained visual search

  • Human perception based multimedia retrieval

  • Studies of information-seeking behavior among image/video users

  • Affective/emotional interaction or interfaces for image/video retrieval

  • HCI issues in multimedia retrieval

  • Crowdsourcing in multimedia retrieval

  • Community-based multimedia content management

  • Internet of multimedia things

  • Image/video summarization and visualization

  • Mobile visual search

  • Applications of multimedia retrieval (Healthcare, Fintech, etc.)

  • Evaluation of multimedia retrieval systems


Demo papers, are up to 4 pages, plus additional pages for the list of references. These type of papers will have demo and poster presentations at the conference. ICMR 2019 is a premier conference to display scientific achievements and innovative industrial products in the field of multimedia retrieval. We are seeking original high quality submissions addressing innovative research in the field. Contributions related to any of the topics of interest mentioned above are welcome.

Please note that the deadlines for demo paper submissions are different to the general paper submissions deadlines and are as follows:

  • Mar 01, 2020. Deadline for Demo Paper Submission

  • Mar 15, 2020. Notification of Acceptance for Demo Papers

  • Mar 31, 2020. Camera-Ready Demo Papers Due

Special Sessions

ACM ICMR 2020 will include four Special Sessions on innovative and frontier topics in the field of multimedia computing and retrieval. Special session papers, which can be invited or submitted, are limited to 6-8 pages. They will supplement the regular research papers and be included in the proceedings of ICMR2020.

The following special sessions have been proposed and accepted for ICMR 2020:

Please note that the deadlines for special paper submissions are the same as general paper submission deadlines.

Brave New Ideas

The Brave New Ideas Track is calling for papers that suggest new opportunities and challenges for multimedia retrieval. A BNI paper is expected to stimulate activity towards addressing new, long term challenges of interest to the multimedia retrieval community. The papers should address topics with a clear potential for high societal impact; authors should be able to argue that their proposal is important to solving problems, to supporting new perspectives, or to providing services that positively impact on people. Note that is not necessary that papers in this track have large-scale experimental results or comparisons to the state of the art, since it is expected that large, publicly available datasets may not be available, and there may be no existing approaches to which the proposed approach in the paper can be compared. BNI papers should be no longer than 9 pages in length, with one additional page for references if needed.

Please note that the deadlines for special paper submissions are the same as general paper submission deadlines.


ACM ICMR 2020 will include five Workshops on innovative and frontier topics in the field of multimedia computing and retrieval. Workshops are half-day or full-day events and are topically related to the topics of interest for ICMR. The purpose of workshops is to provide a platform for presenting novel ideas and research results in a focused and more interactive way. A summary paper of the workshop will be published in the conference proceedings and the workshop papers will be published in the workshop proceedings of ACM ICMR 2020.

The following workshops have been accepted for inclusing in ICMR 2020:

The Third Annual Workshop on the Lifelog Search Challenge (LSC 2020)

The Lifelog Search Challenge (LSC) is a highly interactive and entertaining workshop in which participants compete against each other in an open manner to see who has the best performing lifelog search engine. LSC is a participation workshop, which means that all participants will write and present a paper, as well as taking part in the live interactive search challenge. The live interactive search challenge is open for all ICMR delegates to attend (during the welcome reception) and attendees can even take part as a novice participant in the search challenge. The workshop has an associated six month lifelog dataset gathered by two lifeloggers. This dataset consists of rich multimodal lifelog data (wearable camera images, user activities and locations). The LSC is always an entertaining and challenging event.

Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia (MMArt-ACM 2020)

The MMArt-ACM workshop provides highly interactive venues for researchers in multimedia artworks analysis and attractiveness computing. MMArt focuses on novel contributions to multimedia research related to emerging type of artworks. In addition to conventional art forms like paintings and photos, we will especially encourage contributions that propose new methodologies, novel challenges, and new applications for emerging multimedia artworks such as comics, illustrations, micro films, animation and game, which may be largely available on social media platforms and are associated with user's comments and ratings. ACM is intended to provide a forum for researchers and engineers to present their latest innovations and share their experiences on all aspects of attractiveness computing in multimedia.

Multimedia for Cooking and Eating Activities (CEA2020)

Cooking is one of the most fundamental activities of humankind. Since a cooking activity requires people to manipulate foods, watch their conditions, listen to the sounds, smell the aromas, and taste it, a cooking assistive system should also be capable of handling multiple sensitivities. CEA has been aiming to provide an opportunity for interested research groups to discover each other, introduce their trials, and discuss their status and where they should go. The research community of CEA is truly interdisciplinary, including health science, domestic science, and cultural science. CEA2020 will provide an opportunity for research groups on multimedia concerning cooking and eating activities to discover each other, introduce their trials, and discuss how it should be and where they should go.

Intelligent Cross-Data Analysis and Retrieval (ICDAR 2020)

Currently, people can collect data from themselves and their surrounding environment quickly due to the exponential development of sensors and communication technologies and social networks. The ability to collect such data opens the new opportunity to understand better the association between human beings and the properties of the surrounding environment. The target of the workshop is to attract researchers to work on the intelligent cross-data analysis and retrieval to bring the smart sustainable society to human beings. The domain of the research can vary from wellbeing, disaster prevention and mitigation, mobility, to food computing, to name a few

Please note that the deadlines for workshop paper submissions are different to the general paper submissions deadlines and are as follows:

  • Mar 12, 2020. Deadline for Workshop Paper Submission

  • Mar 28, 2020. Notification of Acceptance for Workshop Papers

  • April 15, 2020. Camera-Ready Workshop Papers Due


ICMR tutorials aim to provide a compre~nsive overview of specific topics in multimedia retrieval. There are two tutoruals accepted for ICMR 2020, based on their relevance with respect to the state-of-the-art the educational potential of the topics. There are two tutorials:

Automation of Deep Learning - Theory and Practice (Martin Wistuba, Ambrish Rawat, Tejaswini Pedapati)

With the advances and success of machine learning technology in solving complex AI problems, the natural step forward lies in building systems that automate the decision steps required for setting up a machine learning pipeline. Traditional approaches for this rely on human expertise and extensive domain knowledge. Tackling this automation is not only crucial for speeding up the deployment of machine learning models, it also helps in expanding the capabilities of models to other challenging scenarios like modelling with limited data or under resource constraints. This tutorial seeks to provide a comprehensive overview of the approaches used in this regard with a focus on Neural Architecture Search (NAS). NAS has been at the forefront of deep learning research over the last few years and has led to the development of a wide range of search algorithms and high performing models. The tutorial is geared towards graduate students, AI researchers, and practitioners, who are interested in automating parts of their machine learning pipelines, want to learn about principles of automated machine and deep learning, and apply those principles to make their own work more effective and less arduous. The attendee will walk away with a broad knowledge of the subject along with many relevant references and guidelines to further explore and choose models for her specific topic of interest.

One Perceptron to Rule Them All: Language, Vision, Audio and Speech (Xavier Giro)

Deep neural networks have boosted the convergence of multimedia data analytics in a unified framework shared by practitioners in natural language, vision and speech. Image captioning, lip reading or video sonorization are some of the first applications of a new and exciting field of research exploiting the generalization properties of deep neural representation. This tutorial will firstly review the basic neural architectures to encode and decode vision, text and audio, to later review the those models that have successfully translated information across modalities.

Doctoral Symposium Submissions

ICMR 2019 doctoral symposium plans to bring together Ph.D. students working on topics aligned with the topics of this year conference. For a full list of topics, see the main conference call for papers. The Ph.D. students of the accepted doctoral symposium papers coming at the conference to present solely their doctoral symposium paper will be entitled to a student registration fee for the entire conference.

Prospective student attendees should already have a clear direction for research, and possibly have published some results. Preference will be given to students who have advanced to Ph.D. candidacy.

Regarding the papers, each doctoral symposium paper should not be longer than 4 pages. ICMR will use a single-blind review process for doctoral symposium paper selection. Authors should provide author names and affiliations in their manuscript. Selections will be based on the submitted 4-page paper, singly authored by the student wishing to attend. Submissions will be reviewed by the doctoral symposium Committee (appointed by the doctoral Symposium Chairs). Accepted proposals will be published in the conference proceedings. Doctoral students who submit to the doctoral symposium are encouraged to submit a paper on their research to the main conference. However, acceptance for participation in the doctoral symposium will be based solely on the paper written ad-hoc for the event. All papers will be reviewed with respect to overall quality of presentation, potential for future impact of the research on the field and expected benefit to the other doctoral students attending the conference.

The submitted paper should include:

  • Abstract and the keywords

  • Motivation and problem description

  • Background and related work (including key references)

  • Novelty and significance relative to the state of the art

  • Approach, data, methods and proposed experiments

  • Results obtained and work in progress

  • Specific research issues for discussion at the doctoral symposium.

In addition to the paper, the applicants are expected to provide a 1 page appendix that should describe the benefits that would be obtained by attending the doctoral symposium, including:

  • A statement by the student saying why they want to attend the Symposium

  • A statement by their advisor saying how the student would benefit by attending the Symposium

  • Advisors should also specifically state whether the student has written, or is close to completing, a thesis proposal (or equivalent) and when they expect the student would defend their dissertation if they progress at a typical rate

The appendix should be uploaded as a separated file.

Guidelines for Reviewers

Thank you for agreeing to review for ICMR 2020. We appreciate your service: your time and effort directly contributes to maintaining the high quality of the conference and strengthening the multimedia information retrieval community.

As a TPC member, we expect that you are already experienced with writing excellent reviews. However, in practice we find that guidelines can help streamline the process. As in the past, ICMR 2020 will be announcing awards for the best reviewers of the conference. The guidelines also serve as a basis for informing the choice of the best reviewers.

The Golden Rule of reviewing: Write a review that you would like to receive yourself. A review should be helpful to the authors, even if the review recommends rejection of the paper. Make sure that you would be happy to put your name on the review if it weren't anonymous.

Best practices for reviewing:

1. Check that the paper falls into the topical scope of ICMR and that it is a multimedia retrieval paper.

  • First, please check if it belongs to a topic-of-interest mentioned by the Calls for Papers

  • Papers submitted to ICMR are expected to address multiple modalities for retrieval. A method solely focusing on text retrieval, for example, would not be considered as a multimedia retrieval paper. The proposed approach/method should combine different modalities, such as visual data with time or text, audio data with text or images, sensor data with images or speech, or any other combination of different modalities.

  • Although many submissions make a technical contribution in the form of a new algorithm, not all do, nor is it a requirement of ICMR. For example, multimedia retrieval also includes user studies, interaction behaviour, presentation of multimedia information, and similar techniques that contribute to multimedia retrieval. Do not give less value to papers that carry out studies of new multimedia retrieval problems because they do not make a novel algorithmic contribution. Instead, judge these papers by the novelty of their insights and the value these insights could have for the community.

2. Support your statements.

  • Reviews should not just state, "It is well known that...", but rather, they should include citations.

  • Reviews should not just state, "Important references are missing...", but rather, they should include examples.

  • Authors appreciate if reviewers are generous with their feedback.

3. Respect the authors.

  • Reviews should critique "the paper", and not the authors.

  • Reviews should not address the authors directly, esp. not as "you". (A direct address can be interpreted as an affront by the reader).

  • Please respect the anonymity of the authors, i.e. do not try to guess who the authors are or proactively try to identify the authors.

4. Please include in your review.

  • Statement of novelty: What does the paper contribute?

  • Related work: Has the related work been covered? Has the paper’s contribution been contextualised with respect to related work?

  • Statement of scientific rigor: Are the experiments well designed? Are they reproducible?

  • Fixes that the authors should make for the camera ready. We can trust the authors to correct minor errors. Major flaws must lead to rejection, since it is not possible to confirm that the authors have actually corrected them successfully (i.e., the paper does not go back to the reviewers).

Policy on arXiv papers:

We consider a "publication" to be a manuscript that has undergone peer review and has been accepted for publication. This means that the following points apply to arXiv papers (and any other papers available online that have not been peer reviewed):

  • If the paper that you are reviewing is available on arXiv, and has not been published elsewhere, it is an acceptable submission to ICMR, since arXiv papers are not peer reviewed and are not publications.

  • Please do not insist that the authors cite a paper that is only on arXiv and has not otherwise been published. Since arXiv papers are not publications, missing an arXiv paper does *not* count as missing related work.

  • Likewise, if the authors do not compare their work with an approach described in an arXiv paper, it does *not* count as a weakness in their experimental evaluation of their own approach.

  • If you know of an interesting arXiv paper relevant to the paper you are reviewing, you are more than welcome to tell the authors about it, but make sure you mark the reference as FYI "for your information" so that the authors know that you do not regard it as missing related work.

If you have any questions about the guidelines, please contact the Technical Program Chairs at

ACM ICMR'20, Dublin, Ireland. 26-29 October 2020