Call for Contributions ICMR 2016

SUBMISSION INSTRUCTIONS

Camera Ready manuscript preparation instructions

Please follow the guidelines on the Sheridan Publication page to prepare the Camera Ready version of your accepted manuscript.

The hard deadline to submit the Camera ready version of the manuscripts is April 26th

Paper Format

All papers must be formatted according to ACM proceedings style. Latex and word templates for this format can be downloaded from the following links:

Latex files (Sample file, Style file, PDF sample file, Bib Sample file and Graph sample file)

Word files

Formatting instructions for other tools

Abstract and Keywords

The abstract and the keywords form the primary source for assigning papers to reviewers. So make sure that they form a concise and complete summary of your paper with sufficient information to let someone who doesn’t read the full paper know what it is about .

Complying with double-blind review (full and short paper only)

In a "Double-blind Review" process, authors should not know the names of the reviewers of their papers, and reviewers should not know the names of the authors. Please prepare your paper in a way that preserves anonymity of the authors.

- Do not put your names under the title.

- Avoid using phrases such as “our previous work” when referring to earlier publications by the authors.

- Remove information that may identify the authors in the acknowledgments (e.g., co-workers and grant IDs).

- Check supplemental material (e.g., titles in the video clips, or supplementary documents) for information that may identify the authors identity.

- Avoid providing links to websites that identify the authors.

Submissions

Submissions should be made through the EasyChair conference website.

Authors take note

The official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to two weeks prior to the first day of your conference. The official publication date affects the deadline for any patent filings related to published work. (For those rare conferences whose proceedings are published in the ACM Digital Library after the conference is over, the official publication date remains the first day of the conference.)

CALL FOR FULL PAPERS

ICMR-2016 is seeking high quality and original papers that address novel problems and explore innovative technical approaches for multimedia retrieval that are of interest to a broad community of multimedia scientists, engineers, practitioners, and students. Of particular interest are contributions that investigate multimedia retrieval in practice including challenges related scale, effectiveness, efficiency, multi-modal integration, user interfaces and multimedia retrieval deployment across a range of industries.

We particularly welcome contributions on the following topics:

Multimedia content extraction, analysis and indexing

Multimedia content-based search and retrieval

Multimedia semantic modeling, taxonomies, ontologies, facets

Multi-modal integration (audio, visual, text, metadata)

Multimedia machine learning, deep learning, neural nets

Relevance feedback, active learning and transfer learning

Audio-visual feature design and evaluation

Multimedia retrieval metrics, data sets and evaluation

Social media, crowdsourcing and tagging

Large-scale multimedia indexing and search

Multimedia analysis/search acceleration: GPU, FPGA, etc.

Solutions: video repositories, smart albums, media sharing, media personalization, content management

Industry applications: medicine, retail, travel, media and entertainment, Web, advertising, fashion, security

Important Dates

Paper Submission: January 29 February 5, 2016 11:59 PM PST

Notification of Acceptance: March 30, 2016

Camera-Ready Papers Due: April 26, 2016

Double-Blind Review

ICMR follows a double-blind review process for full paper selection. Authors should not know the names of the reviewers of their papers, and reviewers should not know the name(s) of the authors. Please prepare your paper in a way that preserves anonymity of the authors.

Abstract and Keywords

The abstract and the keywords form the primary source for assigning papers to reviewers. So make sure that they form a concise and complete summary of your paper with sufficient information to let someone who doesn’t read the full paper know what it is about.

Maximum Length of a Paper

Each full paper should not be longer than 8 pages.

CALL FOR SHORT PAPERS

In addition to full papers, ICMR 2016 is inviting short paper submissions: original contributions incorporating latest results, 4 pages long in ACM format, addressing innovative research in the broad field of multimedia retrieval. Of particular interest are contributions that investigate multimedia retrieval in practice including challenges related scale, effectiveness, efficiency, multi-modal integration, user interfaces and multimedia retrieval deployment across a range of industries.

We particularly welcome contributions on the following topics:

Multimedia content extraction, analysis and indexing

Multimedia content-based search and retrieval

Multimedia semantic modeling, taxonomies, ontologies, facets

Multi-modal integration (audio, visual, text, metadata)

Multimedia machine learning, deep learning, neural nets

Relevance feedback, active learning and transfer learning

Audio-visual feature design and evaluation

Multimedia retrieval metrics, data sets and evaluation

Social media, crowdsourcing and tagging

Large-scale multimedia indexing and search

Multimedia analysis/search acceleration: GPU, FPGA, etc.

Solutions: video repositories, smart albums, media sharing, media personalization, content management

Industry applications: medicine, retail, travel, media and entertainment, Web, advertising, fashion, security

Important Dates

Paper Submission: January 29 February 5, 2016 11:59 PM PST

Notification of Acceptance: March 30, 2016

Camera-Ready Papers Due: April 26, 2016

Double-Blind Review

ICMR follows a double-blind review process for short paper selection. Authors should not know the names of the reviewers of their papers, and reviewers should not know the name(s) of the authors. Please prepare your paper in a way that preserves anonymity of the authors.

Abstract and Keywords

The abstract and the keywords form the primary source for assigning papers to reviewers. So make sure that they form a concise and complete summary of your paper with sufficient information to let someone who doesn’t read the full paper know what it is about.

Maximum Length of a Paper

Each full paper should not be longer than 4 pages.

CALL FOR BRAVE NEW IDEAS PAPERS

In this track we invite visionary papers exploring highly innovative ideas and/or paradigm shifts in conventional theory and practice of multimedia retrieval. Such papers may for example arise from solid mono-disciplinary completely new ways of thinking, interdisciplinary work bringing totally new perspectives on problems or solutions, involve unprecedented scales of data volume, or (strongly encouraged) involve combinations of information channels not pursued before. These papers may not be “complete” in the “traditional” manner in the sense that it may not be possible to have experimental results comparing other related efforts or that they may not have large, publicly available data sets to be used for performance comparison. However, we expect these papers to be visionary by nature.

Any paper submitted to this track should have a cover page indicating why this paper is submitted to this track, referring to the criteria indicated above, and not within the regular ICMR paper track.

Submission Paper Length

Each Brave New Idea paper should be between 4 and 8 pages.

Important Dates

Paper Submission:February 12, 2016 11:59 PM PST

Notification of Acceptance: March 30, 2016

Camera-Ready Papers Due: April 26, 2016

Review Process

ICMR 2016 will use a single-blind review process for brave new idea paper selection. Authors should provide author names and affiliations in their manuscript.

For any questions regarding submissions, please email the Brave New Ideas Chairs

CALL FOR TECHNICAL DEMONSTRATIONS

The Annual ACM International Conference on Multimedia Retrieval (ICMR) offers a great opportunity for exchanging leading-edge multimedia retrieval ideas among researchers, practitioners and other potential users of multimedia retrieval systems. This conference is set up to illuminate the state of the art in multimedia (text, image, video, audio, etc.) retrieval. ICMR 2016 is accepting proposals for technical demonstrators that will be showcased during the conference. The session will include demonstrations of latest innovations by research and engineering groups in industry, academia and government. ICMR 2016 is seeking original high quality submissions addressing innovative research in the broad field of multimedia retrieval, as advertised in the ICMR 2016 general call for papers. A specific preference will be given to solutions of multi-modal, multi-media nature, meaning employing more than one single modality.

We solicit two types of contributions:

1 - Demonstrators with innovative interfaces and visualizations showcasing new opportunities, functionality, or the use of multimedia retrieval in new application domains.

2 - Demonstrations which accompany a research paper presented at the conference to illustrate the potential of the methods presented or providing better understanding of the underlying algorithms. These could also be demonstrators for which the work has been presented before, but with significant interest to the multimedia retrieval field.

Submission Paper Length

Papers must be formatted according to the ACM conference style. Papers of type 1 are allowed a maximum of 4 pages in 9 point font. Papers of type 2 should not exceed 2 pages in 9 point font. In the event of a type 2 submission for which the research paper is rejected but the demo paper is accepted, the authors will be allowed (under shepherding) to extend the demo paper from 2 to 4 pages. While submitting the paper, please make sure that the names and affiliations of the authors are included in the document.

Important Dates

Paper Submission: January 29 February 5, 2016 11:59 PM PST

Notification of Acceptance: March 30, 2016

Camera-Ready Papers Due: April 26, 2016

Review Process

Submissions are not required to be anonymous. The review process for demo submissions will NOT be double-blind. Links to working prototypes and videos showcasing the capabilities of the systems are encouranged with the submission. All demo submissions will be peer-reviewed to ensure maximum quality and accepted demo papers will be included in the conference proceedings. The best demos in each category will be awarded and announced during the Social Event. Short introductory presentations of each demo will be given before the demo session.

Logistics

Once accepted, demonstrators will be provided with a table, poster board, power outlet and wireless (shared) Internet. Demo presenters are expected to bring with themselves everything else needed for their demo, such as hardware, laptops, sensors, PCs, etc. However if you have special requests such as a larger space, special lighting conditions and so on, we will do our best to arrange them..

For any questions regarding submissions, please email the Demonstrations Chairs

DOCTORAL SYMPOSIUM

The ICMR 2016 Doctoral Symposium plans to bring together Ph.D. students working on topics related to multimedia and information retrieval. The Doctoral Symposium will take place during the main conference in oral presentation format. The goal is to provide a forum for Ph.D. students to present ongoing research in a collaborative environment and to share ideas with other renowned and experienced researchers. Participants will discuss their research ideas and results, and they will receive constructive feedback from an audience consisting of peers as well as more senior people. It will be an excellent opportunity for developing person-to-person networks to the benefit of the community and Ph.D. students in their future careers.

Eligibility

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.

Review Process and Publication

Review is single-blind. Selections will be based on a 4 page abstract, singly authored by the student wishing to attend. Submissions will be reviewed by the members of the Doctoral Symposium Committee. Accepted proposals will be published in the proceedings (part of the ACM Digital Library). 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 Symposium will be based solely on the abstract written ad hoc for the event. All abstracts 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 Doctoral Symposium.

Submissions

Applications to the Doctoral Symposium should include a 4-pages abstract summarizing the applicant’s dissertation research. The abstract should include:

- Motivation, 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.

Added to the application, a 1-page appendix should describe the benefits that would be obtained by attending the 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.

Submissions must be written in English and submitted in the ACM Conference style (for LaTeX, use the “Option 2″ style). The paper should be no more than 4 pages in length including all figures and references. The first page must contain the title of the paper, full author name, affiliation and contact details, an abstract of up to 250 words, ACM Computing Reviews categories, and up to 3 keywords describing the topic areas. Information about categories and keywords can be found in the ACM Web pages on the computing classification system and in the LaTeX and Word templates.

Important Dates

Paper Submission:March 4, 2016 11:59 PM PST

Notification of Acceptance: March 30, 2016

Camera-Ready Papers Due: April 26, 2016

SPECIAL SESSION

ICMR 2016 will include a Special Session for innovative and frontier topics in the field of multimedia retrieval. The Special Session will include around 5 papers.

Special Session on Learning with Semantic Information for Large Scale Multimedia Understanding

The explosive growth of visual and textual data, both on the Web and stored in private repositories, has led to urgent requirements in terms of search, processing and management of digital content. Developing optimal solutions to allow access to and mine such data is crucial. For image and video understanding, due to the unconstrained nature of images and videos, and the lack of fully reliable low-level features, the process of image and video understanding can be helped by grounding it with a prior semantic model describing any domain knowledge, which may operate during both learning and inference. An important step for Artificial Intelligence is to bridge the semantic gap between vision and language.

This special session serves as a forum for researchers all over the world to discuss their works and recent advances in learning with semantic information methods and its applications in multimedia analysis. Papers addressing interesting real-world multimedia applications are especially encouraged. Topics of interest include, but are not limited to,

- Cross-media indexing, retrieval and understanding

- Multi-modal multimedia learning

- Text, audio and visual search

- Large scale semantic indexing

- Event detection from multimedia data

- Multimedia applications based upon semantic cues

- Semantics learning with deep learning

- Multimedia quality assessment with semantic information

- Surveys and benchmark datasets related to learning with semantic information

Important Dates

Special session paper submission: January 29 February 5, 2016

Notification of acceptance: March 30, 2016

Camera-ready paper due: April 26, 2016

Organizers

Dr. Yan Yan, Department of Information Engineering and Computer Science, University of Trento, Italy. [email protected]

Dr. Liqiang Nie, National University of Singapore, Singapore. [email protected]

Dr. Luming Zhang, Hefei Institute of Technology, China. [email protected]

GRAND CHALLENGE

Following the tradition of Grand Challenges at ACM Multimedia and Multimedia Retrieval competitions such as the VideOlympics at CIVR, ICMR 2016 will introduce its first edition of grand challenges. Industry leaders are encouraged to organize challenges which are meant to engage the Multimedia Rerieval research community in solving relevant, interesting and challenging questions about the industry’s 3-5 year vision for important retrieval problems of strict multi-modal, multi-media nature. These challenges will provide a fun and engaging framework to provide creative multi-media solutions to challenging real problems affecting the industry today and in the immediate future.

Yahoo! Flickr YFCC100M User Tag and Caption Prediction Challenge

Challenge overview

Full details on the Challenge can be found here .

The members of the Flickr community manually tag photos with the goal of making them searchable and discoverable. With the advent of mobile phone cameras and autouploaders, photo uploads have become more numerous and asynchronous, and manual tagging is cumbersome for most users. Progress has been largely driven by training deep neural networks on datasets, such as ImageNet, that were built by manual annotators. However, acquiring annotations is expensive. In addition, the different categories of annotations are defined by researchers and not by users, which means they are not necessarily relevant to users’ interests, and cannot be directly leveraged to enable search and discovery.

This challenge fills a void that is not currently addressed by existing challenges and is uniquely aligned with the context of multimedia retrieval in two aspects: (1) the dataset contains on the order of 100 million photos, which reflects well the challenges of understanding multimedia at large scale, and (2) the benchmark focuses on usergenerated content, where a large vocabulary of concepts is collected from tags annotated by users.

Submissions should:

Significantly address the challenge posted on the web site.

Depict working, presentable systems or demos, using the grand challenge dataset.

Describe why the system presents a novel and interesting solution.

Submission Guidelines

The submissions (max 4 pages) should be formatted according to ICMR formatting guidelines. Grand Challenge reviewing is double-blind so authors shouldn’t reveal their identity in the paper. The finalists will be selected by a committee consisting of academia and industry representatives, based on novelty, presentation, scientific interest of the approaches, and for the evaluation-based challenges, on the performance against the task.

Accepted submissions will be published in the conference proceedings, and will be presented in a special event during the ICMR 2016 conference. At the conference, finalists will be requested to introduce their solutions, give a quick demo, and take questions from the judges and the audience.

Winners will be selected for Grand Challenge awards based on their presentation.

Challenge Solutions to be submitted to the EasyChair conference website

Important Dates

Grand Challenge paper submission: March 20, 2016

Notification of acceptance: April 1, 2016

Camera-ready paper due: April 26, 2016

WORKSHOPS

The selected ICMR workshops focus on topics relevant to multimedia retrieval theory or practice. Emerging research themes with interests to the multimedia retrieval community are addressed. ICMR workshops will be held at Columbia University in the City of New York.

First International Workshop on Multimedia Analysis and Retrieval for Multimodal Interaction - MARMI 2016

Workshop overview

Full details on the Workshop can be found here .

Important Dates

Workshop Paper Submission Deadline: March 1, 2016

Workshop Paper Notification: March 30, 2016

Camera-ready paper due: April 26, 2016

Workshops Co-chairs

Liangliang Cao ([email protected] ), Yahoo Labs, USA

Yu-Gang Jiang ([email protected]), Fudan University, China.

TUTORIALS PROPOSALS

ICMR 2016 will feature free tutorials on the first day (June 6th, 2016) addressing the broad interests of the multimedia retrieval community.

ICMR tutorials aim to provide a comprehensive overview of specific topics in multimedia retrieval. The topic should be of sufficient relevance with respect to the state-of-the-art and the course should be educational rather than a cursory survey of techniques; hands-on tutorials are highly welcome. The audience for ICMR short courses and tutorials consists primarily of graduate students in multimedia retrieval. Although most courses are half-day offerings, we also invite proposals for full-day courses provided that the topic merits the additional time and can be anticipated to generate sufficient interest from our community.

The proposed tutorial should be linked to the ICMR 2016 topics included in the general call for papers:

Multimedia content extraction, analysis and indexing

Multimedia content-based search and retrieval

Multimedia semantic modeling, taxonomies, ontologies, facets

Multi-modal integration (audio, visual, text, metadata)

Multimedia machine learning, deep learning, neural nets

Relevance feedback, active learning and transfer learning

Audio-visual feature design and evaluation

Multimedia retrieval metrics, data sets and evaluation

Social media, crowdsourcing and tagging

Large-scale multimedia indexing and search

Multimedia analysis/search acceleration: GPU, FPGA, etc.

Solutions: video repositories, smart albums, media sharing, media personalization, content management

Industry applications: medicine, retail, travel, media and entertainment, Web, advertising, fashion, security

Submissions

Proposals should be submitted by email to the Tutorials Chairs, either in plain-text or PDF format. Please include the following information:

- Short course/tutorial title.

- Proposers’ names, titles, affiliations, and primary contact email.

- Short bio for each organizer.

- Preference for half- or full-day event.

- Course description that includes topics that will be covered, along with a brief outline and significant details.

ICMR 2016