This year the first time: Open Source Software Track at ICMR 2017, and the deadline is approaching fast: Jan 27, 2017.
ICMR 2017 is calling for papers presenting significant and innovative open source contributions of researchers and software developers to advance the field of multimedia retrieval by providing the community with implementations of middleware, frameworks, toolkits, libraries, players, authoring tools, and other multimedia software. We strongly believe that making available open source resources significantly advances the field by providing a common set of tools for (i) building upon previous work, (ii) improving multimedia research prototypes and (iii) allowing others to replicate research results more easily.
The Open Source Software Session is a novel part of the ACM ICMR program. To qualify, the software must be provided in a from compliant following the open source definition of the Open Source Initiative:
Open source software is software that can be freely accessed, used, changed, and shared (in modified or unmodified form) by anyone (cp. https://opensource.org/osd).
Open source software is typically available under an open source license, like Apache License 2.0, GPL, LGPL, MIT, etc. In addition submissions must match the topics of ACM ICMR 2017. The scope of the conference includes core topics in multimedia retrieval and recommendation, as well as the broader set of topics that must be addressed to ensure that multimedia retrieval technologies are of practical use in real-world use cases. Special emphasis is placed on topics related to large-scale indexing, user interaction, exploiting diverse and multimodal data, and domain-specific challenges.
Topics of interest include (but are not limited to):
- Multimedia content-based search and retrieval
- Multimedia-content-based (or hybrid) recommender systems
- Large-scale and web-scale multimedia retrieval
- Multimedia content extraction, analysis, and indexing
- Multimedia analytics and knowledge discovery
- Multimedia machine learning, deep learning, and neural nets
- Relevance feedback, active learning, and transfer learning
- Zero-shot learning and fine-grained retrieval for multimedia
- Event-based indexing and multimedia understanding
- Semantic descriptors and novel high- or mid-level features
- Crowdsourcing, community contributions, and social multimedia
- Multimedia retrieval leveraging quality, production cues, style, framing, affect
- Narrative generation and narrative analysis
- User intent and human perception in multimedia retrieval
- Query processing and relevance feedback
- Multimedia browsing, summarization, and visualization
- Multimedia beyond video, including 3D data and sensor data
- Mobile multimedia browsing and search
- Multimedia analysis/search acceleration, e.g., GPU, FPGA
- Benchmarks and evaluation methodologies for multimedia analysis/search
- Applications of multimedia retrieval, e.g., medicine, sports, commerce, lifelogs, travel, security, environment.
Submissions should be done with the ICMR submission system and will be peer reviewed. The paper should include an overview of the open source software package, its description, applications, intended audience, main features, etc. As part of the review process, the build process of the software will be investigated. All source code, license, installation instructions, and other documentation must be available on a public web page or on a publicly available software repository such as GitHub. Make sure to include discussions on possible use, further plans to extend or distribute the software and pointers and summaries of existing applications or demos. Dependencies on non-open source third-party software are discouraged. Accepted papers will be published in the ACM ICMR proceedings and need to be presented in an oral session of the ACM ICMR conference.
Each open source software paper should not be longer than 4 pages.
More information and submission at http://www.icmr2017.ro/call-for-open-source-software-papers.php.