Multimedia information processing is a fruitful research topic that has focused in a number of tasks, among them, those focusing on the analysis of human behavior. Although great advances have been obtained in the, so-called, Looking At People field, it is only recently that attention from this area is targeting problems that have to do with more complex behavior. For instance, personality and social behaviors are only starting to be explored from a multimedia information processing perspective. In this context, we are organizing a workshop and an associated contest for ICPR focusing on the analysis of non-obvious human behavior by using multimodal information. The workshop will receive submissions in all aspects of computer vision and pattern recognition for the analysis of personality and human social behaviors, making emphasis on the processing of multimedia information. On the other hand, the contest will run two tracks on the same topic. A first track will focus on information fusion of retrieval results in imagery collected from social networks. A second track will be devoted to develop solutions for recognizing personality traits for users starting from handwritten texts (including text and images). More information on the contest can be found in the following link: http://chalearnlap.cvc.uab.es/challenge/27/description/
Paper submissions are expected from both, contest participants and authors of authors of research papers that fall within the scope of the workshop.
The workshop aims to compile the latest research advances on the analysis of multimodal information for facing problems that are not visually obvious, this is, problems for which the sole visual analysis is insufficient to provide a satisfactory solution. Specifically, two problems are of interest for the workshop: personality analysis and social behavior analysis, although submissions in related topics will be considered as well.
The following are topics of interest for the workshop:
All aspects of human behavior analysis in the context of social networks by using multimodal information. Including but not limited to gesture/action, emotion recognition, personality analysis and human-computer interaction.
Personality analysis from multimodal information. Including textual, visual, and audible information.
Information fusion for the analysis of human behavior in the context of social networks.
Information retrieval, categorization and clustering of social networks data, including images, text, and videos.
Analysis of human intention from social networks data involving multimodal information.
New tasks, data sets and benchmarks on human behavior analysis from multimodal information
Solutions and novel methodologies for approaching the tasks considered in the ICPR18 Multimedia Information Processing for Personality and Social Networks Analysis Contest
Submissions on related topics will be considered as well.
Paper formatting instructions & submission
Accepted papers will be pulblished in Springer LNCS as post proceedings. Authors should follow the instructions from LNCS series for preparing their papers. The papers must not exceed 12 pages, including references.
Please submit your paper in the following link: https://cmt3.research.microsoft.com/MIPPSNA2018
* This is an IAPR endorsed workshop