SeMP 2019 : First International Workshop on Bridging the Gap between Semantics and Multimedia Processing
Call For Papers
1st International Workshop on Bridging the Gap between
Semantics and Multimedia Processing
Collocated with IEEE ISM 2019
San Diego, CA, USA, December 9-11, 2019
The SeMP 2019 workshop aims to bring together AI research in multimedia that
can contribute to narrow or advance the understanding of the semantic gap
that exists between multimedia signals and the concepts represented by these
signals. This includes not only research that improves on traditional
(symbolic or non-symbolic) AI techniques applied to multimedia, but also
research that combines these techniques in novel, interesting, and
The workshop will provide a forum for researchers to present and discuss new
ideas, work in progress, and preliminary results which can advance the state
of current AI techniques and their interpretability applied to multimedia.
### Topics of interest (not limited to)
* Ontologies for multimedia and multimedia annotation
* Hybrid/integrated representations of multimodal data and semantic
* Concept detection and learning
* Moving object detection, tracking, and description
* Human intention detection and description
* Multimedia understanding and summarization
* Interactive scene description and interpretation
* Probabilistic, non-monotonic reasoning over multimedia descriptions
* Spatiotemporal query and reasoning over multimedia descriptions
* Multi-sensorial and immersive media description
* Real-time stream reasoning over multimedia data
* Content- and concept-based multimedia understanding, modeling, management,
* Connectionist AI applied to multimedia (coding, communication, quality of
* Interpretability of deep-learning models for multimedia processing
### The semantic gap
There is a big representational gap between the audiovisual signals that
compose multimedia objects and the concepts represented by these signals.
One way to narrow this gap, from the concepts side, is through symbolic AI.
One can use logic to describe the multimedia content and then apply symbolic
querying and reasoning to obtain relevant information from these
descriptions. The problem with this purely symbolic approach is that it
does not scale well.
The large volumes of multimedia data generated by current applications
demand efficient methods of concept detection and annotation. This is where
deep learning techniques usually come in—to narrow the gap from the signals
side. Through deep learning one can learn correlations among the training
dataset but overall it is not clear how these correlations map to high level
semantic concepts, which brings many interpretability issues on current deep
learning models. Additional challenges on both sides of the gap are posed by
the diverse, multimodal, imprecise, and uncertain nature of multimedia data.
### Submissions and peer-review
Authors are invited to submit a **4-page** PDF manuscript in English in
double-column IEEE format (the same format adopted by IEEE ISM 2019).
Authors must submit their PDF manuscripts through EasyChair:
At least two independent reviewers will evaluate each paper according to the
suitability of its topic, originality, methodology, and clarity.
Please only submit original material where copyright of all parts is owned
by the authors declared and which is not currently under review elsewhere.
### Important dates
* Submission: October 14, 2019, 23:59 PST
* Camera-ready: October 31, 2019, 23:59 PST
* Workshop: December 9-11, 2019
### Organization and Program committee
* Marcio Ferreira Moreno, IBM Research, Brazil
* Guilherme Lima, IBM Research, Brazil
* Rodrigo Costa, IBM Research, Brazil
* Markus Endler, PUC-Rio, Brazil
* Roberto Azevedo, EPFL, Switzerland
The SeMP 2019 workshop will be collocated with IEEE ISM 2019, which will
take place at the Wyndham San Diego Bay Side in San Diego, CA, USA. See the
IEEE ISM 2019 website for more information on the venue.