1st Workshop

Gavin Gunter News

We are pleased to announce the 1st Workshop on Natural Language Processing in Image Management: Application of Integrated Models (IMNLP 2015).

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 mining such data is crucial. An important part of this is to bridge the semantic gap between vision and language. This, in turn, calls for expertise from two still less connected fields: Computer Vision (CV) and Natural Language Processing (NLP). Research projects that require vision and language integration for a variety of applications go back to the very early days of Artificial Intelligence; significant research in this issue has taken place in the last decade too, with increasing basic research and industrial interest from both computer vision and computational linguistics communities. However, with few exceptions, we still miss joined research by the two research communities, for optimal solution on vision-language integration. With this workshop, we try to bring this issue into focus, welcoming all research activities on the automatic integration of language and vision.

To this end, the main goal of this workshop is to provide a forum for researchers and practitioners from the fields of computer vision, natural
language processing, information retrieval, multimedia, and other related disciplines, where they can constructively explore and discuss the conception and realisation of systems incorporating the afore-mentioned vision-language integration, and its novelties.

Topics of interests:

Topics of interest include, but are not limited to the following themes:

– Integration of text, speech and vision
– Image and video search and retrieval
– Automatic image annotation systems
– Probabilistic models for image annotations
– Semantic-associative visual content labelling and retrieval
– Machine learning approach for vision-language integration
– Multi-modal scene understanding
– BigData Analytics in computer vision and NLP

Important dates:

Paper Submission: April 6th, 2015
Acceptance Notification: May 6, 2015
Camera Ready: May 11, 2015
Author Registration: May 30, 2015

Venue:

The workshop is co-located with WIMS 2015 conference. This means that the workshop will be organized in the same location at the St. Raphael
Resort. For more information about local information, and the conference venue please refer to http://cyprusconferences.org/wims2015/?page_id=292.

Submission:

We solicit papers describing original research combining and integrating natural language processing and computer vision. Papers should be maximum 6 pages in length including references. To encourage the sharing of novel and emerging ideas, we also welcome papers describing new data sets, grand challenges, open problems, benchmarks and work in progress as well as survey papers.

Submission and reviewing will be online, managed by the EasyChair system. Reviewing will be double-blind, and thus no author information should be included in the papers; self-reference should be avoided as well. Papers should be submitted through EasyChair at https://easychair.org/conferences/?conf=imnlp2015.

The only accepted format for all submissions is PDF, and all submissions should adhere to the official ACM SIG proceedings template:
http://www.acm.org/sigs/publications/proceedings-templates

Each submission will be reviewed by at least 3 members of the program committee. Each accepted submission will be presented as a talk or a
poster (to be decided solely based on the nature of the work).

Accepted papers will appear in the WIMS2015 proceedings.

Organization:

The workshop is co-chaired by

– H. Ramampiaro, Norwegian University of Science and Technology, Norway
– N. Pombo, University of Beira Interior, Portugal

All submission will be rigorously evaluated by at least two of the
following members of the technical committee (still under update):

– S. Moens, Katholieke Universiteit Leuven, Belgum
– N. Garcia, University of Beira Interior, Portugal
– D. M. Popovici, Ovidius University of Constanta, Romania
– S. Nikolov, Imagga Technologies Ltd, Bulgaria
– A. Smeaton, Dublin City University, Ireland
– A. Jaimes, Yahoo Labs Barcelona, Spain
– L. Coheur, Instituto Superior Técnico, Portugal
– D. Hogg, University of Leeds, UK
– Y. HaCohen-Kerner, Jerusalem College of Technology, Israel
– Z. Zdravev, University Goce Delcev, Macedonia
– T. Puolakainen, University of Tartu, Estonia
– P. Buitelaar, DERI, National University of Ireland, Ireland
– E. Bruni, Faculty of Computer Science, Italy
– H. Strindberg, Xcerion, Sweeden
– K. Pastra, Cognitive Systems Research Institute, Greece