pecial Issue on CVIU
Computer Vision and Image Understanding
an Elsevier Journal
Call for Papers: Special Issue on
Semantic Understanding of Human Behaviours
in Image Sequences
Motivation
During the past decades, important research efforts in computer vision have been focused on developing theories, methods and systems applied to the description of human behaviours in image sequences. Broadly speaking, in the past the main goal was the estimation of quantitative parameters describing where was motion. Nowadays, the focus is on the analysis of image sequences by incorporating cognitive processes which provide interpretation and understanding for detected human motion. That is, the true challenge is the generation of qualitative interpretations of the meaning of motion, therefore describing not only where (and what) motion is being observed, but also understanding why. This goal is becoming a key task in many promising computer-vision applications, such as image and scene understanding; video indexing and retrieval; video surveillance; and advanced human-computer interaction.
So a holistic view on the interpretation and description of human behaviours in image sequences is required, specially focusing on the interactions and collaborations between computer vision researchers and: (i) artificial intelligence techniques for the high-level analysis of human behaviours in human-populated scenarios; (ii) multimedia semantics methods for content-based browsing, indexing and retrieval of human motion detected in image sequences; (iii) computer animation algorithms for graphical-models generation learned/controlled by semantic concepts extracted from image sequences; and (iv) computational linguistics theories for natural-language description and semantic mapping of human motion based on ontologies. Although some interesting works have been done, the semantic understanding of human behaviours in videos remains quite challenging.
Topics
This Special Issue is particularly interested in new advances towards the semantic understanding of human behaviours in image sequences like sports, news, surveillance, documentaries, movie footage or streaming media. We are soliciting original contributions, of leading researchers and practitioners from academia as well as industry, which address a wide range of theoretical and application issues. Original papers to survey the recent progress in this exciting area and highlight potential solutions to common challenging problems are also welcomed. The topics include, but not limited to:
- Cognitive visual surveillance and ambient intelligence
- Object detection, tracking and recognition in image sequences
- High-level behaviour recognition and understanding
- Identification of semantic regions in human-populated scenarios
- Ontologies and semantic annotation of human motion in video content
- Human behaviour analysis: articulated models and animation
- Content-based browsing, efficient indexing and retrieval of behaviour concepts
- Natural-language description of human motion from image sequences
- Learning human models for behaviour synthesis (body/face)
- Learning human motion semantics from multimedia content
Submissions
Submitted articles must not have been previously published and must not be currently submitted for publication elsewhere. Prospective authors are responsible for understanding and adhering to the journal submission guidelines. All submitted papers will be reviewed by at least three independent reviewers. Details of author instructions may be found at the CVIU webpage.
This special issue follows the First ACM International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams(ARTEMIS2010) workshop held in association with ACM Multimedia 2010. Workshop paper authors are encouraged to submit to the Special Issue. However, such submissions must contain significant new material. The Special Issue is also open to those whose work was not presented at the workshop. All manuscripts will undergo the review process that is used for all CVIU submissions.
Important Dates
Full paper due: December 1, 2010
First notification: April 15, 2011
Revised manuscript (for second review) due: June 15, 2011
Acceptance notification: August 15, 2011
Final Manuscript due: September 15, 2011
Publication of the Special Issue: the 1st quarter of 2012
Guest Editors
Jordi Gonzàlez (poal at cvc dot uab dot es)
Dept. Computer Science & Centre de Visió per Computador
Universitat Autònoma de Barcelona
Bellaterra 08193, Barcelona, Catalonia, Spain
Thomas B. Moeslund (tbm at imi dot aau dot dk)
Department of Media Technology
Aalborg University
Niels Jernes Vej 14, 9220 Aalborg East, Denmark
Liang Wang (L.Wang5 at bath dot ac dot uk)
Department of Computer Science
University of Bath
Bath, BA2 7AY, United Kingdom
