The International Journal of Computer Vision (IJCV) provides a forum for the dissemination of new research results in the rapidly growing field of computer vision. Now publishing 12 issues a year, International Journal of Computer Vision presents high-quality, original contributions to the science and engineering of this rapidly growing field. · Regular articles (up to 25 journal pages) present major technical advances of broad general interest. · Short articles (up to 10 pages) provide a fast publication path for novel research results. · Survey articles (up to 30 pages) offer critical reviews of the state of the art and/or tutorial presentations of pertinent topics. · Book reviews, position papers, and editorials by leading scientific figures will from time to time complement the technical content of the journal. · Additional, on-line material such as still images and video sequences, data sets, and software is encouraged. Papers should cover: · Mathematical, physical and computational aspects of computer vision: image formation, processing, analysis, and interpretation; machine learning techniques; statistical approaches; sensors. · Applications: image-based rendering, computer graphics, robotics, photo interpretation, image retrieval, video analysis and annotation, multi-media, medicine, human-machine interaction, surveillance. · Connections with human perception: computational and architectural aspects of human vision. Editorial Policies · There are no page charges in IJCV. · Papers are published online in advance of print publication. · Responses to position papers are welcome. · Editorials, position papers, and their responses will be available online free of charge. · IJCV has a liberal copyright policy. Academic and industrial researchers in computer vision, robotics, and artificial intelligence, as well as psychologists and neuroscientists interested in the connection between computer and human vision, will find IJCV to be the essential forum for important results in the field. .