2026-04-05T12:38:40Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/103672026-01-21T05:42:34Zcom_2072_1033col_2072_452950

urn:hdl:2117/10367 Categorizing object-actions relations from semantic scene graphs Aksoy, Eren Erdal Abramov, Alexey Wörgötter, Florentin Dellen, Babette Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes Pattern recognition systems automation pattern recognition PARAULES CLAU/AUTOR: object-action categorization Reconeixement de formes (Informàtica) Classificació INSPEC::Pattern recognition::Object recognition In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene graphs are extracted from image sequences and used to find the characteristic main graphs of the action sequence via an exact graph-matching technique, thus providing an event table of the action scene, which allows extracting objectaction relations. The method is applied to several artificial and real action scenes containing limited context. The central novelty of this approach is that it is model free and needs a priori representation neither for objects nor actions. Essentially actions are recognized without requiring prior object knowledge and objects are categorized solely based on their exhibited role within an action sequence. Thus, this approach is grounded in the affordance principle, which has recently attracted much attention in robotics and provides a way forward for trial and error learning of object-action relations through repeated experimentation. It may therefore be useful for recognition and categorization tasks for example in imitation learning in developmental and cognitive robotics. Peer Reviewed Postprint (published version) 2010 Conference report http://dx.doi.org/10.1109/ROBOT.2010.5509319 http://creativecommons.org/licenses/by-nc-nd/3.0/es/ Restricted access - publisher's policy Attribution-NonCommercial-NoDerivs 3.0 Spain