Mostra el registre d'ítem simple
Categorizing object-actions relations from semantic scene graphs
dc.contributor.author | Aksoy, Eren Erdal |
dc.contributor.author | Abramov, Alexey |
dc.contributor.author | Wörgötter, Florentin |
dc.contributor.author | Dellen, Babette |
dc.contributor.other | Institut de Robòtica i Informàtica Industrial |
dc.date.accessioned | 2010-11-22T19:06:37Z |
dc.date.available | 2010-11-22T19:06:37Z |
dc.date.created | 2010 |
dc.date.issued | 2010 |
dc.identifier.citation | Aksoy , E. [et al.]. Categorizing object-actions relations from semantic scene graphs. A: IEEE International Conference on Robotics and Automation. "2010 IEEE International Conference on Robotics and Automation". Anchorage: 2010, p. 398-405. |
dc.identifier.uri | http://hdl.handle.net/2117/10367 |
dc.description.abstract | 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. |
dc.format.extent | 8 p. |
dc.language.iso | eng |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Spain |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes |
dc.subject.lcsh | Pattern recognition systems |
dc.subject.other | automation pattern recognition PARAULES CLAU/AUTOR: object-action categorization |
dc.title | Categorizing object-actions relations from semantic scene graphs |
dc.type | Conference report |
dc.subject.lemac | Reconeixement de formes (Informàtica) |
dc.identifier.doi | 10.1109/ROBOT.2010.5509319 |
dc.description.peerreviewed | Peer Reviewed |
dc.subject.inspec | Classificació INSPEC::Pattern recognition::Object recognition |
dc.relation.publisherversion | http://dx.doi.org/10.1109/ROBOT.2010.5509319 |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 3686097 |
dc.description.version | Postprint (published version) |
local.citation.author | Aksoy , E.; Abramov, A.; Wörgötter , F.; Dellen, B. |
local.citation.contributor | IEEE International Conference on Robotics and Automation |
local.citation.pubplace | Anchorage |
local.citation.publicationName | 2010 IEEE International Conference on Robotics and Automation |
local.citation.startingPage | 398 |
local.citation.endingPage | 405 |