Şener, FadimeBas, C.Ikizler-Cinbis, N.2016-02-082016-02-0820120302-9743http://hdl.handle.net/11693/28150Date of Conference: October 7-13, 2012Conference name: Conference name: ECCV: European Conference on Computer Vision ECCV 2012. Workshops and DemonstrationsWe propose a multi-cue based approach for recognizing human actions in still images, where relevant object regions are discovered and utilized in a weakly supervised manner. Our approach does not require any explicitly trained object detector or part/attribute annotation. Instead, a multiple instance learning approach is used over sets of object hypotheses in order to represent objects relevant to the actions. We test our method on the extensive Stanford 40 Actions dataset [1] and achieve significant performance gain compared to the state-of-the-art. Our results show that using multiple object hypotheses within multiple instance learning is effective for human action recognition in still images and such an object representation is suitable for using in conjunction with other visual features. © 2012 Springer-Verlag.EnglishData setsHuman actionsHuman-action recognitionMultiple featuresMultiple instance learningMultiple objectsObject detectorsObject regionObject representationsPerformance GainStanfordStill imagesVisual featureGesture recognitionLearning systemsStatistical testsComputer visionConference Paper10.1007/978-3-642-33885-4_2710.1007/978-3-642-33885-4