İşcen, AhmetDuygulu, Pınar2016-02-082016-02-082013-10http://hdl.handle.net/11693/28025Date of Conference: 21-21 October, 2013Conference name: CEA '13 Proceedings of the 5th international workshop on Multimedia for cooking & eating activitiesIn this paper, we introduce a model to classify cooking activities using their visual and temporal coherence information. We fuse multiple feature descriptors for fine-grained activity recognition as we would need every single detail to catch even subtle differences between classes with low inter-class variance. Considering the observation that daily activities such as cooking are likely to be performed in sequential patterns of activities, we also model temporal coherence of activities. By combining both aspects, we show that we can improve the overall accuracy of cooking recognition tasks. © Copyright 2013 ACM.EnglishAction recognitionActivity recognitionCooking activitiesImage recognitionActivity sequenceDaily activityMultiple feature descriptorsOverall accuraciesSequential patternsTemporal coherenceMotion estimationConference Paper10.1145/2506023.2506025