"2"^^ . "On-line human action detection using space-time interest points" . . "2011-09-23+02:00"^^ . . "The on-line human action detection is an important task in human-machine interaction and related applications. One of the possible approaches to the detection is exploitation of space-time interest points. Such points are typically identified using feature extractor and then they are processed and classifified. The classifification can be performed using codebooks built based on feature vectors statistics. The individual feature vectors are transformed into bag of words representation using such codebooks and then the code words are classified using SVM. The proposed approach improves the training process and extends the known approaches. The training part of the dataset is split into shorter shots with equal duration and these are annotated and classified using a SVM classifier. This ensures that the time-local motion is captured by the SVM while the longer time behavior is left on further processing mechanisms, such as, e.g. HMMs. In the proposed approach, the output of the SVM classifier is s" . "\u0158ezn\u00ED\u010Dek, Ivo" . "978-80-89557-01-1" . . "Praha" . . "P(7E11024), Z(MSM0021630528)" . . . . "Zborn\u00EDk pr\u00EDspevkov prezentovan\u00FDch na konferencii ITAT, september 2011" . "Faculty of Mathematics and Physics" . "RIV/00216305:26230/11:PU96174" . . "Zem\u010D\u00EDk, Pavel" . . "[0D05AF7E2541]" . "On-line human action detection using space-time interest points"@en . . "218368" . . . "On-line human action detection using space-time interest points" . "7"^^ . "RIV/00216305:26230/11:PU96174!RIV12-MSM-26230___" . . "26230" . . . "space-time interest points SVM classifier bag of words"@en . "2"^^ . . "Hotel Boboty, Vr\u00E1tna Dolina" . "The on-line human action detection is an important task in human-machine interaction and related applications. One of the possible approaches to the detection is exploitation of space-time interest points. Such points are typically identified using feature extractor and then they are processed and classifified. The classifification can be performed using codebooks built based on feature vectors statistics. The individual feature vectors are transformed into bag of words representation using such codebooks and then the code words are classified using SVM. The proposed approach improves the training process and extends the known approaches. The training part of the dataset is split into shorter shots with equal duration and these are annotated and classified using a SVM classifier. This ensures that the time-local motion is captured by the SVM while the longer time behavior is left on further processing mechanisms, such as, e.g. HMMs. In the proposed approach, the output of the SVM classifier is s"@en . "On-line human action detection using space-time interest points"@en . . .