Action recognition in a high-dimensional feature space [Yüksek boyutlu öznitelik uzayinda hareket tanima]
2013 21st Signal Processing and Communications Applications Conference, SIU 2013
MetadataShow full item record
Please cite this item using this persistent URLhttp://hdl.handle.net/11693/28003
Analyzing and interpreting human actions is an important and challenging area of computer vision. Different solutions are used for representing human actions; we prefer to use spatio-temporal interest points for motion descriptors. Besides, the space-time interest point feature space is considerably high-dimensional and it is hard to eliminate the curse of dimensionality with traditional similarity functions. We apply a matching based approach for high dimensional feature space that matches sequences to classify actions. © 2013 IEEE.
- Conference Paper 2294
Showing items related by title, author, creator and subject.
Double subband occupation of the two-dimensional electron gas in In xAl1 - XN/AlN/GaN/AlN heterostructures with a low indium content (0.064 ≤ x ≤ 0.140) barrier Lisesivdin, S.B.; Tasli P.; Kasap, M.; Ozturk, M.; Arslan, E.; Ozcelik, S.; Ozbay, E. (2010)We present a carrier transport study on low indium content (0.064 ≤ x ≤ 0.140) InxAl1 - xN/AlN/GaN/AlN heterostructures. Experimental Hall data were carried out as a function of temperature (33-300 K) and a magnetic field ...
Naughton, T.J.; Kreis, T.; Onural L.; Ferraro P.; Depeursinge, C.; Emery, Y.; Hennelly, B.M.; Kujawiñska, M. (2009)In digital holography, holograms are usually optically captured and then two-dimensional slices of the reconstruction volume are reconstructed by computer and displayed on a two-dimensional display. When the recording is ...
Khan F.; Delibalta I.; Kozat S.S. (European Signal Processing Conference, EUSIPCO, 2016)We study online sequential logistic regression for churn detection in cellular networks when the feature vectors lie in a high dimensional space on a time varying manifold. We escape the curse of dimensionality by tracking ...