000125036 001__ 125036
000125036 005__ 20180318102356.0
000125036 037__ $$aCONF
000125036 245__ $$aFast multi-view face tracking with pose estimation
000125036 260__ $$c2008
000125036 269__ $$a2008
000125036 336__ $$aConference Papers
000125036 520__ $$aIn this paper, a fast and an effective multi-view face  tracking algorithm with head pose estimation is introduced.  For modeling the face pose we employ a tree of boosted  classifiers built using either Haar-like filters or Gauss  filters. A first classifier extracts faces of any pose from  the background. Then more specific classifiers discriminate  between different poses. The tree of classifiers is trained  by hierarchically sub-sampling the pose space. Finally,  Condensation algorithm is used for tracking the faces.  Experiments show large improvements in terms of detection  rate and processing speed compared to state-of-the-art  algorithms.
000125036 6531_ $$alts5
000125036 6531_ $$alts
000125036 6531_ $$aface detection
000125036 6531_ $$aface tracking
000125036 6531_ $$ahead pose
000125036 6531_ $$acondensation
000125036 700__ $$aMeynet, Julien
000125036 700__ $$aArsan, Taner
000125036 700__ $$0243039$$aCruz Mota, Javier$$g172622
000125036 700__ $$0240323$$athiran, Jean-Philippe$$g115534
000125036 7112_ $$a16th European Signal Processing Conference$$cLausanne$$dAugust, 2008
000125036 773__ $$tProceeedings of the 16th European Signal Processing Conference
000125036 8564_ $$zURL
000125036 8564_ $$s184462$$uhttps://infoscience.epfl.ch/record/125036/files/face_tracking_mod5.pdf$$yn/a$$zn/a
000125036 909CO $$ooai:infoscience.tind.io:125036$$pconf$$pSTI$$pENAC
000125036 909C0 $$0252123$$pTRANSP-OR$$xU11418
000125036 909C0 $$0252394$$pLTS5$$xU10954
000125036 917Z8 $$x102085
000125036 937__ $$aEPFL-CONF-125036
000125036 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000125036 980__ $$aCONF