000232613 001__ 232613
000232613 005__ 20180913064600.0
000232613 013__ $$d20171102$$bUS$$cA1$$aUS2017316578
000232613 02470 $$2EPO Family ID$$a60156929
000232613 02470 $$a6.1627$$2TTO
000232613 037__ $$aPATENT
000232613 245__ $$aMethod, System and Device for Direct Prediction of 3D Body Poses from Motion Compensated Sequence
000232613 260__ $$c2017
000232613 269__ $$a2017
000232613 336__ $$aPatents
000232613 520__ $$aA method for predicting three-dimensional body poses from image sequences of an object, the method performed on a processor of a computer having memory, the method including the steps of accessing the image sequences from the memory, finding bounding boxes around the object in consecutive frames of the image sequence, compensating motion of the object to form spatio-temporal volumes, and learning a mapping from the spatio-temporal volumes to a three-dimensional body pose in a central frame based on a mapping function.
000232613 700__ $$0240252$$g112366$$aFua, Pascal
000232613 700__ $$0240235$$g149007$$aLepetit, Vincent
000232613 700__ $$0246627$$g222094$$aRozantsev, Artem
000232613 700__ $$0247609$$g211045$$aTekin, Bugra
000232613 909C0 $$0252085$$pTTO$$xU10021
000232613 909C0 $$xU10659$$0252087$$pCVLAB
000232613 909CO $$pIC$$ooai:infoscience.tind.io:232613
000232613 917Z8 $$x112366
000232613 937__ $$aEPFL-PATENT-232613
000232613 973__ $$aEPFL
000232613 980__ $$aPATENT