000187534 001__ 187534
000187534 005__ 20181203040016.0
000187534 037__ $$aREP_WORK
000187534 245__ $$aFacial Descriptors for Identity-Preserving Multiple People Tracking
000187534 269__ $$a2013
000187534 260__ $$aLausanne$$c2013
000187534 336__ $$aReports
000187534 520__ $$aIn this report, we show that facial descriptors can be used very effectively in conjunction with a tracklet-based multi-person tracker both to localize and to identify or re-identify people over long sequences. Thus, we can reliably deliver both trajectories and identities in crowded scenes. Furthermore, the whole approach is fast enough to be implemented in real-time. Our key insight is that this can be done even though the faces can only be recognized relatively infrequently.
000187534 6531_ $$aPeople Tracking
000187534 6531_ $$aFacial Recognition
000187534 6531_ $$aIdentification
000187534 6531_ $$aRe-Identification
000187534 700__ $$0(EPFLAUTH)211858$$aZervos, Michail$$g211858
000187534 700__ $$aBenShitrit, Horesh
000187534 700__ $$0240254$$aFleuret, François$$g146262
000187534 700__ $$0240252$$aFua, Pascal$$g112366
000187534 8564_ $$s8554187$$uhttps://infoscience.epfl.ch/record/187534/files/top_1.pdf$$yn/a$$zn/a
000187534 909C0 $$0252087$$pCVLAB$$xU10659
000187534 909CO $$ooai:infoscience.tind.io:187534$$pIC$$preport$$qGLOBAL_SET
000187534 917Z8 $$x112366
000187534 917Z8 $$x112366
000187534 917Z8 $$x112366
000187534 937__ $$aEPFL-REPORT-187534
000187534 973__ $$aEPFL
000187534 980__ $$aREPORT