432:
118:, and has published more than 80 journal papers, 200 conference papers, with over 34,000 citations and his h-index is 88. In addition, he holds 103 patents to his name which include Visual tracking in video images in unconstrained environments by exploiting on-the-fly context using supporters and distracters and
243:
Medioni established Tensor Voting, an approach to a wide range of problems in computer vision and machine learning that is non-parametric, data-driven, local, and requires a minimal number of assumptions. The tensor voting framework provided a unified perceptual organization methodology applicable to
181:
Following his Ph.D., in 1983, Medioni began his academic career as a research associate professor in the
Department of Computer Science and Electrical Engineering at the University of Southern California. He was subsequently promoted, becoming an assistant professor in 1987, an associate professor in
208:
Medioni's research spans the field of image understanding, focusing on fundamental issues of representation, matching, and recognition. He has also been interested in designing and implementing highly reliable vision systems capable of tackling challenging tasks, even when constructed from imperfect
270:
Medioni has also worked on face modeling and introduced a technique for building human face models by using only two photographs. Through collaborative research efforts he proposed a 3D face modeling and recognition system and a method to produce 3D face models in laser scan quality. Moreover, he
217:
Medioni introduced the Just Walk Out technology (JWO) which is a new shopping experience for customers. The data captured by a bank of cameras and other sensors in the store is processed in real-time to solve the "who took what" problem for every customer. It achieved a high level of accuracy in
279:
Medioni has also worked on face recognition technology. He proposed domain-specific data augmentation as a more accessible way to improve face recognition, achieving performance similar to systems using large datasets. Additionally, he introduced Pose-Aware Models (PAMs) for unconstrained face
234:
As an advisory board member and technical consultant, Medioni contributed to developing a low-cost 3D depth (range) sensor, PrimeSensor, used in the
Microsoft Kinect. After Apple acquired PrimeSense in 2013, the sensor was integrated into the Apple iPhone X, enabling FaceID for mobile unlock.
261:
Medioni's Rapid avatar capture and simulation was the first demonstration of using commodity depth sensors to capture the 3D shape and appearance of human subjects, and then registering it and controlling it within an animation system within minutes.
955:
Masi, Iacopo; Trần, Anh Tuấn; Hassner, Tal; Leksut, Jatuporn Toy; Medioni, Gérard (October 11, 2016). "Do We Really Need to
Collect Millions of Faces for Effective Face Recognition?". In Leibe, Bastian; Matas, Jiri; Sebe, Nicu; Welling, Max (eds.).
1106:
252:
Medioni developed the
Iterative Closest Point (ICP) algorithm to create a complete 3D model of a physical object from partial scans. ICP serves as a dominant method for registering partial 3-D scans of a scene, with over 5,500 citations.
244:
a wide variety of problems. While the original tensor voting formulation worked with 2-D input, it was extended to 3-D (surfaces, stereo), 4-D (motion), and N-D. It is thus applicable to both
Computer Vision and Machine Learning.
446:
1116:
374:
Khan, S., Rahmani, H., Shah, S. A. A., Bennamoun, M., Medioni, G., & Dickinson, S. (2018). A guide to convolutional neural networks for computer vision (Vol. 8, No. 1, pp. 1–207). San Rafael: Morgan & Claypool
1101:
218:
detecting people, keeping track of their location throughout their journey in the store, recognizing items that a customer picks up from the shelves, and producing an accurate receipt for items they end up buying.
1111:
362:
Huertas, A., & Medioni, G. (1986). Detection of intensity changes with subpixel accuracy using
Laplacian-Gaussian masks. IEEE Transactions on Pattern Analysis and Machine Intelligence, (5), 651–664.
138:
226:
Medioni developed the algorithmic components for Amazon One. This device optically captures the unique print and vein patterns of the palm and identifies a user among enrolled users.
188:
Medioni was the
President and CEO at I.C. Vision, Chief Technical Officer at Geometrix, and Director of Research at Amazon. Additionally, he has served as an advisory board member at
912:
Medioni, Gerard; Choi, Jongmoo; Kuo, Cheng-Hao; Choudhury, Anustup; Li Zhang; Fidaleo, Douglas (2007). "Non-Cooperative
Persons Identification at a Distance with 3D Face Modeling".
1121:
371:
Dinh, T. B., Vo, N., & Medioni, G. (2011, June). Context tracker: Exploring supporters and distracters in unconstrained environments. In CVPR 2011 (pp. 1177–1184). IEEE.
840:
Kim, Donghyun; Choi, Jongmoo; Leksut, Jatuporn Toy; Medioni, Gerard (2016). "Accurate 3D face modeling and recognition from RGB-D stream in the presence of large pose changes".
182:
1992, and a full professor in 1999. Since 2019, he has been serving as an emeritus professor in the department of
Computer Science at the University of Southern California.
1141:
368:
Stein, F., & Medioni, G. (1992). Structural indexing: Efficient 3-D object recognition. IEEE Transactions on
Pattern Analysis and Machine Intelligence, 14(2), 125–145.
1136:
146:
142:
563:
209:
modules. Moreover, he used an interdisciplinary approach to connect Computer Vision and Graphics to comprehend visual information processing.
1008:
983:
931:
896:
859:
1081:
173:
from 1977 to 1978. He then completed his MSc in 1980 and his Ph.D. in 1983 in computer science from the University of Southern California.
365:
Chen, Y., & Medioni, G. (1992). Object modelling by registration of multiple range images. Image and vision computing, 10(3), 145–155.
463:
1131:
110:. He has translated his computer vision research into customer-facing inventions and products. He has authored four books, including
816:
767:
92:
45:
359:
Medioni, G., & Nevatia, R. (1985). Segment-based stereo matching. Computer vision, graphics, and image processing, 31(1), 2–18.
1126:
433:"Visual tracking in video images in unconstrained environments by exploiting on-the-fly context using supporters and distracters"
1091:
154:
150:
1096:
1086:
271:
presented a method for remotely identifying non-cooperative individuals using 3D face models from a sequence of images.
185:
From 2001 to 2007, Medioni chaired the department of Computer Science at the University of Southern California.
1146:
1057:
960:. Lecture Notes in Computer Science. Vol. 9909. Springer International Publishing. pp. 579–596.
701:
783:
112:
Emerging Topics in Computer Vision, Multimedia Systems: Algorithms, Standards, and Industry Practices
746:
Feng, Andrew; Shapiro, Ari; Ruizhe, Wang; Bolas, Mark; Medioni, Gerard; Suma, Evan (July 27, 2014).
627:
414:
687:
673:
613:
166:
41:
989:
961:
937:
865:
822:
659:
484:
80:
55:
979:
927:
892:
855:
812:
763:
504:
103:
971:
919:
847:
804:
755:
728:
123:
88:
84:
68:
396:
99:
915:
2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems
341:
Tensor Voting: A Perceptual Organization Approach to Computer Vision and Machine Learning
674:"3D body modeling from one or more depth cameras in the presence of articulated motion"
505:"Alphabetical List of IAPR Fellows – International Association for Pattern Recognition"
83:, author, academic and inventor. He is a vice president and distinguished scientist at
1022:
716:
542:
1075:
732:
993:
941:
869:
826:
595:
200:. In 2019, he was promoted to Distinguished Scientist and Vice President at Amazon.
1007:
Masi, Iacopo; Rawls, Stephen; Medioni, Gerard; Natarajan, Prem (October 11, 2016).
107:
975:
581:
521:
295:
2004 – Fellow, Association for the Advancement of Artificial Intelligence (AAAI)
170:
127:
913:
884:
841:
923:
851:
798:
614:"Locally and globally locating actors by digital cameras and machine learning"
596:"Gerard Medioni, Vice President and Distinguished Scientist, AWS Applications"
193:
131:
808:
889:
2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)
797:
Chen, Q.; Medioni, G. (1998). "Building human face models from two images".
759:
564:"Gérard Medioni believes now is a 'golden age' for computer vision research"
119:
800:
1998 IEEE Second Workshop on Multimedia Signal Processing (Cat. No.98EX175)
628:"Associating events with actors using digital imagery and machine learning"
747:
1107:
Fellows of the Association for the Advancement of Artificial Intelligence
197:
189:
292:
2003 – Fellow, Institute of Electrical and Electronics Engineers (IEEE)
447:"Depth mapping based on pattern matching and stereoscopic information"
304:
2021 – Fellow, Asia-Pacific Artificial Intelligence Association (AAIA)
885:"Laser scan quality 3-D face modeling using a low-cost depth camera"
966:
883:
Matthias Hernandez; Jongmoo Choi; Gérard Medioni (27 August 2012).
784:"Rapid avatar capture and simulation using commodity depth sensors"
748:"Rapid avatar capture and simulation using commodity depth sensors"
1039:
397:"USC - Viterbi School of Engineering - Viterbi Faculty Directory"
347:
Multimedia Systems: Algorithms, Standards, and Industry Practices
1117:
Fellows of the International Association for Pattern Recognition
489:
130:
information, along with patents on Just Walk Out technology and
843:
2016 IEEE International Conference on Image Processing (ICIP)
1102:
Members of the United States National Academy of Engineering
717:"Object modelling by registration of multiple range images"
641:
139:
Association for the Advancement of Artificial Intelligence
298:
2007 – Most Influential Paper over the Decade Award, MVA
167:
Ecole Nationale Supérieure des Telecommunications (ENST)
42:
Ecole Nationale Supérieure des Telecommunications (ENST)
1112:
2023 fellows of the Association for Computing Machinery
1011:. pp. 4838–4846 – via openaccess.thecvf.com.
329:
A Computational Framework for Segmentation and Grouping
116:
A Computational Framework for Segmentation and Grouping
165:
Medioni obtained his Diplôme d'Ingénieur in 1977 from
1040:"Gérard MEDIONI | World AI Cannes Festival 2023"
313:
2023 – Member, National Academy of Engineering (NAE)
62:
51:
37:
25:
18:
754:. Association for Computing Machinery. p. 1.
169:Paris and was appointed as a Research Engineer at
147:International Association for Pattern Recognition
143:Institute of Electrical and Electronics Engineers
307:2021 – Distinguished Leader, APSIPA Industrial
289:1999 – Okawa Foundation Award, Okawa Foundation
1023:"Most Influential Paper over the Decade Award"
646:Bringing Just Walk Out shopping to your stores
715:Chen, Yang; Medioni, Gérard (April 1, 1992).
582:"Gerard Medioni - IEEE Xplore Author Details"
310:2022 – Fellow, National Academy of Inventors
301:2019 – PAMI Mark Everingham Prize, IEEE Trans
8:
1122:Fellows of the National Academy of Inventors
15:
1142:University of Southern California faculty
1009:"Pose-Aware Face Recognition in the Wild"
965:
1137:University of Southern California alumni
702:"Tensor voting in N dimensional spaces"
688:"Tensor voting in N dimensional spaces"
385:
558:
556:
464:"Current AAAI Members Who Are Fellows"
660:"System for biometric identification"
537:
535:
516:
514:
479:
477:
458:
456:
391:
389:
7:
87:and serves as emeritus professor of
1058:"Gérard Medioni named AAIA fellow"
335:Emerging Topics in Computer Vision
98:Medioni has made contributions to
14:
93:University of Southern California
66:University of Southern California
46:University of Southern California
772:– via ACM Digital Library.
257:Rapid avatar capture simulation
155:National Academy of Engineering
58:, author, academic and inventor
543:"Professor Gerard Guy Medioni"
1:
151:National Academy of Inventors
976:10.1007/978-3-319-46454-1_35
733:10.1016/0262-8856(92)90066-C
102:, in particular 3D sensing,
1082:Computer vision researchers
958:Computer Vision – ECCV 2016
349:(2009) ISBN 978-1418835941
331:(2000) ISBN 978-0080529486.
137:Medioni is a Fellow of the
1163:
996:– via Springer Link.
735:– via ScienceDirect.
721:Image and Vision Computing
343:(2006) ISBN 978-1598291001
337:(2004) ISBN 978-0131013667
161:Education and early career
924:10.1109/BTAS.2007.4401961
852:10.1109/ICIP.2016.7532912
153:. He is also a member of
809:10.1109/MMSP.1998.738922
485:"IEEE Fellows Directory"
213:Just walk out technology
1127:Amazon (company) people
760:10.1145/2614106.2614182
752:ACM SIGGRAPH 2014 Talks
248:Iterative closest point
33:Ph.D., Computer Science
1092:21st-century inventors
846:. pp. 3011–3015.
104:surface reconstruction
31:MSc., Computer Science
29:Ingénieur Informatique
1044:www.worldaicannes.com
1132:Télécom Paris alumni
803:. pp. 117–122.
1097:Members of the IEEE
1087:Computer scientists
570:. October 15, 2021.
419:scholar.google.com
81:computer scientist
56:Computer scientist
985:978-3-319-46453-4
933:978-1-4244-1596-0
898:978-1-4673-1068-0
861:978-1-4673-9961-6
354:Selected articles
284:Awards and honors
77:Gérard G. Medioni
74:
73:
20:Gérard G. Medioni
1154:
1066:
1065:
1064:. July 19, 2021.
1054:
1048:
1047:
1036:
1030:
1029:
1027:
1019:
1013:
1012:
1004:
998:
997:
969:
952:
946:
945:
918:. pp. 1–6.
909:
903:
902:
880:
874:
873:
837:
831:
830:
794:
788:
787:
780:
774:
773:
743:
737:
736:
712:
706:
705:
698:
692:
691:
684:
678:
677:
670:
664:
663:
656:
650:
649:
638:
632:
631:
624:
618:
617:
610:
604:
603:
592:
586:
585:
578:
572:
571:
560:
551:
550:
539:
530:
529:
518:
509:
508:
501:
495:
494:
481:
472:
471:
460:
451:
450:
443:
437:
436:
429:
423:
422:
415:"Gerard Medioni"
411:
405:
404:
393:
275:Face Recognition
124:pattern matching
108:object modelling
89:Computer Science
16:
1162:
1161:
1157:
1156:
1155:
1153:
1152:
1151:
1072:
1071:
1070:
1069:
1056:
1055:
1051:
1038:
1037:
1033:
1025:
1021:
1020:
1016:
1006:
1005:
1001:
986:
954:
953:
949:
934:
911:
910:
906:
899:
882:
881:
877:
862:
839:
838:
834:
819:
796:
795:
791:
782:
781:
777:
770:
745:
744:
740:
714:
713:
709:
700:
699:
695:
686:
685:
681:
672:
671:
667:
658:
657:
653:
642:"Just Walk Out"
640:
639:
635:
626:
625:
621:
612:
611:
607:
600:US About Amazon
594:
593:
589:
580:
579:
575:
562:
561:
554:
541:
540:
533:
520:
519:
512:
503:
502:
498:
483:
482:
475:
462:
461:
454:
445:
444:
440:
431:
430:
426:
413:
412:
408:
401:viterbi.usc.edu
395:
394:
387:
382:
356:
325:
320:
286:
277:
268:
259:
250:
241:
232:
224:
215:
206:
179:
163:
100:computer vision
67:
63:Organization(s)
44:
38:Alma mater
32:
30:
21:
12:
11:
5:
1160:
1158:
1150:
1149:
1144:
1139:
1134:
1129:
1124:
1119:
1114:
1109:
1104:
1099:
1094:
1089:
1084:
1074:
1073:
1068:
1067:
1062:Amazon Science
1049:
1031:
1014:
999:
984:
947:
932:
904:
897:
875:
860:
832:
817:
789:
775:
768:
738:
727:(3): 145–155.
707:
693:
679:
665:
651:
633:
619:
605:
587:
573:
568:Amazon Science
552:
531:
510:
496:
473:
452:
438:
424:
406:
384:
383:
381:
378:
377:
376:
372:
369:
366:
363:
360:
355:
352:
351:
350:
344:
338:
332:
324:
323:Selected books
321:
319:
316:
315:
314:
311:
308:
305:
302:
299:
296:
293:
290:
285:
282:
276:
273:
267:
266:Face modelling
264:
258:
255:
249:
246:
240:
237:
231:
228:
223:
220:
214:
211:
205:
202:
178:
175:
162:
159:
72:
71:
64:
60:
59:
53:
49:
48:
39:
35:
34:
27:
23:
22:
19:
13:
10:
9:
6:
4:
3:
2:
1159:
1148:
1147:Living people
1145:
1143:
1140:
1138:
1135:
1133:
1130:
1128:
1125:
1123:
1120:
1118:
1115:
1113:
1110:
1108:
1105:
1103:
1100:
1098:
1095:
1093:
1090:
1088:
1085:
1083:
1080:
1079:
1077:
1063:
1059:
1053:
1050:
1045:
1041:
1035:
1032:
1024:
1018:
1015:
1010:
1003:
1000:
995:
991:
987:
981:
977:
973:
968:
963:
959:
951:
948:
943:
939:
935:
929:
925:
921:
917:
916:
908:
905:
900:
894:
890:
886:
879:
876:
871:
867:
863:
857:
853:
849:
845:
844:
836:
833:
828:
824:
820:
818:0-7803-4919-9
814:
810:
806:
802:
801:
793:
790:
785:
779:
776:
771:
769:9781450329606
765:
761:
757:
753:
749:
742:
739:
734:
730:
726:
722:
718:
711:
708:
703:
697:
694:
689:
683:
680:
675:
669:
666:
661:
655:
652:
647:
643:
637:
634:
629:
623:
620:
615:
609:
606:
601:
597:
591:
588:
583:
577:
574:
569:
565:
559:
557:
553:
548:
544:
538:
536:
532:
527:
523:
517:
515:
511:
506:
500:
497:
492:
491:
486:
480:
478:
474:
469:
465:
459:
457:
453:
448:
442:
439:
434:
428:
425:
420:
416:
410:
407:
402:
398:
392:
390:
386:
379:
373:
370:
367:
364:
361:
358:
357:
353:
348:
345:
342:
339:
336:
333:
330:
327:
326:
322:
317:
312:
309:
306:
303:
300:
297:
294:
291:
288:
287:
283:
281:
280:recognition.
274:
272:
265:
263:
256:
254:
247:
245:
239:Tensor voting
238:
236:
229:
227:
221:
219:
212:
210:
203:
201:
199:
195:
191:
186:
183:
176:
174:
172:
168:
160:
158:
156:
152:
148:
144:
140:
135:
133:
129:
125:
121:
120:Depth mapping
117:
113:
109:
105:
101:
96:
94:
90:
86:
82:
78:
70:
65:
61:
57:
54:
52:Occupation(s)
50:
47:
43:
40:
36:
28:
24:
17:
1061:
1052:
1043:
1034:
1017:
1002:
957:
950:
914:
907:
888:
878:
842:
835:
799:
792:
778:
751:
741:
724:
720:
710:
696:
682:
668:
654:
645:
636:
622:
608:
599:
590:
576:
567:
546:
525:
499:
488:
467:
441:
427:
418:
409:
400:
346:
340:
334:
328:
318:Bibliography
278:
269:
260:
251:
242:
233:
225:
216:
207:
187:
184:
180:
164:
136:
128:stereoscopic
115:
111:
97:
76:
75:
547:NAE Website
375:Publishers.
171:Thomson-CSF
1076:Categories
967:1603.07057
380:References
230:Primesense
222:Amazon One
194:PrimeSense
149:, and the
132:Amazon One
522:"Fellows"
122:based on
26:Education
994:14595783
942:13401437
891:. IEEE.
870:19425541
827:30128026
204:Research
198:Tel Aviv
190:DXO Labs
91:at the
992:
982:
940:
930:
895:
868:
858:
825:
815:
766:
177:Career
145:, the
141:, the
114:, and
106:, and
85:Amazon
69:Amazon
1026:(PDF)
990:S2CID
962:arXiv
938:S2CID
866:S2CID
823:S2CID
79:is a
980:ISBN
928:ISBN
893:ISBN
856:ISBN
813:ISBN
764:ISBN
490:IEEE
468:AAAI
192:and
126:and
972:doi
920:doi
848:doi
805:doi
756:doi
729:doi
526:NAI
196:in
1078::
1060:.
1042:.
988:.
978:.
970:.
936:.
926:.
887:.
864:.
854:.
821:.
811:.
762:.
750:.
725:10
723:.
719:.
644:.
598:.
566:.
555:^
545:.
534:^
524:.
513:^
487:.
476:^
466:.
455:^
417:.
399:.
388:^
157:.
134:.
95:.
1046:.
1028:.
974::
964::
944:.
922::
901:.
872:.
850::
829:.
807::
786:.
758::
731::
704:.
690:.
676:.
662:.
648:.
630:.
616:.
602:.
584:.
549:.
528:.
507:.
493:.
470:.
449:.
435:.
421:.
403:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.