Fusion of Speech, Faces and Text for Person Identification in TV Broadcast

被引：0

作者：

Bredin, Herve ^{[1
]}

Poignant, Johann ^{[2
]}

Tapaswi, Makarand ^{[3
]}

Fortier, Guillaume ^{[4
]}

Viet Bac Le ^{[5
]}

Napoleon, Thibault ^{[6
]}

Gao, Hua ^{[3
]}

Barras, Claude ^{[1
]}

Rosset, Sophie ^{[1
]}

Besacier, Laurent ^{[2
]}

Verbeek, Jakob ^{[4
]}

Quenot, Georges ^{[2
]}

Jurie, Frederic ^{[6
]}

Ekenel, Hazim Kemal ^{[3
]}

机构：

[1] Univ Paris 11, CNRS, UPR 3251, LIMSI, BP 133, F-91403 Orsay, France

[2] UJF Grenoble 1, UPMF Grenoble 2, Grenoble INP, CNRS,UMR 5217,LIG, F-38041 Grenoble, France

[3] Karlsruher Inst Technol, Karlsruhe, Germany

[4] INRIA Rhone Alpes, F-38330 Montbonnot St Martin, France

[5] Vocapia Res, F-91400 Orsay, France

[6] Univ Caen, GREYC, UMR 6072, F-14050 Caen, France

来源：

COMPUTER VISION - ECCV 2012, PT III | 2012年 / 7585卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The Repere challenge is a project aiming at the evaluation of systems for supervised and unsupervised multimodal recognition of people in TV broadcast. In this paper, we describe, evaluate and discuss QCompere consortium submissions to the 2012 Repere evaluation campaign dry-run. Speaker identification (and face recognition) can be greatly improved when combined with name detection through video optical character recognition. Moreover, we show that unsupervised multimodal person recognition systems can achieve performance nearly as good as supervised monomodal ones (with several hundreds of identity models).

引用

页码：385 / 394

页数：10

共 50 条

[41] "Knock! Knock! Who is it?" Probabilistic Person Identification in TV-Series
Tapaswi, Makarand
Baeuml, Martin
Stiefelhagen, Rainer
2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2012, : 2658 - 2665
[42] HEARING FACES: TARGET SPEAKER TEXT-TO-SPEECH SYNTHESIS FROM A FACE
Pluester, Bjoern
Weber, Cornelius
Qu, Leyuan
Wermter, Stefan
2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2021, : 757 - 764
[43] Person recognition and identification: Names and faces compared through time of fame
Lucchelli, F.
Bizzozero, I.
Saetti, M. C.
Spinnler, H.
EUROPEAN JOURNAL OF NEUROLOGY, 2006, 13 : 132 - 132
[44] Explainable Multimodal Fusion for Dementia Detection From Text and Speech
Altinok, Duygu
TEXT, SPEECH, AND DIALOGUE, TSD 2024, PT II, 2024, 15049 : 236 - 251
[45] Automatic Identification of Person using fusion of Gait features
Sivarathinabala, M.
Abirami, S.
2014 INTERNATIONAL CONFERENCE ON SCIENCE ENGINEERING AND MANAGEMENT RESEARCH (ICSEMR), 2014,
[46] Efficient Person Identification by Fusion of Multiple Palmprint Representations
Meraoumia, Abdallah
Chitroub, Salim
Bouridane, Ahmed
IMAGE AND SIGNAL PROCESSING, PROCEEDINGS, 2010, 6134 : 182 - +
[47] Distributed Signature Fusion for Person Re-Identification
Martinel, Niki
Micheloni, Christian
Piciarelli, Claudio
2012 SIXTH INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS (ICDSC), 2012,
[48] Distance Penalization and Fusion for Person Re-identification
Mirmahboub, Behzad
Mekhalfi, Mohamed Lamine
Murino, Vittorio
2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017), 2017, : 1306 - 1314
[49] A FEATURE FUSION STRATEGY FOR PERSON RE-IDENTIFICATION
Gao, Mu
Ai, Haizhou
Bai, Bo
2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, : 4274 - 4278
[50] Dual Network Fusion for Person Re-Identification
Du, Lin
Tian, Chang
Zeng, Mingyong
Wang, Jiabao
Jiao, Shanshan
Shen, Qing
Wu, Guodong
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2020, E103A (03) : 643 - 648

← 1 2 3 4 5 →