AVEC 2012-The Continuous Audio/Visual Emotion Challenge - An Introduction

被引：0

作者：

Schuller, Bjoern ^{[1
]}

Valstar, Michel ^{[1
]}

Cowie, Roddy ^{[1
]}

Pantic, Maja ^{[1
]}

机构：

[1] Forsch Gesell mbH, JOANNEUM RES, Graz, Austria

来源：

ICMI '12: PROCEEDINGS OF THE ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION | 2012年

关键词：

Affective Computing; Emotion Recognition; Speech; Facial Expression; Challenge;

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 second international Audio/Visual Emotion Challenge and Workshop 2012 (AVEC 2012) is introduced shortly. 34 teams from 12 countries signed up for the Challenge. The SEMAINE database serves for prediction of four-dimensional continuous affect in audio and video. For the eligible participants, final scores for the Fully-Continuous Sub-Challenge ranged between a correlation coefficient between gold standard and prediction of 0.174 and 0.456, and for Word-Level Sub-Challenge between 0.113 and 0.280.

引用

页码：361 / 362

页数：2

共 6 条

[1]

[Anonymous], PROC 1 INT AUD VIS

[2]

Cowie R., 2000, PROC ISCA WORKSHOP S, P19

[3]

Eyben F., 2010, P 18 ACM INT C MULT, p1459 1462

[4]

IANG B., 2011, P IEEE INT C AUT FAC, P314

[5] The SEMAINE Database: Annotated Multimodal Records of Emotionally Colored Conversations between a Person and a Limited Agent [J].

McKeown, Gary ;

Valstar, Michel ;

Cowie, Roddy ;

Pantic, Maja ;

Schroeder, Marc .

IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2012, 3 (01) :5-17

[6]

SCHRODER M., 2012, IEEE T AFFE IN PRESS

← 1 →