BAUM-1数据集

The database and baseline results have been published in the following paper: S. Zhalehpour, O. Onder, Z. Akhtar, C. E. Erdem, 'BAUM-1: A Spontaneous Audio-V?°sual Face Database of Affective and Mental States', IEEE Transactions on Affective Computing, Vol. 8, No.3, 2017. The creators of the database are the authors of the above paper. Data Set Information: In order to download the database please send an e-mail to: s.zhalehpour '@' gmail.com or cigdem.erogluerdem '@' gmail.com Relevant information can be found in the readme file. Attribute Information: The dataset contains short video clips in MP4 format. The expressed emotional and mental states consist of happiness, anger, sadness, disgust, fear, surprise, boredom, contempt, confusion, neutral, thinking, concentrating, and bothered. Relevant Papers: Learning Affective Features With a Hybrid Deep Model for Audio-Visual Emotion Recognition By: Zhang, Shiqing; Zhang, Shiliang; Huang, Tiejun; et al. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY Volume: 28 Issue: 10 Special Issue: SI Pages: 3030-3043 Published: OCT 2018 'Facial Expression Analysis under Partial Occlusion: A Survey' By: Zhang, Ligang; Verma, Brijesh; Tjondronegoro, Dian; et al. ACM COMPUTING SURVEYS Volume: 51 Issue: 2 Article Number: 25 Published: JUN 2018 Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching By: Zhang, Shiqing; Zhang, Shiliang; Huang, Tiejun; et al. IEEE TRANSACTIONS ON MULTIMEDIA Volume: 20 Issue: 6 Pages: 1576-1590 Published: JUN 2018 IMPROVED AUDIO-VISUAL LAUGHTER DETECTION VIA MULTI-SCALE MULTI-RESOLUTION IMAGE TEXTURE FEATURES AND CLASSIFIER FUSION By: Akhtar, Zahid; Bedoya, Stefany; Falk, Tiago H. Conference: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Location: Calgary, CANADA Date: APR 15-20, 2018 Sponsor(s): Inst Elect & Elect Engineers; Inst Elect & Elect Engineers Signal Proc Soc 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) Pages: 3106-3110 Published: 2018 Citation Request: S. Zhalehpour, O. Onder, Z. Akhtar, C. E. Erdem, 'BAUM-1: A Spontaneous Audio-V?°sual Face Database of Affective and Mental States', IEEE Transactions on Affective Computing, Vol. 8, No.3, 2017.

本数据库及基准实验结果已发表于以下论文：S. Zhalehpour、O. Onder、Z. Akhtar、C. E. Erdem，《BAUM-1：面向情感与心理状态的自发音视频人脸数据库》，发表于《IEEE情感计算汇刊（IEEE Transactions on Affective Computing）》2017年第8卷第3期。该数据库的创建者即为上述论文的作者。

数据集信息：如需下载本数据库，请发送邮件至s.zhalehpour @ gmail.com或cigdem.erogluerdem @ gmail.com以申请下载。相关说明可查阅自述文件（readme file）。

属性信息：本数据集包含MP4格式的短视频片段，涵盖的情感与心理状态表达包括：快乐、愤怒、悲伤、厌恶、恐惧、惊讶、无聊、轻蔑、困惑、中性状态、思考状态、专注状态以及烦躁状态。

相关论文：
1. 《基于混合深度模型的音视频情感识别学习情感特征》（Learning Affective Features With a Hybrid Deep Model for Audio-Visual Emotion Recognition），作者：Zhang, Shiqing; Zhang, Shiliang; Huang, Tiejun; 等。发表于《IEEE电路与系统视频技术汇刊（IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY）》2018年10月，第28卷第10期特刊，页码：3030-3043。
2. 《部分遮挡下的面部表情分析：综述》（Facial Expression Analysis under Partial Occlusion: A Survey），作者：Zhang, Ligang; Verma, Brijesh; Tjondronegoro, Dian; 等。发表于《ACM计算概览（ACM COMPUTING SURVEYS）》2018年6月，第51卷第2期，文章编号：25。
3. 《基于深度卷积神经网络与判别式时间金字塔匹配的语音情感识别》（Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching），作者：Zhang, Shiqing; Zhang, Shiliang; Huang, Tiejun; 等。发表于《IEEE多媒体汇刊（IEEE TRANSACTIONS ON MULTIMEDIA）》2018年6月，第20卷第6期，页码：1576-1590。
4. 《基于多尺度多分辨率图像纹理特征与分类器融合的改进型音视频笑声检测》（IMPROVED AUDIO-VISUAL LAUGHTER DETECTION VIA MULTI-SCALE MULTI-RESOLUTION IMAGE TEXTURE FEATURES AND CLASSIFIER FUSION），作者：Akhtar, Zahid; Bedoya, Stefany; Falk, Tiago H.，发表于2018年IEEE国际声学、语音与信号处理会议（IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP），会议地点：加拿大卡尔加里，会议日期：2018年4月15-20日，主办方：电气与电子工程师协会、电气与电子工程师协会信号处理学会，收录于《2018 IEEE国际声学、语音与信号处理会议论文集》，页码：3106-3110，2018年出版。

引用请求：S. Zhalehpour、O. Onder、Z. Akhtar、C. E. Erdem，《BAUM-1：面向情感与心理状态的自发音视频人脸数据库》，《IEEE情感计算汇刊（IEEE Transactions on Affective Computing）》2017年第8卷第3期。

搜集汇总

背景与挑战

背景概述

BAUM-1数据集包含1184个多模态面部视频片段，来自31名受试者，涵盖了13种情感和心理状态的自发面部表情和语音。该数据集适用于情感计算和心理状态分析的研究。