.png){kind=icon}
.png){kind=icon}
Return
Audio-Visual Automatic Group Affect Analysis
.png){kind=icon}
PRE
AI
DOI：10.1109/TAFFC.2021.3104170.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Affective computing has progressed well due to methods, which can identify a person's posed and spontaneous perceived affect with high accuracy. This paper focuses on group-level affect analysis on videos, which is one of the first few multimodal group-level affect analysis studies. There are many challenges on video-based group-level affect analysis as most of the work is focused on either a single person's affect recognition or image-based group affect analysis. To address this, first, we present an audio-visual perceived group affect dataset - 'Video-level Group AFfect (VGAF)'. VGAF is a large-scale dataset consisting of 4,183 group videos. The videos are collected from YouTube with large variations in the keywords for collecting data across different genders, group settings, group sizes, illuminations and poses. The variety within the dataset will help the study of perception of group affect in a real environment. The data is manually annotated for three group affect classes - positive, neutral, and negative. Further, a fusion based audio-visual method is proposed to set a benchmark performance on the proposed dataset. The experimental results show the effectiveness of facial, holistic and speech features for group-level affect analysis. The baseline code, dataset, and pre-trained models are available at [LINK].
Keywords:
Videos
Face recognition
Emotion recognition
Affective computing
Speech recognition
Feature extraction
Cameras
Group-level affect recognition
affect recognition
affective computing
Journal
IF:
9.8
Papers:
1.3K
Citations:
9.1K