Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Qing, Guo, Wangdong, Mao, Qirong, Huang, Xiaohua, Shao, Xiuyan, Zheng, Wenming
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.21747
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912606447468544
author Zhu, Qing
Guo, Wangdong
Mao, Qirong
Huang, Xiaohua
Shao, Xiuyan
Zheng, Wenming
author_facet Zhu, Qing
Guo, Wangdong
Mao, Qirong
Huang, Xiaohua
Shao, Xiuyan
Zheng, Wenming
contents Group-level emotion recognition (GER) aims to identify holistic emotions within a scene involving multiple individuals. Current existed methods underestimate the importance of visual scene contextual information in modeling individual relationships. Furthermore, they overlook the crucial role of semantic information from emotional labels for complete understanding of emotions. To address this limitation, we propose a novel framework that incorporates visual scene context and label-guided semantic information to improve GER performance. It involves the visual context encoding module that leverages multi-scale scene information to diversely encode individual relationships. Complementarily, the emotion semantic encoding module utilizes group-level emotion labels to prompt a large language model to generate nuanced emotion lexicons. These lexicons, in conjunction with the emotion labels, are then subsequently refined into comprehensive semantic representations through the utilization of a structured emotion tree. Finally, similarity-aware interaction is proposed to align and integrate visual and semantic information, thereby generating enhanced group-level emotion representations and subsequently improving the performance of GER. Experiments on three widely adopted GER datasets demonstrate that our proposed method achieves competitive performance compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Incorporating Scene Context and Semantic Labels for Enhanced Group-level Emotion Recognition
Zhu, Qing
Guo, Wangdong
Mao, Qirong
Huang, Xiaohua
Shao, Xiuyan
Zheng, Wenming
Computer Vision and Pattern Recognition
Group-level emotion recognition (GER) aims to identify holistic emotions within a scene involving multiple individuals. Current existed methods underestimate the importance of visual scene contextual information in modeling individual relationships. Furthermore, they overlook the crucial role of semantic information from emotional labels for complete understanding of emotions. To address this limitation, we propose a novel framework that incorporates visual scene context and label-guided semantic information to improve GER performance. It involves the visual context encoding module that leverages multi-scale scene information to diversely encode individual relationships. Complementarily, the emotion semantic encoding module utilizes group-level emotion labels to prompt a large language model to generate nuanced emotion lexicons. These lexicons, in conjunction with the emotion labels, are then subsequently refined into comprehensive semantic representations through the utilization of a structured emotion tree. Finally, similarity-aware interaction is proposed to align and integrate visual and semantic information, thereby generating enhanced group-level emotion representations and subsequently improving the performance of GER. Experiments on three widely adopted GER datasets demonstrate that our proposed method achieves competitive performance compared to state-of-the-art methods.
title Incorporating Scene Context and Semantic Labels for Enhanced Group-level Emotion Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.21747