Open-Vocabulary Audio-Visual Semantic Segmentation

Audio-visual semantic segmentation (AVSS) aims to segment and classify sounding objects in videos with acoustic cues. However, most approaches operate on the close-set assumption and only identify pre-defined categories from training data, lacking the generalization ability to detect novel categorie...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Guo, Ruohao, Qu, Liao, Niu, Dantong, Qi, Yanyu, Yue, Wenzhen, Shi, Ji, Xing, Bowei, Ying, Xianghua
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Multimedia
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!