A cross-modal collaborative guiding network for sarcasm explanation in multi-modal multi-party dialogues

Open Webpage

Xingjie Zhuang, Zhixin Li, Canlong Zhang, Huifang Ma

Published: 01 Jan 2025, Last Modified: 11 Apr 2025Eng. Appl. Artif. Intell. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•CCG-Net accurately generates explanations for sarcastic utterances in dialogues.•Dynamic modal guidance sequence helps understand semantic information in context.•CMGBF facilitates deeper sarcastic semantic interactions between multimodal signals.•Our MIF module can prevent the infiltration of multimodal noise into the model.