2026
Prototype-as-Prompt: Multimodal Sentiment Prototypes Endowing Large Language Models the Capability to Perform Multimodal Sentiment Analysis
CVPR 2026
Multimodal Sentiment Analysis (MSA) aims to integrate textual, acoustic, and visual information to predict sentiment polarity. With the emergence of Large Language Models (LLMs), existing studies commonly employ learnable queries to compress audio-visual representations and feed them as soft prompts