VLP2MSA: Expanding vision-language pre-training to multimodal sentiment analysis
Guofeng Yi, Cunhang Fan, Kang Zhu, Zhao Lv, Shan Liang, Zhengqi Wen, Guanxiong Pei, Taihao Li, Jianhua Tao
Topics & Concepts
Computer scienceDiscriminative modelModalitiesModality (human–computer interaction)Artificial intelligenceMultimodal learningRepresentation (politics)Sentiment analysisMultimodalityNatural language processingSociologyPolitical sciencePoliticsSocial scienceLawWorld Wide WebMultimodal Machine Learning ApplicationsSentiment Analysis and Opinion MiningImage Retrieval and Classification Techniques