AffectGPT introduces a 115K-sample descriptive emotion dataset, a pre-fusion multimodal LLM, and a unified benchmark, reporting large gains over existing MLLMs.
Related Works This paper focuses on constructing datasets and designing models to enhance the emotional understanding capability of MLLMs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
AffectGPT introduces a 115K-sample descriptive emotion dataset, a pre-fusion multimodal LLM, and a unified benchmark, reporting large gains over existing MLLMs.