AffectGPT introduces a 115K-sample descriptive emotion dataset, a pre-fusion multimodal LLM, and a unified benchmark, reporting large gains over existing MLLMs.
For more implementation details, please refer to the code provided in https://github.com/zeroQiaoba/AffectGPT
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 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.