Research map / Label-efficient and robust learning / Domain adaptation and generalization
PromptEmo: Learning Emotion with Bilateral Textual Prompts in Multi-Domain Open-set Scenarios
Xinyi Zeng, Yuxiang Yang, Pinxian Zeng, Wenxia Yin, Bo Liu, Xi Wu, Yan Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add positive prompts and positive-oriented CEI losses to the baseline (ablation) | PromptEmo · FERPlus | AUC-U (%): 58.57 -> 66.64 (+8.07) | Improved |
| add negative prompts and negative-oriented CEI losses (ablation) | PromptEmo · FERPlus | AUC-U (%): 66.64 -> 69.08 (+2.44) | Improved |
| add explicit semantic separation loss L_ESS (ablation) | PromptEmo · FERPlus | AUC-U (%): 69.08 -> 69.53 (+0.45) | Improved |
| add latent domain alignment loss L_LDA (ablation) | PromptEmo · FERPlus | AUC-U (%): 69.53 -> 70.66 (+1.13) | Improved |
| use LLM-generated descriptions instead of 'a photo of {class}' (ablation) | PromptEmo positive prompts · FERPlus | AUC-U (%): 68.16 -> 70.24 (w/o delta_k) | Improved |
| add trainable prompt vectors delta_k to LLM descriptions (ablation) | PromptEmo positive prompts · FERPlus | ACC-S (%): 56.63 -> 58.04 | Improved |
| add a CLIP text encoder with standard prompts to LA-CMFER (ablation) | LA-CMFER · FERPlus | AUC-U (%): 60.59 -> 60.67 | No clear effect |
| PromptEmo vs best prior method (LA-CMFER) on unseen classes | MO-FER, four FER datasets · AffectNet/Oulu-CASIA/FERPlus/RAF-DB | AUC-U (%): e.g. RAF-DB 68.74 -> 75.91 | Improved |
Closest papers by meaning
- Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis (AAAI 2026 · similarity 0.86)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.86)
- Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy (CVPR 2026 · similarity 0.86)
- Bridge Then Begin Anew: Generating Target-Relevant Intermediate Model for Source-Free Visual Emotion Adaptation (AAAI 2025 · similarity 0.86)
- AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition (NeurIPS 2026 · similarity 0.86)
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
