Research map / Label-efficient and robust learning / Recognition and long-tail
Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition
Haiying Xia, Zhongyi Huang, Yumei Tan, Shuxiang Song
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 FiLM-based mode injection into first layer (ablation) | MIDIBERT · EMOPIA | accuracy: 0.716 -> 0.752 | Improved |
| add FiLM-based mode injection into first layer (ablation) | MIDIBERT · EMOPIA | macro-F1: 0.715 -> 0.751 | Improved |
| add FiLM-based mode injection into first layer (ablation) | MIDIBERT · VGMIDI | accuracy: 0.500 -> 0.591 | Improved |
| add FiLM-based mode injection into first layer (ablation) | MIDIBERT · VGMIDI | macro-F1: 0.365 -> 0.587 | Improved |
| fine-tune on mode-preserving transposition augmented data | MIDIBERT · EMOPIA | accuracy: 0.675 -> 0.723 | Improved |
| add mode injection (MoFi) versus plain MIDIBERT-Piano baseline | MIDIBERT-Piano · EMOPIA | accuracy: 0.634 -> 0.752 | Improved |
| add mode injection (MoFi) versus plain MIDIBERT-Piano baseline | MIDIBERT-Piano · VGMIDI | accuracy: 0.473 -> 0.591 | Improved |
| add mode injection (MoFi) versus plain MIDIBERT-Piano baseline | MIDIBERT-Piano · EMOPIA | macro-F1: 0.628 -> 0.751 | Improved |
| add mode injection (MoFi) versus plain MIDIBERT-Piano baseline | MIDIBERT-Piano · VGMIDI | macro-F1: 0.432 -> 0.587 | Improved |
Closest papers by meaning
- MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotion (AAAI 2024 · similarity 0.88)
- FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition (NeurIPS 2025 · similarity 0.83)
- HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization (CVPR 2025 · similarity 0.83)
- MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models (CVPR 2024 · similarity 0.83)
- From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment (NeurIPS 2026 · similarity 0.83)
- Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning (NeurIPS 2024 · similarity 0.83)
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.
