Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912571311783936 |
|---|---|
| author | Takahashi, Ryo Saito, Naoki Maeda, Keisuke Ogawa, Takahiro Haseyama, Miki |
| author_facet | Takahashi, Ryo Saito, Naoki Maeda, Keisuke Ogawa, Takahiro Haseyama, Miki |
| contents | Visual Emotion Recognition (VER) is an important research topic due to its wide range of applications, including opinion mining and advertisement design. Extending this capability to recognize emotions at the individual level further broadens its potential applications. Recently, Multimodal Large Language Models (MLLMs) have attracted increasing attention and demonstrated performance comparable to that of conventional VER methods. However, MLLMs are trained on large and diverse datasets containing general opinions, which causes them to favor majority viewpoints and familiar patterns. This tendency limits their performance in a personalized VER, which is crucial for practical and real-world applications, and indicates a key area for improvement. To address this limitation, the proposed method employs discrete prompt tuning inspired by the process of humans' prompt engineering to adapt the VER task to each individual. Our method selects the best natural language representation from the generated prompts and uses it to update the prompt for the realization of accurate personalized VER. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04480 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition Takahashi, Ryo Saito, Naoki Maeda, Keisuke Ogawa, Takahiro Haseyama, Miki Computation and Language Machine Learning Visual Emotion Recognition (VER) is an important research topic due to its wide range of applications, including opinion mining and advertisement design. Extending this capability to recognize emotions at the individual level further broadens its potential applications. Recently, Multimodal Large Language Models (MLLMs) have attracted increasing attention and demonstrated performance comparable to that of conventional VER methods. However, MLLMs are trained on large and diverse datasets containing general opinions, which causes them to favor majority viewpoints and familiar patterns. This tendency limits their performance in a personalized VER, which is crucial for practical and real-world applications, and indicates a key area for improvement. To address this limitation, the proposed method employs discrete prompt tuning inspired by the process of humans' prompt engineering to adapt the VER task to each individual. Our method selects the best natural language representation from the generated prompts and uses it to update the prompt for the realization of accurate personalized VER. |
| title | Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.04480 |