Contrastive Language-Image Learning with Augmented Textual Prompts for 3D/4D FER Using Vision-Language Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918002097651712 |
|---|---|
| author | Behzad, Muzammil Zhao, Guoying |
| author_facet | Behzad, Muzammil Zhao, Guoying |
| contents | In this paper, we introduce AffectVLM, a vision-language model designed to integrate multiviews for a semantically rich and visually comprehensive understanding of facial emotions from 3D/4D data. To effectively capture visual features, we propose a joint representation learning framework paired with a novel gradient-friendly loss function that accelerates model convergence towards optimal feature representation. Additionally, we introduce augmented textual prompts to enhance the model's linguistic capabilities and employ mixed view augmentation to expand the visual dataset. We also develop a Streamlit app for a real-time interactive inference and enable the model for distributed learning. Extensive experiments validate the superior performance of AffectVLM across multiple benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19739 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contrastive Language-Image Learning with Augmented Textual Prompts for 3D/4D FER Using Vision-Language Model Behzad, Muzammil Zhao, Guoying Computer Vision and Pattern Recognition In this paper, we introduce AffectVLM, a vision-language model designed to integrate multiviews for a semantically rich and visually comprehensive understanding of facial emotions from 3D/4D data. To effectively capture visual features, we propose a joint representation learning framework paired with a novel gradient-friendly loss function that accelerates model convergence towards optimal feature representation. Additionally, we introduce augmented textual prompts to enhance the model's linguistic capabilities and employ mixed view augmentation to expand the visual dataset. We also develop a Streamlit app for a real-time interactive inference and enable the model for distributed learning. Extensive experiments validate the superior performance of AffectVLM across multiple benchmarks. |
| title | Contrastive Language-Image Learning with Augmented Textual Prompts for 3D/4D FER Using Vision-Language Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19739 |