Improving image classification tasks using fused embeddings and multimodal models (2025)
- Authors:
- USP affiliated authors: HIRATA JUNIOR, ROBERTO - IME ; CESAR JUNIOR, ROBERTO MARCONDES - IME ; OLIVEIRA, ARTUR ANDRE ALMEIDA DE MACEDO - IME ; ESPADOTO, MATEUS - IME
- Unidade: IME
- DOI: 10.5220/0013365600003912
- Subjects: IMAGEM; INTELIGÊNCIA ARTIFICIAL; CLUSTERS
- Keywords: Prompt Engineering; Guided Embeddings; Multimodal Learning; Clustering; t-SNE Visualization; Zero-Shot Learning; Modelos multimodais; Prompts textuais
- Agências de fomento:
- Language: Inglês
- Imprenta:
- Publisher: SciTePress
- Publisher place: Setúbal
- Date published: 2025
- Source:
- Título: Proceedings
- ISSN: 2184-4321
- Volume/Número/Paginação/Ano: p. 232-241, 2025
- Conference titles: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - VISIGRAPP
- Status:
- Artigo publicado em periódico de acesso aberto (Gold Open Access)
- Versão do Documento:
- Versão publicada (Published version)
- Acessar versão aberta:
-
ABNT
OLIVEIRA, Artur André Almeida de Macedo et al. Improving image classification tasks using fused embeddings and multimodal models. 2025, Anais.. Setúbal: SciTePress, 2025. p. 232-241. Disponível em: https://www.scitepress.org/Papers/2025/133656/133656.pdf. Acesso em: 01 abr. 2026. -
APA
Oliveira, A. A. A. de M., Espadoto, M., Hirata Júnior, R., & César Júnior, R. M. (2025). Improving image classification tasks using fused embeddings and multimodal models. In Proceedings (p. 232-241). Setúbal: SciTePress. doi:10.5220/0013365600003912 -
NLM
Oliveira AAA de M, Espadoto M, Hirata Júnior R, César Júnior RM. Improving image classification tasks using fused embeddings and multimodal models [Internet]. Proceedings. 2025 ; 232-241.[citado 2026 abr. 01 ] Available from: https://www.scitepress.org/Papers/2025/133656/133656.pdf -
Vancouver
Oliveira AAA de M, Espadoto M, Hirata Júnior R, César Júnior RM. Improving image classification tasks using fused embeddings and multimodal models [Internet]. Proceedings. 2025 ; 232-241.[citado 2026 abr. 01 ] Available from: https://www.scitepress.org/Papers/2025/133656/133656.pdf - Graph memory: a structured and interpretable framework for modality-agnostic embedding-based inference
- Efficient video segmentation with differential networks
- SDBM: Supervised Decision Boundary Maps for machine learning classifiers
- Towards a method for evaluating bus stop infrastructure with street level images and large language models
- Towards interpretable multimodal embeddings: a QR-based prototype projection approach
- Improving self-supervised dimensionality reduction: exploring hyperparameters and pseudo-labeling strategies
- Stability analysis of supervised decision boundary maps
- Deep learning and data integration for detecting trees entangled with utility lines
- Locating urban trees near electric wires using Google Street View Photos: a new dataset and a semi-supervised learning approach in the wild
- INACITY - INvestigate and Analyze a CITY
Informações sobre a disponibilidade de versões do artigo em acesso aberto coletadas automaticamente via oaDOI API (Unpaywall).
Por se tratar de integração com serviço externo, podem existir diferentes versões do trabalho (como preprints ou postprints), que podem diferir da versão publicada.
Download do texto completo
| Tipo | Nome | Link | |
|---|---|---|---|
 |
3253290.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
