Robust image features for classification and zero-shot tasks by merging visual and semantic attributes (2022)
- Authors:
- USP affiliated authors: PONTI, MOACIR ANTONELLI - ICMC ; RESENDE, DAMARES CRYSTINA OLIVEIRA DE - ICMC
- Unidade: ICMC
- DOI: 10.1007/s00521-021-06601-7
- Subjects: RECONHECIMENTO DE IMAGEM; APRENDIZADO COMPUTACIONAL
- Keywords: Image classification; Feature learning; Zero-shot learning; Autoencoder
- Agências de fomento:
- Language: Inglês
- Imprenta:
- Source:
- Título: Neural Computing and Applications
- ISSN: 0941-0643
- Volume/Número/Paginação/Ano: v. 34, n. 6, p. 4459-4471, Mar. 2022
- Este periódico é de acesso aberto
- Este artigo NÃO é de acesso aberto
-
ABNT
RESENDE, Damares Crystina Oliveira de e PONTI, Moacir Antonelli. Robust image features for classification and zero-shot tasks by merging visual and semantic attributes. Neural Computing and Applications, v. 34, n. 6, p. 4459-4471, 2022Tradução . . Disponível em: https://doi.org/10.1007/s00521-021-06601-7. Acesso em: 17 fev. 2026. -
APA
Resende, D. C. O. de, & Ponti, M. A. (2022). Robust image features for classification and zero-shot tasks by merging visual and semantic attributes. Neural Computing and Applications, 34( 6), 4459-4471. doi:10.1007/s00521-021-06601-7 -
NLM
Resende DCO de, Ponti MA. Robust image features for classification and zero-shot tasks by merging visual and semantic attributes [Internet]. Neural Computing and Applications. 2022 ; 34( 6): 4459-4471.[citado 2026 fev. 17 ] Available from: https://doi.org/10.1007/s00521-021-06601-7 -
Vancouver
Resende DCO de, Ponti MA. Robust image features for classification and zero-shot tasks by merging visual and semantic attributes [Internet]. Neural Computing and Applications. 2022 ; 34( 6): 4459-4471.[citado 2026 fev. 17 ] Available from: https://doi.org/10.1007/s00521-021-06601-7 - Robust image features creation by learning how to merge visual and semantic attributes
- Mobile inertial sensors for fall risk screening and prediction
- A decision cognizant Kullback-Leibler divergence
- Deep manifold alignment for mid-grain sketch based image retrieval
- Como funciona o deep learning
- Sketching out the details: sketch-based image retrieval using convolutional neural networks with multi-stage regression
- Generalization of feature embeddings transferred from different video anomaly detection domains
- An incremental linear-time learning algorithm for the optimum-path forest classifier
- Relevance image sampling from collection using importance selection on randomized optimum-path trees
- Compact descriptors for sketch-based image retrieval using a triplet loss convolutional neural network
Informações sobre o DOI: 10.1007/s00521-021-06601-7 (Fonte: oaDOI API)
Download do texto completo
| Tipo | Nome | Link | |
|---|---|---|---|
 |
3058063.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
