Proxy tasks ensemble for explainable inference in sensitive data (2025)
- Authors:
- USP affiliated authors: RIBEIRO, LEO SAMPAIO FERRAZ - ICMC ; CARVALHO, CLARA ERNESTO DE - ICMC
- Unidade: ICMC
- DOI: 10.5753/sibgrapi.est.2025.38296
- Subjects: RECONHECIMENTO DE IMAGEM; APRENDIZADO COMPUTACIONAL; ABUSO SEXUAL; CRIANÇAS
- Language: Inglês
- Objetivos de Desenvolvimento Sustentável (ODS):
16. Paz, justiça e instituições eficazes
- Imprenta:
- Publisher: SBC
- Publisher place: Porto Alegre
- Date published: 2025
- Source:
- Título: Anais
- Conference titles: Conference on Graphics, Patterns, and Images - SIBGRAPI
- Este periódico é de acesso aberto
- Este artigo NÃO é de acesso aberto
-
ABNT
ERNESTO, Clara et al. Proxy tasks ensemble for explainable inference in sensitive data. 2025, Anais.. Porto Alegre: SBC, 2025. Disponível em: https://doi.org/10.5753/sibgrapi.est.2025.38296. Acesso em: 20 jan. 2026. -
APA
Ernesto, C., Avila, S., Caetano, C., & Ribeiro, L. S. F. (2025). Proxy tasks ensemble for explainable inference in sensitive data. In Anais. Porto Alegre: SBC. doi:10.5753/sibgrapi.est.2025.38296 -
NLM
Ernesto C, Avila S, Caetano C, Ribeiro LSF. Proxy tasks ensemble for explainable inference in sensitive data [Internet]. Anais. 2025 ;[citado 2026 jan. 20 ] Available from: https://doi.org/10.5753/sibgrapi.est.2025.38296 -
Vancouver
Ernesto C, Avila S, Caetano C, Ribeiro LSF. Proxy tasks ensemble for explainable inference in sensitive data [Internet]. Anais. 2025 ;[citado 2026 jan. 20 ] Available from: https://doi.org/10.5753/sibgrapi.est.2025.38296 - Cross Domain Visual Search with Feature Learning using Multi-stream Transformer-based Architectures
- Neglected risks: the disturbing reality of children's images in datasets and the urgent call for accountability
- Minimizing risk through minimizing model-data interaction: a protocol for relying on proxy tasks when designing child sexual abuse imagery detection models
- Scene Designer: a unified model for scene search and synthesis from sketch
- Scene designer: compositional sketch-based image retrieval with contrastive learning and an auxiliary synthesis task
- Sketchformer: transformer-based representation for sketched structure
- Training deep networks from zero to hero: avoiding pitfalls and going beyond
Informações sobre o DOI: 10.5753/sibgrapi.est.2025.38296 (Fonte: oaDOI API)
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
