LOG.org

Notas

sáb 27 mar 2021 18:23:33: Apêndice vs Anexo

https://www.puc-rio.br/ensinopesq/ccpg/normas/apendices_e_anexos.html#:~:text=Ap%C3%AAndices%20s%C3%A3o%20textos%20elaborados%20pelo,mapas%2C%20leis%2C%20estatutos%20etc.

Apêndices são textos elaborados pelo autor a fim de complementar sua argumentação. Anexos são os documentos não elaborados pelo autor, que servem de fundamentação, comprovação ou ilustração, como mapas, leis, estatutos etc.

ter 30 ago 2022 02:38:36: Linters pra Latex

Opções:

• lacheck: verificação mais simples, não faz exit(1) quando dá erro
• chktex: verificação mais ampla e faz exit(1) quando há errors

Referências

PhD. Jarbas

• (2016) ELM based signature for texture classification: https://www.sciencedirect.com/science/article/abs/pii/S0031320315003453
• (2018) Randomized neural network based signature for dynamic texture classification: https://www.sciencedirect.com/science/article/abs/pii/S0957417419303914
• (2019) Randomized neural network based descriptors for shape classification: https://www.sciencedirect.com/science/article/abs/pii/S0925231218306842
• (2020) Fusion of complex networks and randomized neural networks for

texture analysis https://www.sciencedirect.com/science/article/abs/pii/S0031320319304893

Conclusion of Fusion of CN + RNN => Texture Analysis (2020)

This paper presents an innovative approach of texture feature extraction based on the fusion of complex network and random- ized neural network. In the proposed method, a new approach to model the image as a CN that uses only one parameter is pre- sented. We also proposed a new way of characterizing the CN based on the idea of using the output weights of a random- ized neural network trained with topological properties of the CN. The obtained classification results on four databases outperformed other methods of the literature. Also, the proposed approach has an excellent trade-off between performance and size of the feature vectors. This demonstrates that the proposed approach is highly discriminative using the three feature vectors considered. In this way, this paper shows that the fusion of complex network and randomized neural network is a research field with great potential as a feasible texture analysis methodology

PhD. Verri

• Network Unfolding Map by Edge Dynamics Modeling: https://arxiv.org/abs/1603.01182
• Random Walk in Feature-Sample Networks for Semi-supervised Classification: https://ieeexplore.ieee.org/document/7839592

Pesquisa complementar

• Superpixel segmentation: A benchmark: https://www.sciencedirect.com/science/article/pii/S0923596517300735
• Semi-supervised Medical Image Segmentation through Dual-task Consistency: https://arxiv.org/abs/2009.04448
• Mask R-CNN: https://arxiv.org/abs/1703.06870