LaTeX templates and examples — Conference Paper

This is a skeleton file demonstrating the use of IEEEtran.cls (requires IEEEtran.cls version 1.8b or later) with an IEEE Computer Society conference paper. For other IEEE conferences, please see the IEEE conference paper template, and to find additional IEEE templates please use the tags below. IEEEtran.cls version: 1.8b

As instruções apresentadas neste texto objetivam auxiliar os autores na preparação de artigos a serem submetidos para a Revista Brasileira de Computação Aplicada (RBCA). Os artigos devem ser submetidos no modelo de formato nas versões Word ou LaTeX, disponíveis na página da revista. O resumo deve ser escrito em Português e não deve ultrapassar 200 palavras, utilizando fonte do tipo Times, tamanho 10, margens laterais reduzidas em 1 cm de cada lado, com duas linhas em branco antes e depois do resumo. Os autores deverão colocar três palavras-chave que destaquem os principais temas/áreas de pesquisa abordados no artigo. Caso o artigo seja escrito em língua inglesa a ordem do resumo/abstract deve ser invertida.

Official template for abstracts to be sent to the Sistedes series of conferences. These abstracts should summarize and give details of relevant, already published conference or journal papers. This template is based on the LNCS template, and includes the required license watermark required by the Sistedes Digital Library.

Template for Submission to IJCAI-19; downloaded from the conference's Author's Kit page.

Official template for regular papers (in Spanish) to be sent to the Sistedes series of conferences. This template is based on the LNCS template, and includes the required license watermark required by the Sistedes Digital Library.

Template for the Interactive Sonification (ISon) workshop proceedings.

Paper presented at ICCV 2019. This paper targets the task with discrete and periodic class labels (e.g., pose/orientation estimation) in the context of deep learning. The commonly used cross-entropy or regression loss is not well matched to this problem as they ignore the periodic nature of the labels and the class similarity, or assume labels are continuous value. We propose to incorporate inter-class correlations in a Wasserstein training framework by pre-defining (i.e., using arc length of a circle) or adaptively learning the ground metric. We extend the ground metric as a linear, convex or concave increasing function w.r.t. arc length from an optimization perspective. We also propose to construct the conservative target labels which model the inlier and outlier noises using a wrapped unimodal-uniform mixture distribution. Unlike the one-hot setting, the conservative label makes the computation of Wasserstein distance more challenging. We systematically conclude the practical closed-form solution of Wasserstein distance for pose data with either one-hot or conservative target label. We evaluate our method on head, body, vehicle and 3D object pose benchmarks with exhaustive ablation studies. The Wasserstein loss obtaining superior performance over the current methods, especially using convex mapping function for ground metric, conservative label, and closed-form solution.

AI4Treat at MICCAI template for abstracts

Modelo de TCC para alunos do Programa de Pós-Graduação em Automação Industrial e Sistemas Eletro-Eletrônicos