Gallery — Two-column

计算机学报模板，在官方模板基础上修改，适配Overleaf XeLaTex环境，增加参考文献样式，同时修复一些bug。官方模板地址 https://cjc.ict.ac.cn/ Template for Chinese Journal of Computers. This version is modified based on the official version. It is now capable with Overleaf XeLaTeX. Official site: https://cjc.ict.ac.cn/

Template para o EduComp 2022

LaTeX Overleaf template for ACL-IJCNLP 2021 Note from Overleaf: SyncTeX will not work correctly with this template (as well as other templates based on similar underlying code, eg CVPR, EMNLP, etc) when the line numbers are active. To make SyncTeX function while authoring your manuscript, either on Overleaf or in your own LaTeX installation, the line numbers have to be turned off by uncommenting \aclfinalcopy.

Esta plantilla esta basada en el formato IEEE Journal. Es utilizada para fines formativos en la asignatura de física para estudiantes de la educación media.

12th Edition of the Language Resources and Evaluation Conference LaTeX template. Source: https://lrec2020.lrec-conf.org/en/submission2020/authors-kit/.

I am using this template to share with my students to start their term paper.

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.

Vietnamese IEEE Report Template

Lab 3 report following IEEE EEET2493