{overleaf skabelonsgalleri}LaTeX templates and examples — Recent

Software Requirements Specification

This repository contains LaTeX template for NIT Trichy's M.S. (By Research)/PhD Thesis. This template has been created considering latest guidelines. The first prepared thesis using this template was submitted and accepted by MS/PhD section in May 2019. This template can also be used by B.Tech./M.Tech. students for their thesis preparation.

A template for creating a beamer talk.

Template de Proposta de Dissertação do PGCC/UEFS - Programa de Pós-Graduação em Ciência da Computação da Universidade Estadual de Feira de Santana.

Anchal Srivastava's CV. Created using the AltaCV template.

Report template for students of TU Delft's course TI3115TU Software Engineering and Methods, part of the Minor Computer Science.

Rupal Lohani's CV (a sample CV for a Undergraduate BTECH student). Created with the AltaCV template.

Customizações do abnTeX2 para o Instituto Federal de Minas Gerais - Campus Avançado Arcos

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.