Gallery — Recent

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.

Reseña del Autor del premio Nobel

Micromouse Symposium article template.

Modelo de Avaliação em LaTeX desenvolvido para o IFPR, campus Paranavaí.

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

Template for a physics thesis that has been passed down through the department a few times, with Benjamin Hornberger apparently being the original author. Should hopefully still be compliant with formatting guidelines.

首都大学東京システムデザイン学部情報通信システムコース卒論用テンプレート Faculty of Tokyo System Design, Tokyo Metropolitan University Information and Communication System Course Graduation Template

Plantilla para las contribuciones al Simposio de Control Inteligente. Basado en la plantilla de RIAI.

This is the official Virginia Tech letterhead template. This template is designed to be easily modified so that it can be used by anyone at VT for composing professional business communications according to the VT branding guidelines. Add your own information and text to the template to send a custom message.