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.

template for EE8001

Lab exercise on LaTeX basic formatting commands.

usmthesis is a LaTeX class for typesetting a Universiti Sains Malaysia (USM) postgraduate research thesis. (Updated December 8, 2016 with a bunch of new document class options you can use to mix-and-match various settings required by IPS for different candidates. Please read the comments in usmthesis.tex.) There will be no further updates until an official updated formatting guidelines with concrete clear instructions is available. Copyright (C) 2005-2016 Lim Lian Tze Website: http://liantze.penguinattack.org/latextypesetting.html Github: https://github.com/liantze/usmthesis

Mathematical Induction paper

Syed Ishtiaque Ahmed's CV

Es un resultado de la mecánica Hamiltoniana sobre la evolución temporal de un sistema mecánico. Un conjunto de partículas con condiciones iniciales cercanas pueden representarse por la región conexa que ocupa en el espacio de fase. El teorema establece que dicha región mantendrá invariante su volumen a pesar de que se estirar y se encogerá a medida que cada partícula evolucione

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

A template in Swedish for a Bachelor Thesis at the Division of Statistics and Machine Learning at Linköping University.