{overleaf template gallery}Community articles — Recent

Vinayak Goel's Résumé. Created with the Deedy CV template.

Math project.

This is a project for Calculus 2 students at Fitchburg State University. This project walks students through two examples of using definite integrals to determine the volume of objects: a bundt cake serves as the solid of revolution and the students build a structure from play dough that is not a solid of revolution.

My first CV

Using WebRTC we are trying to develop a prod- uct called 'Ping' used for audio, mult-video, file and screen sharing. Ping uses WebRTC for the source of data exchange and XMPP Server for signalling and transporting. Ping works on Browser to Browser connections instead of naive client server approach. Ping guarentees high scalability and upto 60% more efficiency than existin

Trabajo monográfico sobre cualquiera de los temas de la asignatura utilizando las herramientas de trabajo colaborativo de Google

Computer vision systems can be applied to a wide variety of tasks, but some of the most interesting are those related with security and surveillance. Within this group, our application for Video Surveillance for Road Traffic Monitoring can be placed. We propose a solution based on machine learning and video analysis techniques that involves the whole process: database evaluation, background estimation, foreground segmentation, video stabilization and object tracking. As a result of this, our system will be able to monitorize some basic parameters of traffic flow as vehicles counting or speed estimation.

Livro Adaptado da Apostila do Rev. Everton Barcelos Tokashiki para Classes de Novos Membros da Igreja Presbiteriana do Brasil.

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.