Anil K. Shrestha

Papers

Abstract

Virtual Try-On (trying clothes virtually) is a promising application of the Generative Adversarial Network (GAN). However, it is arduous to transfer the desired clothing item onto the corresponding regions of a human body because of varying body size, pose, and occlusions like hair and overlapped clothes. This paperaims to produce photo-realistic translated images through semantic segmentation and a generative adversarial architecture-based image translation network. We present a novel image-based Virtual Try-On application VTON-IT that takesan RGB image, segments desired body part, and overlays target cloth over thesegmented body region. Most state-of-the-art GAN-based Virtual Try-On appli-cations produce unaligned pixelated synthesis images on real-life test images.However, our approach generates high-resolution natural images with detailedtextures on such variant images.

Comparison of Virtual Machines and Containers for Small and Medium Enterprises (SMEs)

[2020]

Abstract

Even as cloud computing stakes its claim as one of the most vital technologies of this era, businesses still hesitate to adopt it. It is to be expected that the myriad choices presented by cloud platforms may be intimidating. One of the most important of these is perhaps the choice of virtualization technologies. In this paper we evaluate the suitability of two different virtualization technologies - containers and Virtual Machines (VMs) - insofar as they could help Small and Medium Enterprises (SMEs) adopt and succeed in a cloud-based paradigm. We come to a decision based on several comparative tests and a thorough study of related literature.

Implementation of HCI Principles in a Web-based Instant Messenger Application

[2019]

Abstract

This study developed and evaluated a user-friendly web-based instant messaging (IM) application aimed at novice to intermediate users. By applying modern Human-Computer Interaction (HCI) principles, we focused on enhancing usability and communication efficiency. Our methodology included user surveys, laboratory-style tests, heuristic evaluations, and think-aloud protocols, complemented by heat map analysis. Participants performed common IM tasks such as creating accounts, adding contacts, and sending messages. Think-aloud sessions provided qualitative insights, while heuristic evaluations based on Shneiderman’s eight golden rules ensured adherence to key HCI principles. Results showed that combining a familiar interface with intuitive features and consistent feedback significantly improved user satisfaction. This research demonstrates that the applied HCI techniques can enhance user experience in communication platforms, providing valuable insights for future IM application development.