activity
20192022
most citedAmortized Variational Inference: A Systematic Review

28 citations · 73 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2022★ 10 cited

FastCLIPstyler: Optimisation-free Text-based Image Style Transfer Using Style Representations

Ananda Padhmanabhan Suresh, Sanjana Jain, Pavit Noinongyao +3

In recent years, language-driven artistic style transfer has emerged as a new type of style transfer technique, eliminating the need for a reference style image by using natural la…

cs.LG2022★ 28 cited

Amortized Variational Inference: A Systematic Review

Ankush Ganguly, Sanjana Jain, Ukrit Watchareeruetai

The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization…

cs.CV2021★ 4 cited

Development of a face mask detection pipeline for mask-wearing monitoring in the era of the COVID-19 pandemic: A modular approach

Benjaphan Sommana, Ukrit Watchareeruetai, Ankush Ganguly +4

During the SARS-Cov-2 pandemic, mask-wearing became an effective tool to prevent spreading and contracting the virus. The ability to monitor the mask-wearing rate in the population…

cs.CV2021★ 21 cited

LOTR: Face Landmark Localization Using Localization Transformer

Ukrit Watchareeruetai, Benjaphan Sommana, Sanjana Jain +5

This paper presents a novel Transformer-based facial landmark localization network named Localization Transformer (LOTR). The proposed framework is a direct coordinate regression a…

cs.LG2021★ 1 cited

An Introduction to Variational Inference

Ankush Ganguly, Samuel W. F. Earp

Approximating complex probability densities is a core problem in modern statistics. In this paper, we introduce the concept of Variational Inference (VI), a popular method in machi…

cs.CV2019★ 9 cited

Face Detection with Feature Pyramids and Landmarks

Samuel W. F. Earp, Pavit Noinongyao, Justin A. Cairns +1

Accurate face detection and facial landmark localization are crucial to any face recognition system. We present a series of three single-stage RCNNs with different sized backbones…