Search Results for author: Ankush Ganguly

Found 6 papers, 0 papers with code

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

no code implementations7 Oct 2022 Ananda Padhmanabhan Suresh, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly, Ukrit Watchareeruetai, Aubin Samacoits

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 language descriptions of the style.

Style Transfer

Amortized Variational Inference: A Systematic Review

no code implementations22 Sep 2022 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 problem.

Representation Learning Variational Inference

LOTR: Face Landmark Localization Using Localization Transformer

no code implementations21 Sep 2021 Ukrit Watchareeruetai, Benjaphan Sommana, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly, Aubin Samacoits, Samuel W. F. Earp, Nakarin Sritrakool

The proposed framework is a direct coordinate regression approach leveraging a Transformer network to better utilize the spatial information in the feature map.

Face Alignment Face Recognition

An Introduction to Variational Inference

no code implementations30 Aug 2021 Ankush Ganguly, Samuel W. F. Earp

In this paper, we introduce the concept of Variational Inference (VI), a popular method in machine learning that uses optimization techniques to estimate complex probability densities.

Generative Adversarial Network Variational Inference

Face Detection with Feature Pyramids and Landmarks

no code implementations2 Dec 2019 Samuel W. F. Earp, Pavit Noinongyao, Justin A. Cairns, Ankush Ganguly

Accurate face detection and facial landmark localization are crucial to any face recognition system.

Face Alignment Face Detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.