Artificial Intelligence in Vision Modelling

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 31 December 2024 | Viewed by 740

Special Issue Editors


E-Mail Website
Guest Editor
Senior Staff Scientist, Lawrence Livermore National Lab, Livermore, CA 94550, USA
Interests: machine learning; computer vision; artificial intelligence; deep learning

E-Mail Website
Guest Editor
Lawrence Livermore National Laboratory, Livermore, Livermore, CA 94550, USA
Interests: time series; applied machine learning

Special Issue Information

Dear Colleagues,

In the era of deep and machine learning, multi-task and multi-modal learning have been explored separately. However, in most practical scenarios, we often require solving several tasks while the data consists of multiple modalities, e.g., image and text, image and temporal information, and many more. In this Special Issue, we will focus on theory and applications involving multi-modalities and multi-task applications. More specifically, we will encourage authors to submit manuscripts containing novel techniques for optimization in the setting of multi-task learning while the data sources span across different modalities. We will focus on articles demonstrating novel techniques to structure latent space in a multi-modal/multi-task setting. Often, when dealing with multi-modal data, we need to place additional geometric constraints on the latent space. Hence, articles dealing with novel geometric techniques to achieve the above are highly encouraged.

Dr. Rudrasis Chakraborty
Dr. Indrasis Chakraborty
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • multi-task learning
  • multi-modalities
  • latent representation
  • geometric representation

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

28 pages, 5142 KiB  
Article
Multi-Stream Isolated Sign Language Recognition Based on Finger Features Derived from Pose Data
by Ali Akdag and Omer Kaan Baykan
Electronics 2024, 13(8), 1591; https://doi.org/10.3390/electronics13081591 - 22 Apr 2024
Viewed by 381
Abstract
This study introduces an innovative multichannel approach that focuses on the features and configurations of fingers in isolated sign language recognition. The foundation of this approach is based on three different types of data, derived from finger pose data obtained using MediaPipe and [...] Read more.
This study introduces an innovative multichannel approach that focuses on the features and configurations of fingers in isolated sign language recognition. The foundation of this approach is based on three different types of data, derived from finger pose data obtained using MediaPipe and processed in separate channels. Using these multichannel data, we trained the proposed MultiChannel-MobileNetV2 model to provide a detailed analysis of finger movements. In our study, we first subject the features extracted from all trained models to dimensionality reduction using Principal Component Analysis. Subsequently, we combine these processed features for classification using a Support Vector Machine. Furthermore, our proposed method includes processing body and facial information using MobileNetV2. Our final proposed sign language recognition method has achieved remarkable accuracy rates of 97.15%, 95.13%, 99.78%, and 95.37% on the BosphorusSign22k-general, BosphorusSign22k, LSA64, and GSL datasets, respectively. These results underscore the generalizability and adaptability of the proposed method, proving its competitive edge over existing studies in the literature. Full article
(This article belongs to the Special Issue Artificial Intelligence in Vision Modelling)
Show Figures

Figure 1

Back to TopTop