applsci-logo

Journal Browser

Journal Browser

Uncertainty Learning for Video Systems in Open Environment

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (20 July 2024) | Viewed by 1221

Special Issue Editors


E-Mail Website
Guest Editor
School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China
Interests: data mining; machine learning

E-Mail Website
Guest Editor
School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China
Interests: video processing; scene understanding; incremental learning; representation leaning

E-Mail Website
Guest Editor
Associate Professor, School of Artificial Intelligence, Hebei University of Technology, Tianjin, China
Interests: data mining; community detection; graph neural networks; knowledge modeling

E-Mail Website
Guest Editor
College of Intelligence and Computing, Tianjin University, Peiyang Park Campus, No.135 Yaguan Road, Haihe Education Park, Tianjin, China
Interests: machine learning; including multimodal learning; uncertainty; robustness and fairness in machine learning; machine learning in healthcare

Special Issue Information

Dear Colleagues,

Video processing has always been a frontier topic and an influential research direction in the field of machine computer vision. Most of the research in this field focuses on the use of intelligent technology to analyze the content of video sequences without human intervention, to detect, identify and track suspicious targets in video scenes, and to analyze the behavior of targets and understand the meaning of image content. At present, the method of "deep learning+big data" has achieved excellent recognition performance in many video tasks, and even exceeded the human intelligence level in some tasks. Essentially, knowledge for these video tasks is well estimated and modelled when sufficient data and effective tools are combined. However, in an open environment, due to the uncontrollable quality and content of surveillance data, dynamic changes in categories and data distribution, small amounts of labeled data, noise interference and other reasons, the existing methods show obvious shortcomings in generalization, robustness, interpretability, self-adaptability and other aspects. Therefore, open environment intelligent video processing faces a series of new research problems and needs to explore new theories, models and algorithms.

Therefore, this Special Issue is intended for the presentation of new ideas, advanced theories, and experimental results in the field of video processing, knowledge modeling and uncertainty learning. Topics of interest for this Special Issue include, but are not limited to, the following:

  • Video processing technologies, like detection, tracking, segmentation, etc.;
  • Video content understanding;
  • Natural scene understanding;
  • Knowledge discovery and data mining;
  • Knowledge graph;
  • Multimodal fusion;
  • Image processing, recognition and classification;
  • Model interpretability;
  • Uncertainty learning, open environment incremental learning and continual learning;
  • Multi-granularity feature learning;
  • Retroactive reasoning.

Prof. Dr. Youxi Wu
Dr. Linhao Li
Prof. Dr. Liang Yang
Dr. Changqing Zhang
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. Applied Sciences 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

  • video processing
  • uncertainty modeling
  • movement segmentation
  • knowledge discovery and data mining
  • multimodal fusion
  • 3D human pose estimation in video
  • image processing and recognition
  • model interpretability
  • fine-grained image classification
  • uncertainty learning
  • open environment incremental learning
  • continual learning
  • scene understanding
  • multi-granularity feature learning
  • knowledge graph
  • retroactive reasoning
  • knowledge graph completion

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

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

Research

18 pages, 5972 KiB  
Article
Image Generation with Global Photographic Aesthetic Based on Disentangled Generative Adversarial Network
by Hua Zhang, Muwei Wang, Lingjun Zhang, Yifan Wu and Yizhang Luo
Appl. Sci. 2023, 13(23), 12871; https://doi.org/10.3390/app132312871 - 30 Nov 2023
Viewed by 834
Abstract
Global photographic aesthetic image generation aims to ensure that images generated by generative adversarial networks (GANs) contain semantic information and have global aesthetic feelings. Existing image aesthetic generation algorithms are still in the exploratory stage, and images screened or generated by a computer [...] Read more.
Global photographic aesthetic image generation aims to ensure that images generated by generative adversarial networks (GANs) contain semantic information and have global aesthetic feelings. Existing image aesthetic generation algorithms are still in the exploratory stage, and images screened or generated by a computer have not yet achieved relatively ideal aesthetic quality. In this study, we use an existing generative model, StyleGAN, to build the height of image content and put forward a new method based on the GAN disentangled representation of a global aesthetic image generation algorithm by mining GANs’ latent space, potential global aesthetic feeling, and aesthetic editing of the original image to realize the aesthetic feeling and content of high-quality global aesthetic image generation. In contrast with the traditional aesthetic image generation methods, our method does not need to retrain GANs. Using the existing StyleGAN generation model, by learning a prediction model to score the generated image and the score as a label to learn a support vector machine decision surface, we use the learned decision to edit the original image to obtain an image with a global aesthetic feeling. This method solves the problems of poor content construction effect and poor global beauty of the aesthetic images generated by the existing methods. Experimental results show that the proposed method greatly increases the aesthetic score of the generated images and makes the generated images more in line with people’s aesthetic. Full article
(This article belongs to the Special Issue Uncertainty Learning for Video Systems in Open Environment)
Show Figures

Figure 1

Back to TopTop