Advanced Vision Technologies That Mimic Human Visual Understanding

Dear Colleagues,

With the era of deep learning, the image recognition level of AI has nearly reached the human level. However, there is still a long way to go to understand the visual context of objects, indoor and outdoor environments, or medical images in the same ways humans perceive them.

This issue introduces studies that can take the level of visual understanding to the next level, using research papers that interpret visual data in a way similar to human visual understanding. The main topics of this issue are as follows:

• Deep learning-based visual understanding: This involves studies in areas such as image recognition, face recognition, environmental recognition, and medical image recognition that can identify and classify objects in images based on deep learning.
• Three-dimensional vision and depth detection: This involves studies on understanding spatial context in images or videos that mimic human depth perception in order for robots to share a living environment with humans.
• Visual understanding with natural language processing: This involves studies that implement agents that interact with humans by understanding images and videos or three-dimensional spaces by combining visual and language models.
• Creation using generative deep learning: This involves studies that can generate creative outcomes utilizing images, videos, or stories using generative deep learning models.

Prof. Dr. Hyunsik Ahn
Guest Editor

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. Biomimetics is an international peer-reviewed open access monthly 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 2200 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.

• visual understanding
• 3D vision
• depth detection
• generative deep learning
• mimicking human vision
• advanced vision
• medical image processing
• human–robot interaction