Transformers in Computer Vision
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".
Deadline for manuscript submissions: closed (30 September 2023) | Viewed by 3835
Special Issue Editors
Interests: 5G/B5G/6G; space-air-ground integrated network (SAGIN); AI-enabled 6G networks; deep-learning-based HIDS & NIDS; smart transportation
Special Issue Information
Dear Colleagues,
Currently, state-of-the-art research in computer vision is heavily focused on deep learning approaches, particularly significant breakthroughs in various tasks based on transformer architecture. Object detection and recognition is a key area of research, with significant progress being made in developing models that can accurately identify and locate objects in images and videos. Additionally, image and video analysis is a popular area of research, with many recent developments in action recognition, video segmentation, and activity detection. Another important area of research is 3D reconstruction and scene understanding, which involves creating 3D models of objects and scenes from 2D images. Deep learning techniques are also being used to improve the performance of medical image analysis, such as tumor detection and segmentation in medical scans. Finally, computer vision for autonomous systems, such as self-driving cars and drones, is also an active area of research, with ongoing work on object detection, scene understanding, and motion planning.
Topics include but are not limited to:
- Transformer architectures for object detection and recognition
- Transformer-based face applications, such as face recognition systems and multiple-object tracking systems.
- Transformer-based approaches for image segmentation
- Transformer-based models for video analysis and action recognition
- Transformer-based models for 3D object detection
- Transformer-based models for panoptic segmentation
- Multi-modal transformer models for image–text understanding
- Transformer-based models for image synthesis and style transfer
- Transformer-based models for image super-resolution
- Transformer-based models for image captioning and text-to-image synthesis
- Transformer-based models for video synthesis and action generation
Prof. Dr. Ren-Hung Hwang
Dr. Chen-Kuo Chiang
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. Sensors 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 2600 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
- computer vision
- deep learning
- transformer
