Dear Colleagues,

Visual object tracking and segmentation are both essential components of perception, and taken together they have become an active research topic in the computer vision community over the decades. Visual object tracking and segmentation algorithms have developed rapidly thanks to the massive amount of video data that in turn creates high demand for the speed and accuracy of tracking algorithms. Researchers are motivated to design faster and better methods in spite of the challenges that exist in visual object tracking and segmentation, especially robustness when it comes to heavy occlusions, fast motion, accurate localization, mult-object tracking, and low-resolution. Despite the success in addressing numerous challenges under a wide range of circumstances, the core problems remain complex and challenging.

This main aim of this Special lssue will be to focus on the most recent advancements and trends in visual object tracking and segmentation. Methods such as those reported in the formulation of Siamese networks and spatial-temporal memory for VOT and VOS may be further explored to improve performance. We invite original research work involving novel technigues, innovative methods, and useful applications that lead to significant advances in VOT and VOS. We also welcome reviews and surveys on state-of-the-art methods. Topics of interest include, but are not limited to:

1. Object detection, identification, recognition, tracking, and segmentation.
2. Video analysis and tracking.
3. Image and video enhancement algorithms to improve the quality of video object tracking.
4. Computational photography and imaging for advanced object detection and tracking.
5. Depth estimation and three-dimensional reconstruction for augmented reality (AR) and/or advanced driver assistance systems (ADAS).
6. Learning data representation from video based on supervised, unsupervised, and semi-supervised learning.
7. Dataset and performance evaluation, person re-identification, and vehicle re-identification.
8. Human behavior detection, human pose estimation, and tracking.
9. Visual surveillance and monitoring.

Prof. Dr. Kaihua Zhang
Dr. Francesco Camastra
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. Information 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 1600 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 object tracking
• image segmentation
• pose estimation
• image and video enhancement

Title: A Comprehensive Survey on the Effectiveness of Sharpness Aware Minimization and its Progressive Derivative
Authors: Chen-Chien James Hsu
Affiliation: National Taiwan Normal University
Abstract: With the ongoing development of larger and more sophisticated AI models to improve performance, the challenge persists in effectively preventing overfitting of overparametrized Neural Networks to training data. Despite the presence of various regularization techniques aimed at mitigating this issue, poor generalization remains a concern, especially when handling diverse and limited data. This paper explores one of the latest and most promising strategies to address this challenge, Sharpness Aware Minimization (SAM), which concurrently minimizes loss value and sharpness-related loss. While this method exhibits substantial effectiveness, it comes with a notable trade-off in increased training time. Consequently, several variants of SAM have emerged to alleviate these limitations and bolster model performance. This survey paper critically examines the significant advancements achieved by SAM, delves into its constraints, categorizes recent progressive variants, and identifies avenues for further progress to augment current State-of-the-Art results.