State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China
Dr. Lin Zhou
State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China
Robust visual tracking is one of the most challenging problems in computer vision applications. However, the limited training data and the computational complexity have severely affected tracking performance. In this paper, we propose an Auto-Encoder pair model for visual tracking which is composed of source domain network and target domain network to help a more accurate localization. We adopt the dense circular samples of the object state to increase the number of training samples and prevent model overfitting. Meanwhile, a difference regularization term is also introduced into our framework to penalize the large appearance variations of the object in two domains. The alternating optimization is used to solve the optimization problems. Furthermore, our method alleviates the model update problem and improves the tracking speed by using long-term and short-term updating scheme. In addition, the target domain filter is updated by introducing the updated source domain filter to avoid the object drift. Comprehensive experiments on some challenging benchmarks demonstrate that our approach concurrently improves both tracking accuracy and speed.
Organs in the human body exist within a highly integrated and dynamically interacting environment, and their interactions are critical for maintaining normal physiological processes. Traditional cell culture models and animal models fail to meet the needs of preclinical research, as they struggle to fully recapitulate in vivo physiology and pathology. Thus, innovative in vivo platforms are urgently needed to bridge the gaps between preclinical research and clinical translation. Multiorgan-on-a-chip (multi-OoC), an emerging field in bioengineering, offers precise control over cellular microenvironments and recapitulates organ-level functions and interorgan crosstalk. By mimicking complex human physiology and pathophysiology, multi-OoC systems provide novel opportunities for disease modeling, drug discovery, and personalized medicine. This paper will systematically elaborate on the necessity of developing multi-OoC systems, delve into their structural design and biomanufacturing strategies, and highlight their recent applications in biomedical research. Additionally, it will analyze key challenges such as the establishment of standardized operating procedures and the validation of model outputs, and envision their application prospects in the field of personalized medicine. The aim is to provide a reference for promoting the standardization and clinical translation of this technology.