Anomaly detection in surveillance videos is a challenging task due to the diversity of anomalous video content and duration. In this paper, we consider video anomaly detection as a regression problem with respect to anomaly scores of video clips under weak supervision. Hence, we propose an anomaly detection framework, called Anomaly Regression Net (AR-Net), which only requires video-level labels in training stage. Further, to learn discriminative features for anomaly detection, we design a dynamic multiple-instance learning loss and a center loss for the proposed AR-Net. The former is used to enlarge the inter-class distance between anomalous and normal instances, while the latter is proposed to reduce the intra-class distance of normal instances. Comprehensive experiments are performed on a challenging benchmark: Shang-haiTech. Our method yields a new state-of-the-art result for video anomaly detection on ShanghaiTech dataset.
The integration of hierarchical structure, chemistry, and functional activity within tissue‐engineered scaffolds is of great importance in mimicking native bone tissue. Bone is a highly mineralized tissue which forms at ambient conditions by continuous crystallization of the mineral phase within an organic matrix in the presence of bone residing cells. Despite recent advances in the biofabrication of complex engineered tissues, replication of the heterogeneity of bone microenvironments has been a major challenge in constructing biomimetic bone scaffolds. Herein, inspired by the bone biomineralization process, the first example of bone mimicking constructs by 3D writing of a novel apatite‐transforming ink in a supportive microgel matrix with living cells is demonstrated. Using this technique, complex bone‐mimicked constructs are made at room temperature without requiring invasive chemicals, radiation, or postprocessing steps. This study demonstrates that mineralized constructs can be deposited within a high density of stem cells, directing the cellular organization, and promoting osteogenesis in vitro. These findings offer a new strategy for fabrication of bone mimicking constructs for bone tissue regeneration with scope to generate custom bone microenvironments for disease modeling, multicellular delivery, and in vivo bone repair.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.