Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves global information by employing an adaptive and efficient selection strategy. The Refining component ameliorates previous results with the contexts stored in the Memory by adopting a spatial-temporal attention mechanism for feature distilling. Experiments on the KITTI and TUM-RGBD benchmark datasets demonstrate that our method outperforms state-of-the-art learning-based methods by a large margin and produces competitive results against classic monocular VO approaches. Especially, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic VO algorithms tend to fail.
We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks. Different from current monocular visual odometry methods, our approach is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we propose a dual-branch recurrent network to learn the rotation and translation separately by leveraging current Convolutional Neural Network (CNN) for feature representation and Recurrent Neural Network (RNN) for image sequence reasoning. To enhance the ability of feature selection, we further introduce an effective context-aware guidance mechanism to force each branch to distill related information for specific motion pattern explicitly. Experiments demonstrate that on the prevalent KITTI and ICL NUIM benchmarks, our method outperforms current state-of-theart model-and learning-based methods for both decoupled and joint camera pose recovery.
We propose a novel 3D spatial representation for data fusion and scene reconstruction. Probabilistic Signed Distance Function (Probabilistic SDF, PSDF) is proposed to depict uncertainties in the 3D space. It is modeled by a joint distribution describing SDF value and its inlier probability, reflecting input data quality and surface geometry. A hybrid data structure involving voxel, surfel, and mesh is designed to fully exploit the advantages of various prevalent 3D representations. Connected by PSDF, these components reasonably cooperate in a consistent framework. Given sequential depth measurements, PSDF can be incrementally refined with less ad hoc parametric Bayesian updating. Supported by PSDF and the efficient 3D data representation, high-quality surfaces can be extracted on-the-fly, and in return contribute to reliable data fusion using the geometry information. Experiments demonstrate that our system reconstructs scenes with higher model quality and lower redundancy, and runs faster than existing online mesh generation systems.
Articular cartilage (AC) has a very limited intrinsic repair capacity after injury or disease. Although exogenous cell-based regenerative approaches have obtained acceptable outcomes, they are usually associated with complicated procedures, donor-site morbidities and cell differentiation during ex vivo expansion. In recent years, endogenous regenerative strategy by recruiting resident mesenchymal stem/progenitor cells (MSPCs) into the injured sites, as a promising alternative, has gained considerable attention. It takes full advantage of body's own regenerative potential to repair and regenerate injured tissue while avoiding exogenous regenerative approachassociated limitations. Like most tissues, there are also multiple stem-cell niches in AC and its surrounding tissues. These MSPCs have the potential to migrate into injured sites to produce replacement cells under appropriate stimuli. Traditional microfracture procedure employs the concept of MSPCs recruitment usually fails to regenerate normal hyaline cartilage. The reasons for this failure might be attributed to an inadequate number of recruiting cells and adverse local tissue microenvironment after cartilage injury. A strategy that effectively improves local matrix microenvironment and recruits resident MSPCs may enhance the success of endogenous AC regeneration (EACR). In this review, we focused on the reasons why AC cannot regenerate itself in spite of potential self-repair capacity and summarized the latest developments of the three key components in the field of EACR. In addition, we discussed the challenges facing in the present EACR strategy. This review will provide an increasing understanding of EACR and attract more researchers to participate in this promising research arena.
A promising approach to the next generation of low-power, functional, and energy-efficient electronics relies on novel materials with coupled magnetic and electric degrees of freedom. In particular, stripy antiferromagnets often exhibit broken crystal and magnetic symmetries, which may bring about the magnetoelectric (ME) effect and enable the manipulation of intriguing properties and functionalities by electrical means. The demand for expanding the boundaries of data storage and processing technologies has led to the development of spintronics toward two-dimensional (2D) platforms. This work reports the ME effect in the 2D stripy antiferromagnetic insulator CrOCl down to a single layer. By measuring the tunneling resistance of CrOCl on the parameter space of temperature, magnetic field, and applied voltage, we verified the ME coupling down to the 2D limit and unraveled its mechanism. Utilizing the multi-stable states and ME coupling at magnetic phase transitions, we realize multi-state data storage in the tunneling devices. Our work not only advances the fundamental understanding of spin-charge coupling, but also demonstrates the great potential of 2D antiferromagnetic materials to deliver devices and circuits beyond the traditional binary operations.
BackgroundVenous thromboembolism (VTE) after hip or knee arthroplasty has attracted increasing attention over the past few decades. However, there is no bibliometric report on the publications in this field. The purpose of this study was to analyze the global research status, hotspots, and trends in VTE after arthroplasty.MethodsAll articles about VTE research after hip or knee arthroplasty from 1990 to 2021 were retrieved from the Web of Science Core Collection database. The information of each article including citation, title, author, journal, country, institution, keywords, and level of evidence was extracted for bibliometric analysis.ResultsA total of 1,245 original articles from 53 countries and 603 institutions were retrieved. The USA contributed most with 457 articles, followed by England and Canada. McMaster University in Canada was the leading institution for publications. The journals with the highest output and citation were the Journal of Arthroplasty and the Thrombosis and Haemostasis, respectively. The median number of citations was significantly different among the levels of evidence (F = 128.957, P < 0.001). The research hotspots switched from VTE diagnosis and heparin to factor Xa inhibitors (fondaparinux, rivaroxaban, apixaban) and direct thrombin inhibitors (dabigatran etexilate, ximelagatran), and finally to aspirin, risk factor studies, which can be observed from the keyword analysis and co-cited reference cluster analysis.ConclusionsThis study observed an increasing trend of research articles on VTE after arthroplasty. Publications with higher levels of evidence gained further popularity among researchers and orthopedic surgeons. Additionally, individualized VTE prevention and the development of new, safe, effective, and inexpensive oral agents would be emerging trends in the future.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.