With the development of 3D and 2D data acquisition techniques, it has become easy to obtain point clouds and images of scenes simultaneously, which further facilitates dual-modal semantic segmentation. Most existing methods for simultaneously segmenting point clouds and images rely heavily on the quantity and quality of the labeled training data. However, massive point-wise and pixel-wise labeling procedures are time-consuming and labor-intensive. To address this issue, we propose a parallel dual-stream network to handle the semi-supervised dual-modal semantic segmentation task, called PD-Net, by jointly utilizing a small number of labeled point clouds, a large number of unlabeled point clouds, and unlabeled images. The proposed PD-Net consists of two parallel streams (called original stream and pseudo-label prediction stream). The pseudo-label prediction stream predicts the pseudo labels of unlabeled point clouds and their corresponding images. Then, the unlabeled data is sent to the original stream for self-training. Each stream contains two encoder-decoder branches for 3D and 2D data respectively. In each stream, multiple dual-modal fusion modules are explored for fusing the dual-modal features. In addition, a pseudo-label optimization module is explored to optimize the pseudo labels output by the pseudo-label prediction stream. Experimental results on two public datasets demonstrate that the proposed PD-Net not only outperforms the comparative semi-supervised methods but also achieves competitive performances with some fully-supervised methods in most cases.

Existing camera-based 3D object detection methods yield inaccurate position, scale, and orientation results due to the inherent challenge of ill-posed depth estimation from 2D images. Recent research has demonstrated that pre-training depth estimation from a single frame substantially enhances the quality of camera-based 3D object detection. We hypothesize that integrating multi-view stereo matching technology into the pretraining process can equip the backbone model with superior geometric feature extraction capabilities, thereby further improving 3D object detection performance. Building upon this premise, we propose MVS3D, a novel depth estimation pre-training method for camera-based 3D object detection. MVS3D incorporates a VMS (Video-stream-based Multi-view Stereo) module and a PME (Pose and Motion Estimation) module, which collectively encourage the backbone to explicitly learning 3D geometric information from image streams through stereo matching. Our method enables existing camera-based 3D object detection frameworks to seamlessly integrate our pre-trained backbone weight, thereby enhancing detection performance without necessitating extensive modifications. Extensive experimental results on nuScenes dataset show that loading the pre-trained weight from MVS3D can significantly improve the mean average precision (mAP) and nuScenes detection score (NDS) of both existing single-frame and multi-frame camera-based methods.

Rotation averaging, which aims to calculate the absolute rotations of a set of cameras from a redundant set of their relative rotations, is an important and challenging topic arising in the study of structure from motion. A central problem in rotation averaging is how to alleviate the influence of noise and outliers. Addressing this problem, we investigate rotation averaging under the Cayley framework in this paper, inspired by the extra-constraint-free nature of the Cayley rotation representation. Firstly, for the relative rotation of an arbitrary pair of cameras regardless of whether it is corrupted by noise/outliers or not, a general Cayley rotation constraint equation is derived for reflecting the relationship between this relative rotation and the absolute rotations of the two cameras, according to the Cayley rotation representation. Then based on such a set of Cayley rotation constraint equations, a Cayley-based approach for Rotation Averaging is proposed, called CRA, where an adaptive regularizer is designed for further alleviating the influence of outliers. Finally, a unified iterative algorithm for minimizing some commonly-used loss functions is proposed under this approach. Experimental results on 16 real-world datasets and multiple synthetic datasets demonstrate that the proposed CRA approach achieves a better accuracy in comparison to several typical rotation averaging approaches in most cases.

3D point cloud semantic segmentation is a challenging topic in the computer vision field. Most of the existing methods in literature require a large amount of fully labeled training data, but it is extremely time-consuming to obtain these training data by manually labeling massive point clouds. Addressing this problem, we propose a superpoint-guided semi-supervised segmentation network for 3D point clouds, which jointly utilizes a small portion of labeled scene point clouds and a large number of unlabeled point clouds for network training. The proposed network is iteratively updated with its predicted pseudo labels, where a superpoint generation module is introduced for extracting superpoints from 3D point clouds, and a pseudo-label optimization module is explored for automatically assigning pseudo labels to the unlabeled points under the constraint of the extracted superpoints. Additionally, there are some 3D points without pseudo-label supervision. We propose an edge prediction module to constrain features of edge points. A superpoint feature aggregation module and a superpoint feature consistency loss function are introduced to smooth superpoint features. Extensive experimental results on two 3D public datasets demonstrate that our method can achieve better performance than several state-of-the-art point cloud segmentation networks and several popular semi-supervised segmentation methods with few labeled scenes.

Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide an insight into spatial manipulation modules. Firstly, we find that the smaller the rotational degree of freedom (RDF) of objects is, the more easily these objects are handled by these DNNs. Then, we investigate the effect of the popular T-Net module and find that it could not reduce the RDF of objects. Motivated by the above two issues, we propose a rotation transformation network for point cloud analysis, called RTN, which could reduce the RDF of input 3D objects to 0. The RTN could be seamlessly inserted into many existing DNNs for point cloud analysis. Extensive experimental results on 3D point cloud classification and segmentation tasks demonstrate that the proposed RTN could improve the performances of several state-of-the-art methods significantly.

N6-methyladenosine (m6A) is the most abundant posttranscriptional modification in mammalian mRNA molecules and has a crucial function in the regulation of many fundamental biological processes. The m6A modification is a dynamic and reversible process regulated by a series of writers, erasers and readers (WERs). Different WERs might have different functions, and even the same WER might function differently in different conditions, which are mostly due to different downstream genes being targeted by the WERs. Therefore, identification of the targets of WERs is particularly important for elucidating this dynamic modification. However, there is still no public repository to host the known targets of WERs. Therefore, we developed the m6A WER target gene database (m6A2Target) to provide a comprehensive resource of the targets of m6A WERs. M6A2Target provides a user-friendly interface to present WER targets in two different modules: 'Validated Targets', referred to as WER targets identified from low-throughput studies, and 'Potential Targets', including WER targets analyzed from high-throughput studies. Compared to other existing m6A-associated databases, m6A2Target is the first specific resource for m6A WER target genes. M6A2Target is freely accessible at http://m6a2target.canceromics.org.

How to learn long-range dependencies from 3D point clouds is a challenging problem in 3D point cloud analysis. Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named as GA-Net, consisting of a point-independent global attention module and a point-dependent global attention module for obtaining contextual information of 3D point clouds in this paper. The point-independent global attention module simply shares a global attention map for all 3D points. In the point-dependent global attention module, for each point, a novel random cross attention block using only two randomly sampled subsets is exploited to learn the contextual information of all the points. Additionally, we design a novel point-adaptive aggregation block to replace linear skip connection for aggregating more discriminate features. Extensive experimental results on three 3D public datasets demonstrate that our method outperforms state-of-the-art methods in most cases.

This paper proposes a new method for document categorization, based on support vector machine (SVM) using a concept vector model (CVM). The traditional document classification usually ignores the semantic relations among the keywords or documents. To effectively solve the semantic problem, the domain ontology is used to capture the semantic information among different terms or keywords in the documents. Using the concept vector model, domain-related semantic information more exactly from documents can be extracted. In the model, concept vector is extracted from a document by the matching method. According to concept features of the documents, documents are classified into a suitable category by SVM. The experimental results show that our CVM method yields higher accuracy compared to the traditional term-based vector space model (VSM) methods

When the information superhighway arrives at the neighborhood, a residential network will connect home appliances to the community access network. These appliances include personal computers, printers, and video clients. Among all local-area network (LAN) protocols, Ethernet is the most economic and the most popular. The unique characteristics of residential networks call for new performance studies. A residential network typically has few nodes and runs different applications than business and academic LANs. Consequently, residential networks have traffic characteristics different from the subject of existing studies. We constructed a residential network testbed to collect typical application traffic statistics. Additional live traffic characterization was obtained from campus networks. Also, we investigated the suitability of Ethernet for video distribution through simulation. This paper discusses the design issues for residential networks and presents a network design that is based on Ethernet technology. Traffic models are established from the actual traffic traces and used for the performance evaluation of residential networks. Furthermore, several future data traffic scenarios are considered with bandwidth up to 6 Mb/s by scaling up current data traffic. The simulation results of the performance suggest that Ethernet can be used as a cost-effective residential network for video and data communications.