We present a novel self-supervised Contrastive LEArning framework for single-cell ribonucleic acid (RNA)-sequencing (CLEAR) data representation and the downstream analysis. Compared with current methods, CLEAR overcomes the heterogeneity of the experimental data with a specifically designed representation learning task and thus can handle batch effects and dropout events simultaneously. It achieves superior performance on a broad range of fundamental tasks, including clustering, visualization, dropout correction, batch effect removal, and pseudo-time inference. The proposed method successfully identifies and illustrates inflammatory-related mechanisms in a COVID-19 disease study with 43 695 single cells from peripheral blood mononuclear cells.

The key challenge in processing point clouds lies in the inherent lack of ordering and irregularity of the 3D points. By relying on perpoint multi-layer perceptions (MLPs), most existing point-based approaches only address the first issue yet ignore the second one. Directly convolving kernels with irregular points will result in loss of shape information. This paper introduces a novel point-based bidirectional learning network (BLNet) to analyze irregular 3D points. BLNet optimizes the learning of 3D points through two iterative operations: feature-guided point shifting and feature learning from shifted points, so as to minimise intra-class variances, leading to a more regular distribution. On the other hand, explicitly modeling point positions leads to a new feature encoding with increased structure-awareness. Then, an attention pooling unit selectively combines important features. This bidirectional learning alternately regularizes the point cloud and learns its geometric features, with these two procedures iteratively promoting each other for more effective feature learning. Experiments show that BLNet is able to learn deep point features robustly and efficiently, and outperforms the prior state-of-the-art on multiple challenging tasks.

This paper proposes a new 3D multi-object tracker to more robustly track objects that are temporarily missed by detectors. Our tracker can better leverage object features for 3D Multi-Object Tracking (MOT) in point clouds. The proposed tracker is based on a novel data association scheme guided by prediction confidence, and it consists of two key parts. First, we design a new predictor that employs a constant acceleration (CA) motion model to estimate future positions, and outputs a prediction confidence to guide data association through increased awareness of detection quality. Second, we introduce a new aggregated pairwise cost to exploit features of objects in point clouds for faster and more accurate data association. The proposed cost consists of geometry, appearance and motion components. Specifically, we formulate the geometry cost using resolutions (lengths, widths and heights), centroids, and orientations of 3D bounding boxes (BBs), the appearance cost using appearance features from the deep learning-based detector backbone network, and the motion cost by associating different motion vectors. Extensive multi-object tracking experiments on the KITTI tracking benchmark demonstrated that our method outperforms, by a large margin, the state-of-the-art methods in both tracking accuracy and speed.

Fully exploring correlation among points in point clouds is essential for their feature modeling. This paper presents a novel end-to-end graph model, named Point2Node, to represent a given point cloud. Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features. Specifically, first, to fully explore the spatial correlation among points for enhanced feature description, in a high-dimensional node graph, we dynamically integrate the node's correlation with self, local, and non-local nodes. Second, to more effectively integrate learned features, we design a data-aware gate mechanism to self-adaptively aggregate features at the channel level. Extensive experiments on various point cloud benchmarks demonstrate that our method outperforms the state-of-the-art.

The Markov chain based model by Bianchi for IEEE802.11 distributed controlled access is a highly accurate analytical tool for estimating the system throughput when a single Basic Service Set (BSS) network operates in isolation. However, with the increase of wireless LAN access points being deployed on the same area, an environment with multiple BSS interfering with each other has become the default network scenario. The purpose of this work is to extend the single BSS Markov chain model into a multi-BSS model by incorporating the influence of STAs' interference range and carrier sense range to their own transmission and collision probabilities. We verify the proposed multi-BSS analytical model using the latest version of the ns-3 simulator which has recently supported accurate PHY abstractions for multi-BSS simulation. We show that the proposed model has a high accuracy (within 1%) independent of the multi-BSS network topology.

In visualization, user guidance has become an essential concept to aid users in making informed decisions ranging from what subsets to focus on in the data space to which regions to explore in the view space. To guide users, predominantly visual cues like colors or arrows are used to indicate particular targets or directions. In this paper, we explore the possibility of another sensory channel for guidance cues: vibrotactile feedback. To that end, we explore different properties of the vibrotactile channel (e.g., amplitude and duration) and discuss their potential use as guidance cues. We then report on an experiment (N=14) in which we investigate possible vibrotactile cues in comparison to visual cues and to a combination of visual and vibrotactile cues for a guided selection scenario and a guided navigation scenario. Although none of the vibrotactile cues significantly outperformed the visual cues, our study results shed light on a number of practical issues when using vibration for user guidance - including differences between various types of vibrotactile feedback, as well as diverging performance for different guidance scenarios.