arXiv subjects

Bo Yang

Publications and source records attributed to Bo Yang.

At least 415 records · Page 23Linked to original sources

arXiv2021

GRF: Learning a General Radiance Field for 3D Representation and Rendering

We present a simple yet powerful neural network that implicitly represents and renders 3D objects and scenes only from 2D observations. The network models 3D geometries as a general radiance field, which takes a set of 2D images with camera poses and intrinsics as input, constructs an internal representation for each point of the 3D space, and then renders the corresponding appearance and geometry of that point viewed from an arbitrary position. The key to our approach is to learn local features for each pixel in 2D images and to then project these features to 3D points, thus yielding general and rich point representations. We additionally integrate an attention mechanism to aggregate pixel features from multiple 2D views, such that visual occlusions are implicitly taken into account. Extensive experiments demonstrate that our method can generate high-quality and realistic novel views for novel objects, unseen categories and challenging real-world scenes.

cs.CV↗

arXiv2021

Fractionalisation and dynamics of anyons at $ν=n+1/3$ in fractional quantum Hall effect and their experimental signatures

We show the low-lying excitations at filling factor $ν=n+1/3$ with realistic interactions are contained completely within the well-defined Hilbert space of "Gaffnian quasiholes". Each Laughlin quasihole can thus be understood as a bound state of two Gaffnian quasiholes, which in the lowest Landau level (LLL) behaves like "partons" with "asymptotic freedom" mediated by neutral excitations acting as "gluons". Near the experimentally observed nematic FQH phase in higher LLs, quasiholes become weakly bounded and fractionalise with rich dynamical properties. By studying the effective interactions between quasiholes, we predict a finite temperature phase transition of the Laughlin quasiholes even when the Laughlin ground state remains incompressible, and derive relevant experimental conditions for its possible observations.

cond-mat.str-el↗

arXiv2021

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Comparative experiments show that our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches. Moreover, extensive experiments on five large-scale point cloud datasets, including Semantic3D, SemanticKITTI, Toronto3D, NPM3D and S3DIS, demonstrate the state-of-the-art semantic segmentation performance of our RandLA-Net.

cs.CV↗

arXiv2021

Influences on Drivers' Understandings of Systems by Presenting Image Recognition Results

It is essential to help drivers have appropriate understandings of level 2 automated driving systems for keeping driving safety. A human machine interface (HMI) was proposed to present real time results of image recognition by the automated driving systems to drivers. It was expected that drivers could better understand the capabilities of the systems by observing the proposed HMI. Driving simulator experiments with 18 participants were preformed to evaluate the effectiveness of the proposed system. Experimental results indicated that the proposed HMI could effectively inform drivers of potential risks continuously and help drivers better understand the level 2 automated driving systems.

cs.HC↗

arXiv2021

HAP-Reserved Communications in Space-Air-Ground Integrated Networks

Terrestrial communication networks have experienced significant development in recent years by providing emerging services for ground users. However, one critical challenge raised is to provide full coverage (especially in dense high-rise urban environments) for ground users due to scarce network resources and limited coverage. To meet this challenge, we propose a high altitude platform (HAP)-reserved ground-air-space (GAS) transmission scheme, which combines with the ground-to-space (G2S) transmission scheme to strengthen the terrestrial communication and save the transmission power. To integrate the two transmission schemes, we propose a transmission control strategy. Wherein, the ground user decides its transmission scheme, i.e., switches between the GAS link transmission and the G2S link transmission with a probability. We then maximize the overall throughput and derive the optimal probability that a ground user adopts the GAS transmission scheme. Numerical results demonstrate the superiority of the proposed transmission control strategy.

cs.NI↗

arXiv2021

Converged Reconfigurable Intelligent Surface and Mobile Edge Computing for Space Information Networks

Space information networks (SIN) are facing an ever-increasing thirst for high-speed and high-capacity seamless data transmission due to the integration of ground, air, and space communications. However, this imposes a new paradigm on the architecture design of the integrated SIN. Recently, reconfigurable intelligent surfaces (RISs) and mobile edge computing (MEC) are the most promising techniques, conceived to improve communication and computation capability by reconfiguring the wireless propagation environment and offloading. Hence, converging RISs and MEC in SIN is becoming an effort to reap the double benefits of computation and communication. In this article, we propose an RIS-assisted collaborative MEC architecture for SIN and discuss its implementation. Then we present its potential benefits, major challenges, and feasible applications. Subsequently, we study different cases to evaluate the system data rate and latency. Finally, we conclude with a list of open issues in this research area.

cs.NI↗

arXiv2021

Effect of Adaptive and Fixed Shared Steering Control on Distracted Driver Behavior

Driver distraction is a well-known cause for traffic collisions worldwide. Studies have indicated that shared steering control, which actively provides haptic guidance torque on the steering wheel, effectively improves the performance of distracted drivers. Recently, adaptive shared steering control based on the physiological status of the driver has been developed, although its effect on distracted driver behavior remains unclear. To this end, a high-fidelity driving simulator experiment was conducted involving 18 participants performing double lane changes. The experimental conditions comprised two driver states: attentive and distracted. Under each condition, evaluations were performed on three types of haptic guidance: none (manual), fixed authority, and adaptive authority based on feedback from the forearm surface electromyography of the driver. Evaluation results indicated that, for both attentive and distracted drivers, haptic guidance with adaptive authority yielded lower driver workload and reduced lane departure risk than manual driving and fixed authority. Moreover, there was a tendency for distracted drivers to reduce grip strength on the steering wheel to follow the haptic guidance with fixed authority, resulting in a relatively shorter double lane change duration.

eess.SY↗

arXiv2021

DEFT: Distilling Entangled Factors by Preventing Information Diffusion

Disentanglement is a highly desirable property of representation owing to its similarity to human understanding and reasoning. Many works achieve disentanglement upon information bottlenecks (IB). Despite their elegant mathematical foundations, the IB branch usually exhibits lower performance. In order to provide an insight into the problem, we develop an annealing test to calculate the information freezing point (IFP), which is a transition state to freeze information into the latent variables. We also explore these clues or inductive biases for separating the entangled factors according to the differences in the IFP distributions. We found the existing approaches suffer from the information diffusion problem, according to which the increased information diffuses in all latent variables. Based on this insight, we propose a novel disentanglement framework, termed the distilling entangled factor (DEFT), to address the information diffusion problem by scaling backward information. DEFT applies a multistage training strategy, including multigroup encoders with different learning rates and piecewise disentanglement pressure, to disentangle the factors stage by stage. We evaluate DEFT on three variants of dSprite and SmallNORB, which show low-variance and high-level disentanglement scores. Furthermore, the experiment under the correlative factors shows incapable of TC-based approaches. DEFT also exhibits a competitive performance in the unsupervised setting.

cs.LG↗

arXiv2021

AI-Assisted MAC for Reconfigurable Intelligent Surface-Aided Wireless Networks: Challenges and Opportunities

Recently, significant research attention has been devoted to the study of reconfigurable intelligent surfaces (RISs), which are capable of reconfiguring the wireless propagation environment by exploiting the unique properties of metamaterials-based integrated large arrays of inexpensive antennas. Existing research demonstrates that RISs significantly improve the physical layer performance, including the wireless coverage, achievable data rate and energy efficiency. However, the medium access control (MAC) of multiple users accessing an RIS-enabled channel is still in its infancy, while many open issues remain to be addressed. In this article, we present four typical RIS-aided multi-user scenarios with special emphasis on the MAC schemes. We then propose and elaborate upon centralized, distributed and hybrid artificial-intelligence (AI)-assisted MAC architectures in RIS-aided multi-user communications systems. Finally, we discuss some challenges, perspectives and potential applications of RISs as they are related to MAC design.

cs.NI↗

arXiv2021

A Joint Energy and Latency Framework for Transfer Learning over 5G Industrial Edge Networks

In this paper, we propose a transfer learning (TL)-enabled edge-CNN framework for 5G industrial edge networks with privacy-preserving characteristic. In particular, the edge server can use the existing image dataset to train the CNN in advance, which is further fine-tuned based on the limited datasets uploaded from the devices. With the aid of TL, the devices that are not participating in the training only need to fine-tune the trained edge-CNN model without training from scratch. Due to the energy budget of the devices and the limited communication bandwidth, a joint energy and latency problem is formulated, which is solved by decomposing the original problem into an uploading decision subproblem and a wireless bandwidth allocation subproblem. Experiments using ImageNet demonstrate that the proposed TL-enabled edge-CNN framework can achieve almost 85% prediction accuracy of the baseline by uploading only about 1% model parameters, for a compression ratio of 32 of the autoencoder.

cs.NI↗

arXiv2021

NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering

In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data. However, the global models are often obtained via a performance tradeoff among users/items, i.e., not all users/items are perfectly fitted by the global models due to the hard non-convex optimization problems in CF algorithms. Ensemble learning can address this issue by learning multiple diverse models but usually suffer from efficiency issue on large datasets or complex algorithms. In this paper, we keep the intermediate models obtained during global model learning as the snapshot models, and then adaptively combine the snapshot models for individual user-item pairs using a memory network-based method. Empirical studies on three real-world datasets show that the proposed method can extensively and significantly improve the accuracy (up to 15.9% relatively) when applied to a variety of existing collaborative filtering methods.

cs.LG↗

arXiv2021

Hyperbolic Neural Collaborative Recommender

This paper explores the use of hyperbolic geometry and deep learning techniques for recommendation. We present Hyperbolic Neural Collaborative Recommender (HNCR), a deep hyperbolic representation learning method that exploits mutual semantic relations among users/items for collaborative filtering (CF) tasks. HNCR contains two major phases: neighbor construction and recommendation framework. The first phase introduces a neighbor construction strategy to construct a semantic neighbor set for each user and item according to the user-item historical interaction. In the second phase, we develop a deep framework based on hyperbolic geometry to integrate constructed neighbor sets into recommendation. Via a series of extensive experiments, we show that HNCR outperforms its Euclidean counterpart and state-of-the-art baselines.

cs.IR↗

arXiv2021

Reconfigurable Intelligent Surface-Assisted Aerial-Terrestrial Communications via Multi-Task Learning

The aerial-terrestrial communication system constitutes an efficient paradigm for supporting and complementing terrestrial communications. However, the benefits of such a system cannot be fully exploited, especially when the line-of-sight (LoS) transmissions are prone to severe deterioration due to complex propagation environments in urban areas. The emerging technology of reconfigurable intelligent surfaces (RISs) has recently become a potential solution to mitigate propagation-induced impairments and improve wireless network coverage. Motivated by these considerations, in this paper, we address the coverage and link performance problems of the aerial-terrestrial communication system by proposing an RIS-assisted transmission strategy. In particular, we design an adaptive RIS-assisted transmission protocol, in which the channel estimation, transmission strategy, and data transmission are independently implemented in a frame. On this basis, we formulate an RIS-assisted transmission strategy optimization problem as a mixed-integer non-linear program (MINLP) to maximize the overall system throughput. We then employ multi-task learning to speed up the solution to the problem. Benefiting from multi-task learning, the computation time is reduced by about four orders of magnitude. Numerical results show that the proposed RIS-assisted transmission protocol significantly improves the system throughput and reduces the transmit power.

cs.NI↗

arXiv2021

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction. Existing learning-based local descriptors are either sensitive to rotation transformations, or rely on classical handcrafted features which are neither general nor representative. In this paper, we introduce a new, yet conceptually simple, neural architecture, termed SpinNet, to extract local features which are rotationally invariant whilst sufficiently informative to enable accurate registration. A Spatial Point Transformer is first introduced to map the input local surface into a carefully designed cylindrical space, enabling end-to-end optimization with SO(2) equivariant representation. A Neural Feature Extractor which leverages the powerful point-based and 3D cylindrical convolutional neural layers is then utilized to derive a compact and representative descriptor for matching. Extensive experiments on both indoor and outdoor datasets demonstrate that SpinNet outperforms existing state-of-the-art techniques by a large margin. More critically, it has the best generalization ability across unseen scenarios with different sensor modalities. The code is available at https://github.com/QingyongHu/SpinNet.

cs.CV↗

arXiv2021

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

Despite the recent progress, 3D multi-person pose estimation from monocular videos is still challenging due to the commonly encountered problem of missing information caused by occlusion, partially out-of-frame target persons, and inaccurate person detection. To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters. In particular, we introduce a human-joint GCN, which, unlike the existing GCN, is based on a directed graph that employs the 2D pose estimator's confidence scores to improve the pose estimation results. We also introduce a human-bone GCN, which models the bone connections and provides more information beyond human joints. The two GCNs work together to estimate the spatial frame-wise 3D poses and can make use of both visible joint and bone information in the target frame to estimate the occluded or missing human-part information. To further refine the 3D pose estimation, we use our temporal convolutional networks (TCNs) to enforce the temporal and human-dynamics constraints. We use a joint-TCN to estimate person-centric 3D poses across frames, and propose a velocity-TCN to estimate the speed of 3D joints to ensure the consistency of the 3D pose estimation in consecutive frames. Finally, to estimate the 3D human poses for multiple persons, we propose a root-TCN that estimates camera-centric 3D poses without requiring camera parameters. Quantitative and qualitative evaluations demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2021

Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks

In monocular video 3D multi-person pose estimation, inter-person occlusion and close interactions can cause human detection to be erroneous and human-joints grouping to be unreliable. Existing top-down methods rely on human detection and thus suffer from these problems. Existing bottom-up methods do not use human detection, but they process all persons at once at the same scale, causing them to be sensitive to multiple-persons scale variations. To address these challenges, we propose the integration of top-down and bottom-up approaches to exploit their strengths. Our top-down network estimates human joints from all persons instead of one in an image patch, making it robust to possible erroneous bounding boxes. Our bottom-up network incorporates human-detection based normalized heatmaps, allowing the network to be more robust in handling scale variations. Finally, the estimated 3D poses from the top-down and bottom-up networks are fed into our integration network for final 3D poses. Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for single person, and consequently cannot assess natural inter-person interactions, we propose a two-person pose discriminator that enforces natural two-person interactions. Lastly, we also apply a semi-supervised method to overcome the 3D ground-truth data scarcity. Our quantitative and qualitative evaluations show the effectiveness of our method compared to the state-of-the-art baselines.

cs.CV↗

arXiv2021

Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges

An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets. However, publicly available datasets are either in relative small spatial scales or have limited semantic annotations due to the expensive cost of data acquisition and data annotation, which severely limits the development of fine-grained semantic understanding in the context of 3D point clouds. In this paper, we present an urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, which is three times the number of labeled points than the existing largest photogrammetric point cloud dataset. Our dataset consists of large areas from three UK cities, covering about 7.6 km^2 of the city landscape. In the dataset, each 3D point is labeled as one of 13 semantic classes. We extensively evaluate the performance of state-of-the-art algorithms on our dataset and provide a comprehensive analysis of the results. In particular, we identify several key challenges towards urban-scale point cloud understanding. The dataset is available at https://github.com/QingyongHu/SensatUrban.

cs.CV↗

arXiv2021

Reconfigurable Intelligent Surface-Assisted MAC for Wireless Networks: Protocol Design, Analysis, and Optimization

Reconfigurable intelligent surface (RIS) is a promising reflective radio technology for improving the coverage and rate of future wireless systems by reconfiguring the wireless propagation environment. The current work mainly focuses on the physical layer design of RIS. However, enabling multiple devices to communicate with the assistance of RIS is a crucial challenging problem. Motivated by this, we explore RIS-assisted communications at the medium access control (MAC) layer and propose an RIS-assisted MAC framework. In particular, RISassisted transmissions are implemented by pre-negotiation and a multi-dimension reservation (MDR) scheme. Based on this, we investigate RIS-assisted single-channel multi-user (SCMU) communications. Wherein the RIS regarded as a whole unity can be reserved by one user to support the multiple data transmissions, thus achieving high efficient RIS-assisted connections at the user. Moreover, under frequency-selective channels, implementing the MDR scheme on the RIS group division, RISassisted multi-channel multi-user (MCMU) communications are further explored to improve the service efficiency of the RIS and decrease the computation complexity. Besides, a Markov chain is built based on the proposed RIS-assisted MAC framework to analyze the system performance of SCMU/MCMU. Then the optimization problem is formulated to maximize the overall system capacity of SCMU/MCMU with energy-efficient constraint. The performance evaluations demonstrate the feasibility and effectiveness of each

cs.NI↗