arXiv subjects

Bo Wang

Publications and source records attributed to Bo Wang.

At least 523 records · Page 29Linked to original sources

arXiv2023

Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection

Pixel-level road crack detection has always been a challenging task in intelligent transportation systems. Due to the external environments, such as weather, light, and other factors, pavement cracks often present low contrast, poor continuity, and different sizes in length and width. However, most of the existing studies pay less attention to crack data under different situations. Meanwhile, recent algorithms based on deep convolutional neural networks (DCNNs) have promoted the development of cutting-edge models for crack detection. Nevertheless, they usually focus on complex models for good performance, but ignore detection efficiency in practical applications. In this article, to address the first issue, we collected two new databases (i.e. Rain365 and Sun520) captured in rainy and sunny days respectively, which enrich the data of the open source community. For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet. Specifically, we introduce a novel olive-shaped structure for the encoder network, a light-weight multi-scale block and a new up-sampling method in the decoder network. Numerous experiments show that our model can better balance detection performance and efficiency compared with previous models. Especially, on the Sun520 dataset, our CarNet significantly advances the state-of-the-art performance with ODS F-score from 0.488 to 0.514. Meanwhile, it does so with an improved detection speed (104 frame per second) which is orders of magnitude faster than some recent DCNNs-based algorithms specially designed for crack detection.

cs.CV↗

arXiv2022

Underactuated Source Seeking by Surge Force Tuning: Theory and Boat Experiments

We extend source seeking algorithms, in the absence of position and velocity measurements, and with tuning of the surge input, from velocity-actuated (unicycle) kinematic models to force-actuated generic Euler-Lagrange dynamic underactuated models. In the design and analysis, we employ a symmetric product approximation, averaging, passivity, and partial-state stability theory. The proposed control law requires only real-time measurement of the source signal at the current position of the vehicle and ensures semi-global practical uniform asymptotic stability (SPUAS) with respect to the linear motion coordinates for the closed-loop system. The performance of our source seeker with surge force tuning is illustrated with both numerical simulations and experiments of an underactuated boat.

eess.SY↗

arXiv2022

The double thresholds distort the lineshapes of the $P_{ψs}^Λ(4338)^0$ resonance

Very recently, the LHCb Collaboration reported the first observation of the hidden charm pentaquark with strangeness, $P_{ψs}^Λ(4338)^0$. Considering this state is very close to the $Ξ_c^0\bar{D}^0$ and $Ξ_c^+D^-$ thresholds, we explore the possible bias of the Breit-Wigner parameterization, with emphasis on the effect of its coupling to the double thresholds $Ξ_c^0\bar{D}^0$ and $Ξ_c^+D^-$. We first use a qualitative picture based on the ``uniformization" of the Riemann surface of the two-channel system to understand the positions of the enhancement. Then we use the Lippmann-Schwinger equation (LSE) formalism (equivalent to the $K$-matrix parameterization) with two models, the zero-range model and Flatté model to investigate the $J/ψΛ$ lineshapes. Our results show that the nominal peak of the $P_{ψs}^Λ(4338)^0$ could arise either from the pole well above the $Ξ_c^+ D^-$ threshold on the $(-,+)$ sheet or from the pole well below the $Ξ_c^0 \bar{D}^0$ threshold on the $(-,-)$ sheet in the two-channel system. Using the Breit-Wigner distribution to depict the above two lineshapes could be misleading. We also find a novel type of lineshapes with the enhancement constrained by the threshold difference. We urge the LHCb collaboration to perform the refined experimental analysis considering the unitarity and analyticity, e.g. using the K-matrix parameterization. As a by-product, we obtain that the ratio of the isospin violating decay ${Γ_{P_{ψs}^Λ\to J/ψΣ}}/{Γ_{P_{ψs}^Λ\to J/ψΛ}}$ could be up to $10\%$.

hep-ph↗

arXiv2022

Overlapping oriented imbalanced ensemble learning method based on projective clustering and stagewise hybrid sampling

The challenge of imbalanced learning lies not only in class imbalance problem, but also in the class overlapping problem which is complex. However, most of the existing algorithms mainly focus on the former. The limitation prevents the existing methods from breaking through. To address this limitation, this paper proposes an ensemble learning algorithm based on dual clustering and stage-wise hybrid sampling (DCSHS). The DCSHS has three parts. Firstly, we design a projection clustering combination framework (PCC) guided by Davies-Bouldin clustering effectiveness index (DBI), which is used to obtain high-quality clusters and combine them to obtain a set of cross-complete subsets (CCS) with balanced class and low overlapping. Secondly, according to the characteristics of subset classes, a stage-wise hybrid sampling algorithm is designed to realize the de-overlapping and balancing of subsets. Finally, a projective clustering transfer mapping mechanism (CTM) is constructed for all processed subsets by means of transfer learning, thereby reducing class overlapping and explore structure information of samples. The major advantage of our algorithm is that it can exploit the intersectionality of the CCS to realize the soft elimination of overlapping majority samples, and learn as much information of overlapping samples as possible, thereby enhancing the class overlapping while class balancing. In the experimental section, more than 30 public datasets and over ten representative algorithms are chosen for verification. The experimental results show that the DCSHS is significantly best in terms of various evaluation criteria.

cs.LG↗

arXiv2022

CodeExp: Explanatory Code Document Generation

Developing models that can automatically generate detailed code explanation can greatly benefit software maintenance and programming education. However, existing code-to-text generation models often produce only high-level summaries of code that do not capture implementation-level choices essential for these scenarios. To fill in this gap, we propose the code explanation generation task. We first conducted a human study to identify the criteria for high-quality explanatory docstring for code. Based on that, we collected and refined a large-scale code docstring corpus and formulated automatic evaluation metrics that best match human assessments. Finally, we present a multi-stage fine-tuning strategy and baseline models for the task. Our experiments show that (1) our refined training dataset lets models achieve better performance in the explanation generation tasks compared to larger unrefined data (15x larger), and (2) fine-tuned models can generate well-structured long docstrings comparable to human-written ones. We envision our training dataset, human-evaluation protocol, recommended metrics, and fine-tuning strategy can boost future code explanation research. The code and annotated data are available at https://github.com/subercui/CodeExp.

cs.CL↗

arXiv2022

Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons

In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection. However, the SOTA bottom-up methods' accuracy is still inferior compared to the existing top-down methods. This is due to the predicted human poses being regressed based on the inconsistent human bounding box center and the lack of human-scale normalization, leading to the predicted human poses being inaccurate and small-scale persons being missed. To push the envelope of the bottom-up pose estimation, we firstly propose multi-scale training to enhance the network to handle scale variation with single-scale testing, particularly for small-scale persons. Secondly, we introduce dual anatomical centers (i.e., head and body), where we can predict the human poses more accurately and reliably, especially for small-scale persons. Moreover, existing bottom-up methods use multi-scale testing to boost the accuracy of pose estimation at the price of multiple additional forward passes, which weakens the efficiency of bottom-up methods, the core strength compared to top-down methods. By contrast, our multi-scale training enables the model to predict high-quality poses in a single forward pass (i.e., single-scale testing). Our method achieves 38.4\% improvement on bounding box precision and 39.1\% improvement on bounding box recall over the state of the art (SOTA) on the challenging small-scale persons subset of COCO. For the human pose AP evaluation, we achieve a new SOTA (71.0 AP) on the COCO test-dev set with the single-scale testing. We also achieve the top performance (40.3 AP) on OCHuman dataset in cross-dataset evaluation.

cs.CV↗

arXiv2022

Aligning Recommendation and Conversation via Dual Imitation

Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations. However, existing conversational recommendation systems (CRS) ignore the advantage of user interest shift in connecting recommendation and conversation, which leads to an ineffective loose coupling structure of CRS. To address this issue, by modeling the recommendation actions as recommendation paths in a knowledge graph (KG), we propose DICR (Dual Imitation for Conversational Recommendation), which designs a dual imitation to explicitly align the recommendation paths and user interest shift paths in a recommendation module and a conversation module, respectively. By exchanging alignment signals, DICR achieves bidirectional promotion between recommendation and conversation modules and generates high-quality responses with accurate recommendations and coherent explanations. Experiments demonstrate that DICR outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics.

cs.CL↗

arXiv2022

OSIC: A New One-Stage Image Captioner Coined

Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a task-based information gap to decrease the performance, since the object features in detection task are suboptimal representation and cannot provide all necessary information for subsequent text generation. Besides, object features are usually represented by the last layer features that lose the local details of input images. In this paper, we propose a novel One-Stage Image Captioner (OSIC) with dynamic multi-sight learning, which directly transforms input image into descriptive sentences in one stage. As a result, the task-based information gap can be greatly reduced. To obtain rich features, we use the Swin Transformer to calculate multi-level features, and then feed them into a novel dynamic multi-sight embedding module to exploit both global structure and local texture of input images. To enhance the global modeling of encoder for caption, we propose a new dual-dimensional refining module to non-locally model the interaction of the embedded features. Finally, OSIC can obtain rich and useful information to improve the image caption task. Extensive comparisons on benchmark MS-COCO dataset verified the superior performance of our method.

cs.CV↗

arXiv2022

Low-Complexity Channel Estimation for Massive MIMO Systems with Decentralized Baseband Processing

The traditional centralized baseband processing architecture is faced with the bottlenecks of high computation complexity and excessive fronthaul communication, especially when the number of antennas at the base station (BS) is large. To cope with these two challenges, the decentralized baseband processing (DPB) architecture has been proposed, where the BS antennas are partitioned into multiple clusters, and each is connected to a local baseband unit (BBU). In this paper, we are interested in the low-complexity distributed channel estimation (CE) method under such DBP architecture, which is rarely studied in the literature. The aim is to devise distributed CE algorithms that can perform as well as the centralized scheme but with a small inter-BBU communication cost. Specifically, based on the low-complexity diagonal minimum mean square error channel estimator, we propose two distributed CE algorithms, namely the aggregate-then-estimate algorithm and the estimate-then-aggregate algorithm. In contrast to the existing distributed CE algorithm which requires iterative information exchanges among the nodes, our algorithms only require one roundtrip communication among BBUs. Extensive experiment results are presented to demonstrate the advantages of the proposed distributed CE algorithms in terms of estimation accuracy, inter-BBU communication cost, and computation complexity.

cs.IT↗

arXiv2022

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

Image guided depth completion aims to recover per-pixel dense depth maps from sparse depth measurements with the help of aligned color images, which has a wide range of applications from robotics to autonomous driving. However, the 3D nature of sparse-to-dense depth completion has not been fully explored by previous methods. In this work, we propose a Graph Convolution based Spatial Propagation Network (GraphCSPN) as a general approach for depth completion. First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning. In addition, the proposed networks explicitly incorporate learnable geometric constraints to regularize the propagation process performed in three-dimensional space rather than in two-dimensional plane. Furthermore, we construct the graph utilizing sequences of feature patches, and update it dynamically with an edge attention module during propagation, so as to better capture both the local neighboring features and global relationships over long distance. Extensive experiments on both indoor NYU-Depth-v2 and outdoor KITTI datasets demonstrate that our method achieves the state-of-the-art performance, especially when compared in the case of using only a few propagation steps. Code and models are available at the project page.

cs.CV↗

arXiv2022

Wafer-level substrate-free low-stress silicon nitride platform for THz metadevices and monolithically integrated narrowband metamaterial absorbers

The implementation of terahertz (THz) wafer-level metadevices is critical to advance the science for applications including (I) integrated focal plane array which can image for biology and (II) integrated narrowband absorbers for high spectral resolution THz spectroscopy. Substantial progress has been made in the development of THz metamaterials; however, a wafer-level low-stress THz metadevices platform remains a challenge. This paper experimentally demonstrates a substrate-free THz metadevices platform adopting engineered Si-rich and low-stress silicon nitride (SiNx) thin films, achieving an extensive THz transparency up to f = 2.5 THz. A new analytical model is first reported from the Lorentz model that can accurately predict spectral responses of metal insulator metal (MIM) metamaterial absorbers. The model is experimentally validated in the THz range and exploited for the first demonstration of a THz absorber, which exhibits performance approaching the predicted results. Our results show that the wafer-level SiNx platform will accelerate the development of large-scale, sophisticated substrate-free THz metadevices. The Lorentz model and its quadratic model will be a very practical method for designing THz metadevices.

physics.optics↗

arXiv2022

Molecular tetraquarks and pentaquarks in chiral effective field theory

We studied the $D\bar{D}^\ast/\bar{D}D^\ast$, $D^\ast\bar{D}^\ast$, $\bar{D}_s D^\ast/\bar{D}_s^\ast D$, $B\bar{B}^\ast/\bar{B}B^\ast$ and $B^\ast\bar{B}^\ast$ di-hadron interactions in chiral effective field theory ($χ$EFT) up to the next-to-leading (NLO) order. The above-threshold tetraquark states $Z_c(3900)$, $Z_c(4020)$, $Z_{cs}(3985)$, $Z_b(10610)$, $Z_b(10650)$ can be explained as the corresponding di-hadron resonances, respectively. We also studied the $Σ_c^{(\ast)}\bar{D}^{(\ast)}$ interactions to investigate the three hidden-charm pentaquarks $P_c(4312)$, $P_c(4440)$ and $P_c(4457)$. We further used the parameters fixed from the $P_c$ states to predict the possible molecular states in $Ξ_c\bar{D}^{(\ast)}$, $Ξ_c^\prime\bar{D}^{(\ast)}$ and $Ξ_c^\ast\bar{D}^{(\ast)}$ systems. Our predictions of the $Ξ_c\bar{D}^{(\ast)}$ bound states are very consistent with two new near-threshold structures recently observed by the LHCb Collaboration.

hep-ph↗

arXiv2022

Template-based Abstractive Microblog Opinion Summarisation

We introduce the task of microblog opinion summarisation (MOS) and share a dataset of 3100 gold-standard opinion summaries to facilitate research in this domain. The dataset contains summaries of tweets spanning a 2-year period and covers more topics than any other public Twitter summarisation dataset. Summaries are abstractive in nature and have been created by journalists skilled in summarising news articles following a template separating factual information (main story) from author opinions. Our method differs from previous work on generating gold-standard summaries from social media, which usually involves selecting representative posts and thus favours extractive summarisation models. To showcase the dataset's utility and challenges, we benchmark a range of abstractive and extractive state-of-the-art summarisation models and achieve good performance, with the former outperforming the latter. We also show that fine-tuning is necessary to improve performance and investigate the benefits of using different sample sizes.

cs.CL↗

arXiv2022

Pressure-induced electronic topological transition and superconductivity in topological insulator Bi2Te2.1Se0.9

One approach to discovering topological superconductor is establishing superconductivity based on well-identified topological insulators. However, the coexistence of superconductivity and topological state is always arcane. In this paper, we report how pressure tunes the crystal structure, electronic structure, and superconductivity in topological insulator Bi2Te2.1Se0.9. The first pressure-induced structure transition start from 8.4 GPa, followed by the structure sequence of R-3m - C2/m - C2/c - Im-3m up to 37 GPa. Superconductivity starts to present at 2.4 GPa with the Tc around 6.6 K. Moreover, at around 2.5 GPa, the abnormal changes of c/a and the full width at half maximum (FWHM) of mode indicate the occurrence of electronic topological transition (ETT). These results suggest that ETT highly promotes the superconductivity in topological insulator Bi2Te2.1Se0.9 in the low-pressure rhombohedral phase. Our work clarifies the complex electronic structure in Bi2Te2.1Se0.9 and sheds light on the new candidate for superconductivity in topological insulators.

cond-mat.supr-con↗

arXiv2022

Cosmological model-independent measurement of cosmic curvature using distance sum rule with the help of gravitational waves

Although the cosmic curvature has been tightly constrained in the standard cosmological model using observations of cosmic microwave background anisotropies, it is still of great importance to independently measure this key parameter using only late-universe observations in a cosmological model-independent way. The distance sum rule in strong gravitational lensing (SGL) provides such a way, provided that the three distances in the sum rule can be calibrated by other observations. In this paper, we propose that gravitational waves (GWs) can be used to provide the distance calibration in the SGL method, which can avoid the dependence on distance ladder and cover a wider redshift range. Using the simulated GW standard siren observation by the Einstein Telescope as an example, we show that this scheme is feasible and advantageous. We find that $ΔΩ_k\simeq 0.17$ with the current SGL data, which is slightly more precise than the case of using SN to calibrate. Furthermore, we consider the forthcoming LSST survey that is expected to observe many SGL systems, and we find that about $10^4$ SGL data could provide the precise measurement of $ΔΩ_k\simeq 10^{-2}$ with the help of GWs. In addition, our results confirm that this method of constraining $Ω_k$ is strongly dependent on lens models. However, obtaining a more accurate phenomenological model for lens galaxies is highly predictable as future massive surveys observe more and more SGL samples, which will significantly improve the constraint of cosmic curvature.

astro-ph.CO↗

arXiv2022

Point-splitting regularization of the stress tensor of a coupling scalar field in de Sitter space

We perform the point-splitting regularization on the vacuum stress tensor of a coupling scalar field in de Sitter space under the guidance from the adiabatically regularized Green's function. For the massive scalar field with the minimal coupling $ξ=0$, the 2nd order point-splitting regularization yields a finite vacuum stress tensor with a positive, constant energy density, which can be identified as the cosmological constant that drives de Sitter inflation. For the coupling $ξ\ne 0$, we find that, even if the regularized Green's function is continuous, UV and IR convergent, the point-splitting regularization does not automatically lead to an appropriate stress tensor. The coupling $ξR$ causes log divergent terms, as well as higher-order finite terms which depend upon the path of the coincidence limit. After removing these unwanted terms by extra treatments, the 2nd-order regularization for small couplings $ξ\in(0,\frac{1}{7.04})$, and respectively the 0th-order regularization for the conformal coupling $ξ=\frac16$, yield a finite, constant vacuum stress tensor, in analogy to the case $ξ=0$. For the massless field with $ξ=0$ or $ξ=\frac16$, the point-splitting regularization yields a vanishing vacuum stress tensor, and there is no conformal trace anomaly for $ξ=\frac16$. If the 4th-order regularization were taken, the regularized energy density for general $ξ$ would be negative, which is inconsistent with the de Sitter inflation, and the regularized Green's function would be singular at the zero mass, which is unphysical. In all these cases, the stress tensor from the point-splitting regularization is equal to that from the adiabatic one.

gr-qc↗

arXiv2022

Fisher Matrix Based Fault Detection for PMUs Data in Power Grids

Abnormal event detection is critical in the safe operation of power system. In this paper, using the data collected from phasor measurement units (PMUs), two methods based on Fisher random matrix are proposed to detect faults in power grids. Firstly, the fault detection matrix is constructed and the event detection problem is reformatted as a two-sample covariance matrices test problem. Secondly, the central limit theorem for the linear spectral statistic of the Fisher matrix is derived and a test statistic for testing faults is proposed. To save computing resources, the screening step of fault interval based on the test statistic is designed to check the existence of faults. Then two point-by-point methods are proposed to determine the time of the fault in the interval. One method detects faults by checking whether the largest sample eigenvalue falls outside the supporting set of limiting spectral distribution of the standard Fisher matrix, which can detect the faults with higher accuracy. The other method tests the faults based on the statistic proposed, which has a faster detection speed. Compared with existing works, the simulation results illustrate that two methods proposed in this paper cost less computational time and provide a higher degree of accuracy.

eess.SY↗

arXiv2022

Indoor optical fiber eavesdropping approach and its avoidance

The optical fiber network has become a worldwide infrastructure. In addition to the basic functions in telecommunication, its sensing ability has attracted more and more attention. In this paper, we discuss the risk of household fiber being used for eavesdropping and demonstrate its performance in the lab. Using a 3-meter tail fiber in front of the household optical modem, voices of normal human speech can be eavesdropped by a laser interferometer and recovered 1.1 km away. The detection distance limit and system noise are analyzed quantitatively. We also give some practical ways to prevent eavesdropping through household fiber.

cs.SD↗