Search

Source detection in graphs has demonstrated robust efficacy in the domain of rumor source identification. Although recent solutions have enhanced performance by leveraging deep neural networks, they often require complete user data. In this paper, we address a more challenging task, rumor source detection with incomplete user data, and propose a novel framework, i.e., Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion (GIN-SD), to tackle this challenge. Specifically, our approach utilizes a positional embedding module to distinguish nodes that are incomplete and employs a self-attention mechanism to focus on nodes with greater information transmission capacity. To mitigate the prediction bias caused by the significant disparity between the numbers of source and non-source nodes, we also introduce a class-balancing mechanism. Extensive experiments validate the effectiveness of GIN-SD and its superiority to state-of-the-art methods., Comment: The paper is accepted by AAAI24

The precise segmentation of ore images is critical to the successful execution of the beneficiation process. Due to the homogeneous appearance of the ores, which leads to low contrast and unclear boundaries, accurate segmentation becomes challenging, and recognition becomes problematic. This paper proposes a lightweight framework based on Multi-Layer Perceptron (MLP), which focuses on solving the problem of edge burring. Specifically, we introduce a lightweight backbone better suited for efficiently extracting low-level features. Besides, we design a feature pyramid network consisting of two MLP structures that balance local and global information thus enhancing detection accuracy. Furthermore, we propose a novel loss function that guides the prediction points to match the instance edge points to achieve clear object boundaries. We have conducted extensive experiments to validate the efficacy of our proposed method. Our approach achieves a remarkable processing speed of over 27 frames per second (FPS) with a model size of only 73 MB. Moreover, our method delivers a consistently high level of accuracy, with impressive performance scores of 60.4 and 48.9 in~$AP_{50}^{box}$ and~$AP_{50}^{mask}$ respectively, as compared to the currently available state-of-the-art techniques, when tested on the ore image dataset. The source code will be released at \url{https://github.com/MVME-HBUT/ORENEXT}., Comment: 10 pages, 8 figures

Image segmentation methods have been utilized to determine the particle size distribution of crushed ores. Due to the complex working environment, high-powered computing equipment is difficult to deploy. At the same time, the ore distribution is stacked, and it is difficult to identify the complete features. To address this issue, an effective box-supervised technique with texture features is provided for ore image segmentation that can identify complete and independent ores. Firstly, a ghost feature pyramid network (Ghost-FPN) is proposed to process the features obtained from the backbone to reduce redundant semantic information and computation generated by complex networks. Then, an optimized detection head is proposed to obtain the feature to maintain accuracy. Finally, Lab color space (Lab) and local binary patterns (LBP) texture features are combined to form a fusion feature similarity-based loss function to improve accuracy while incurring no loss. Experiments on MS COCO have shown that the proposed fusion features are also worth studying on other types of datasets. Extensive experimental results demonstrate the effectiveness of the proposed method, which achieves over 50 frames per second with a small model size of 21.6 MB. Meanwhile, the method maintains a high level of accuracy compared with the state-of-the-art approaches on ore image dataset. The source code is available at \url{https://github.com/MVME-HBUT/OREINST}., Comment: 14 pages, 8 figures

For the ore particle size detection, obtaining a sizable amount of high-quality ore labeled data is time-consuming and expensive. General object detection methods often suffer from severe over-fitting with scarce labeled data. Despite their ability to eliminate over-fitting, existing few-shot object detectors encounter drawbacks such as slow detection speed and high memory requirements, making them difficult to implement in a real-world deployment scenario. To this end, we propose a lightweight and effective few-shot detector to achieve competitive performance with general object detection with only a few samples for ore images. First, the proposed support feature mining block characterizes the importance of location information in support features. Next, the relationship guidance block makes full use of support features to guide the generation of accurate candidate proposals. Finally, the dual-scale semantic aggregation module retrieves detailed features at different resolutions to contribute with the prediction process. Experimental results show that our method consistently exceeds the few-shot detectors with an excellent performance gap on all metrics. Moreover, our method achieves the smallest model size of 19MB as well as being competitive at 50 FPS detection speed compared with general object detectors. The source code is available at https://github.com/MVME-HBUT/Faster-OreFSDet., Comment: 18 pages, 11 figures

The active photonics based on the two-dimensional material graphene has attracted enormous interests for developing the tunable and compact optical devices with high efficiency. Here we integrate graphene into the Fano-resonant all-dielectric metasurfaces consisting of silicon split resonators, and systematically investigate the strong interaction between graphene and the highly localized hot inside feed gaps in the near infrared regime. The numerical results show that the integrated graphene can substantially reduce the Fano resonance due to the coupling effect between the intrinsic absorption of graphene with enhanced electric field in the localized hotspot. With the manipulation of the surface conductivity via varying Fermi level and the layer number of graphene, the Fano resonance strength obtains a significant modulation and is even switched off. This works provides a great degree of freedom to tailor light-matter interaction at the nanoscale and opens up the avenues for actively tunable and integrated nanophotonic device applications, such as the optical biosensing, slow light and enhanced nonlinear effects.

We theoretically and numerically demonstrate an actively tunable slow light in a hybrid metal-graphene metamaterial in the terahertz (THz) regime. In the unit cell, the near field coupling between the metallic elements including the bright cut wire resonator and the dark double split-ring resonator gives rises to a pronounced transmission peak. By positioning a monolayer graphene under the dark mode resonator, an active modulation of the near field coupling is achieved via shifting the Fermi level of graphene. The physical origin can be attributed to the variation in the damping rate of the dark mode resonator arising from the conductive effect of graphene. Accompanied with the actively tunable near filed coupling effect is the dynamically controllable phase dispersion, allowing for the highly tunable slow light effect. This work offers an alternative way to design compact slow light devices in the THz regime for future optical signal processing applications.

Black phosphorus (BP) as a promising two-dimensional material with extraordinary optical properties constitutes an excellent building block in multilayer hyperbolic metamaterials. In this work, we design a multilayer structure composed of BP/dielectric layer stacking unit cells patterned on a gold mirror and theoretically demonstrate the tunable anisotropic absorption in the infrared regime. The electric dipole resonance between the adjacent unit cells drives the structure in the critical coupling state, and impedance of the structure matches to that of free space, showing the perfect absorption for one polarization direction, while the impedance mismatch for the other polarization direction leads to only 8.2$\%$ absorption at the same wavelength. The anisotropic absorption response of the proposed structure can be attributed to the intrinsic anisotropy of BP, which exhibits few dependence on the incident angle. Furthermore, we investigate the tunable optical absorption of the proposed structure with the electron doping of BP and the geometric parameters. These results demonstrate great potentials of BP in constituting multilayer hyperbolic metamaterials, and open up avenues in designing anisotropic metadevices with tunable spectral and polarization selectivity in the infrared regime.

A simple perfect absorption structure is proposed to achieve the high efficiency light absorption of monolayer molybdenum disulfide (MoS 2 ) by the critical coupling mechanism of guided resonances. The results of numerical simulation and theoretical analysis show that the light absorption in this atomically thin layer can be as high as 98 . 3% at the visible wavelengths, which is over 12 times more than that of a bare monolayer MoS 2 . In addition, the operating wavelength can be tuned flexibly by adjusting the radius of the air hole and the thickness of the dielectric layers, which is of great practical significance to improve the efficiency and selectivity of the absorption in monolayer MoS 2 . The novel idea of using critical coupling to enhance the light-MoS 2 interaction can be also adopted in other atomically thin materials. And the meaningful improvement and tunability of the absorption in monolayer MoS 2 provide a good prospect for the realization of high-performance MoS 2 -based optoelectronic applications, such as photodetection and photoluminescence.

Surface plasmon resonance (SPR) has been intensively investigated and widely exploited to trap the incident light and enhance absorption in the optoelectronic devices. The availability of graphene as a plasmonic material with strong half-metallicity and continuously tunable surface conductivity makes it promising to dynamically modulate the absorption enhancement with graphene-based metamaterials. Here we numerically demonstrate tunable light trapping and absorption enhancement can be realized with graphene-based complementary metamaterials. Furthermore, we also explore the polarization sensitivity in the proposed device, in which case either TM or TE plane wave at the specific wavelength can be efficiently absorbed by simply manipulating the Fermi energy of graphene. Therefore, this work can find potential applications in the next generation of photodetectors with tunable spectral and polarization selectivity in the mid-infrared and terahertz (THz) regimes.

We numerically demonstrate a novel monolayer graphene-based perfect absorption multi-layer photonic structure by the mechanism of critical coupling with guided resonance, in which the absorption of graphene can significantly close to 99% at telecommunication wavelengths. The highly efficient absorption and spectral selectivity can be obtained with designing structural parameters in the near infrared ranges. Compared to previous works, we achieve the complete absorption of single-atomic-layer graphene in the perfect absorber for the first time, which not only opens up new methods of enhancing the light-graphene interaction, but also makes for practical applications in high-performance optoelectronic devices, such as modulators and sensors.

Graphene has emerged as a promising building block in the modern optics and optoelectronics due to its novel optical and electrical properties. In the mid-infrared and terahertz (THz) regime, graphene behaves like metals and supports surface plasmon resonances (SPRs). Moreover, the continuously tunable conductivity of graphene enables active SPRs and gives rise to a range of active applications. However, the interaction between graphene and metal-based resonant metamaterials has not been fully understood. In this work, a simulation investigation on the interaction between the graphene layer and THz resonances supported by the two-gap split ring metamaterials is systematically conducted. The simulation results show that the graphene layer can substantially reduce the Fano resonance and even switch it off, while leave the dipole resonance nearly unaffected, which phenomenon is well explained with the high conductivity of graphene. With the manipulation of graphene conductivity via altering its Fermi energy or layer number, the amplitude of the Fano resonance can be modulated. The tunable Fano resonance here together with the underlying physical mechanism can be strategically important in designing active metal-graphene hybrid metamaterials. In addition, the "sensitivity" to the graphene layer of the Fano resonance is also highly appreciated in the field of ultrasensitive sensing, where the novel physical mechanism can be employed in sensing other graphene-like two-dimensional (2D) materials or biomolecules with the high conductivity., Comment: Revised Manuscript