Structural properties of residual carbon in coal gasification fine slag and their influence on flotation separation and resource utilization:A review

Coal gasification fine slag(FS)is a typical solid waste generated in coal gasification.Its current disposal methods of stockpil-ing and landfilling have caused serious soil and ecological hazards.Separation recovery and the high-value utilization of residual carbon(RC)in FS are the keys to realizing the win-win situation of the coal chemical industry in terms of economic and environmental benefits.The structural properties,such as pore,surface functional group,and microcrystalline structures,of RC in FS(FS-RC)not only affect the flotation recovery efficiency of FS-RC but also form the basis for the high-value utilization of FS-RC.In this paper,the characteristics of FS-RC in terms of pore structure,surface functional groups,and microcrystalline structure are sorted out in accordance with gasification type and FS particle size.The reasons for the formation of the special structural properties of FS-RC are analyzed,and their influence on the flotation separation and high-value utilization of FS-RC is summarized.Separation methods based on the pore structural characterist-ics of FS-RC,such as ultrasonic pretreatment-pore-blocking flotation and pore breaking-flocculation flotation,are proposed to be the key development technologies for improving FS-RC recovery in the future.The design of low-cost,low-dose collectors containing polar bonds based on the surface and microcrystalline structures of FS-RC is proposed to be an important breakthrough point for strengthening the flotation efficiency of FS-RC in the future.The high-value utilization of FS should be based on the physicochemical structural proper-ties of FS-RC and should focus on the environmental impact of hazardous elements and the recyclability of chemical waste liquid to es-tablish an environmentally friendly utilization method.This review is of great theoretical importance for the comprehensive understand-ing of the unique structural properties of FS-RC,the breakthrough of the technological bottleneck in the efficient flotation separation of FS,and the expansion of the field of the high value-added utilization of FS-RC.

Endoscopic features and treatments of gastric cystica profunda

BACKGROUND Gastric cystica profunda(GCP)represents a rare condition characterized by cystic dilation of gastric glands within the mucosal and/or submucosal layers.GCP is often linked to,or may progress into,early gastric cancer(EGC).AIM To provide a comprehensive evaluation of the endoscopic features of GCP while assessing the efficacy of endoscopic treatment,thereby offering guidance for diagnosis and treatment.METHODS This retrospective study involved 104 patients with GCP who underwent endoscopic resection.Alongside demographic and clinical data,regular patient followups were conducted to assess local recurrence.RESULTS Among the 104 patients diagnosed with GCP who underwent endoscopic resection,12.5%had a history of previous gastric procedures.The primary site predominantly affected was the cardia(38.5%,n=40).GCP commonly exhibited intraluminal growth(99%),regular presentation(74.0%),and ulcerative mucosa(61.5%).The leading endoscopic feature was the mucosal lesion type(59.6%,n=62).The average maximum diameter was 20.9±15.3 mm,with mucosal involvement in 60.6%(n=63).Procedures lasted 73.9±57.5 min,achieving complete resection in 91.3%(n=95).Recurrence(4.8%)was managed via either surgical intervention(n=1)or through endoscopic resection(n=4).Final pathology confirmed that 59.6%of GCP cases were associated with EGC.Univariate analysis indicated that elderly males were more susceptible to GCP associated with EGC.Conversely,multivariate analysis identified lesion morphology and endoscopic features as significant risk factors.Survival analysis demonstrated no statistically significant difference in recurrence between GCP with and without EGC(P=0.72).CONCLUSION The findings suggested that endoscopic resection might serve as an effective and minimally invasive treatment for GCP with or without EGC.

Structural features and exploration targets of platform margins in Sinian Dengying Formation in Deyang-Anyue Rift, Sichuan Basin, SW China

Based on the seismic, logging, drilling and other data, the distribution, structural types and mound-shoal hydrocarbon accumulation characteristics of platform margins of the Sinian Dengying Formation in the Deyang-Anyue Rift and its periphery were analyzed. Four types of platform margins are developed in the Dengying Formation, i.e., single-stage fault-controlled platform margin, multi-stage fault-controlled platform margin, gentle slope platform margin, and overlapping platform margin. In the Gaoshiti West-Weiyuan East area, single-stage fault controlled platform margins are developed in the Deng 2 Member, which trend in nearly NEE direction and are shielded by faults and mudstones, forming fault-controlled–lithologic traps. In the Lezhi-Penglai area, independent and multi-stage fault controlled platform margins are developed in the Deng 2 Member, which trend in NE direction and are controlled by synsedimentary faults;the mound-shoal complexes are aggraded and built on the hanging walls of the faults, and they are shielded by tight intertidal belts and the Lower Cambrian source rocks in multiple directions, forming fault-controlled–lithologic and other composite traps. In the Weiyuan-Ziyang area, gentle slope platform margins are developed in the Deng 2 Member, which trend in NW direction;the mound-shoal complexes are mostly thin interbeds as continuous bands and shielded by tight intertidal belts in the updip direction, forming lithologic traps. In the Gaoshiti-Moxi-Yanting area, overlapping platform margins are developed in the Deng 2 and Deng 4 members;the mound-shoal complexes are aggraded and overlaid to create platform margin buildup with a huge thickness and sealed by tight intertidal belts and the Lower Cambrian mudstones in the updip direction, forming large-scale lithologic traps on the north slope of the Central Sichuan Paleouplift. To summarize, the mound-shoal complexes on the platform margins in the Dengying Formation in the Penglai-Zhongjiang area, Moxi North-Yanting area and Weiyuan-Ziyang area are large in scale, with estimated resources of 1.58×1012 m3, and they will be the key targets for the future exploration of the Dengying Formation in the Sichuan Basin.

Layered Structural PBAT Composite Foams for Efficient Electromagnetic Interference Shielding

The utilization of eco-friendly,lightweight,high-efficiency and high-absorbing electromagnetic interference(EMI)shielding composites is imperative in light of the worldwide promotion of sustainable manufacturing.In this work,magnetic poly(butyleneadipate-coterephthalate)(PBAT)microspheres were firstly synthesized via phase separation method,then PBAT composite foams with layered structure was constructed through the supercritical carbon dioxide foaming and scraping techniques.The merits of integrating ferroferric oxideloaded multi-walled carbon nanotubes(Fe3O4@MWCNTs)nanoparticles,a microcellular framework,and a highly conductive silver layer have been judiciously orchestrated within this distinctive layered configuration.Microwaves are consumed throughout the process of“absorption-reflection-reabsorption”as much as possible,which greatly declines the secondary radiation pollution.The biodegradable PBAT composite foams achieved an EMI shielding effectiveness of up to 68 dB and an absorptivity of 77%,and authenticated favorable stabilization after the tape adhesion experiment.

Japanese Sign Language Recognition by Combining Joint Skeleton-Based Handcrafted and Pixel-Based Deep Learning Features with Machine Learning Classification

Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.

Artificial intelligence-driven radiomics study in cancer:the role of feature engineering and modeling

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.

Cross-Dimension Attentive Feature Fusion Network for Unsupervised Time-Series Anomaly Detection

Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.

An origami shield with supporting frame structures optimized by a feature-driven topology optimization method

In this paper,the design,manufacture and testing of an origami protective shield with a supporting frame structure are presented.It consists of an origami shield surface and a deployable supporting frame structure that needs to be portable and sufficiently stiff.First,for the design of the shield surface,a threestage origami crease pattern is developed to reduce the shield size in the folded state.The shield surface consists of several stiff modular panels and layered with flexible fabric.The modular panels are made of a multi-layer composite where a ceramic layer is made of small pieces to improve durability as those small pieces enable restriction of crack propagation.Then,the supporting frame structure is designed as a chain-of-bars structure in order to fold into a highly compact state as a bundle of bars and deploy in sequence.Thus,a feature-driven topology structural optimization method preserving component sequence is developed where the inter-dependence of sub-structures is taken into account.A bar with semi-circular ends is used as a basic design feature.The positions of the bar’s end points are treated as design variables and the width of the bars is kept constant.Then,a constraint on the total length of the chain of bars is introduced.Finally,the modular panels made of multi-layer composite and the full-scale prototype of the origami shield are fabricated and tested to verify the bullet-proof performance.

Feature extraction and learning approaches for cancellable biometrics:A survey

Biometric recognition is a widely used technology for user authentication.In the application of this technology,biometric security and recognition accuracy are two important issues that should be considered.In terms of biometric security,cancellable biometrics is an effective technique for protecting biometric data.Regarding recognition accuracy,feature representation plays a significant role in the performance and reliability of cancellable biometric systems.How to design good feature representations for cancellable biometrics is a challenging topic that has attracted a great deal of attention from the computer vision community,especially from researchers of cancellable biometrics.Feature extraction and learning in cancellable biometrics is to find suitable feature representations with a view to achieving satisfactory recognition performance,while the privacy of biometric data is protected.This survey informs the progress,trend and challenges of feature extraction and learning for cancellable biometrics,thus shedding light on the latest developments and future research of this area.

Petrographic and Structural Studies of the Guintéguéla Formations (Northwest of Côte d’Ivoire)

Côte d’Ivoire is currently experiencing strong growth in the mining sector. Identifying the formations present in our subsoil is therefore essential for mining recovery. It is in this context that we conducted studies on the formations present in the locality of Guintéguéla. It is located in the northwest of Côte d’Ivoire in the bafing region. The aim of this work was to determine the petrographic and structural characteristics of the formations of the area. The methodology began with documentation and then followed petrography and structural analysis work on the macroscopic and microscopic levels. We observed six groups of rocks: granitoids, amphibolites, orthogneiss, quartzites (poor and rich in magnetites), volcano-sediments and filonian rocks. Metamorphism is of amphibolite to granulite facies. However, volcano-sediments must be associated with the green schist facies. With regard to the structural, structures and microstructures such as foliation;fractures;sigmoidal figures reveal that the studied area was affected by ductile and also brittle tectonics whose main directions are oriented along the shear corridor, so N-S to NNW-SSE.

Aerodynamic Features of High-Speed Maglev Trains with Different Marshaling Lengths Running on a Viaduct under Crosswinds

The safety and stability of high-speed maglev trains traveling on viaducts in crosswinds critically depend on their aerodynamic characteristics.Therefore,this paper uses an improved delayed detached eddy simulation(IDDES)method to investigate the aerodynamic features of high-speed maglev trains with different marshaling lengths under crosswinds.The effects of marshaling lengths(varying from 3-car to 8-car groups)on the train’s aerodynamic performance,surface pressure,and the flow field surrounding the train were investigated using the three-dimensional unsteady compressible Navier-Stokes(N-S)equations.The results showed that the marshaling lengths had minimal influence on the aerodynamic performance of the head and middle cars.Conversely,the marshaling lengths are negatively correlated with the time-average side force coefficient(CS)and time-average lift force coefficient(Cl)of the tail car.Compared to the tail car of the 3-car groups,the CS and Cl fell by 27.77%and 18.29%,respectively,for the tail car of the 8-car groups.It is essential to pay more attention to the operational safety of the head car,as it exhibits the highest time average CS.Additionally,the mean pressure difference between the two sides of the tail car body increased with the marshaling lengths,and the side force direction on the tail car was opposite to that of the head and middle cars.Furthermore,the turbulent kinetic energy of the wake structure on the windward side quickly decreased as marshaling lengths increased.

Feature Matching via Topology-Aware Graph Interaction Model

Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.

Multi-Strategy Assisted Multi-Objective Whale Optimization Algorithm for Feature Selection

In classification problems,datasets often contain a large amount of features,but not all of them are relevant for accurate classification.In fact,irrelevant features may even hinder classification accuracy.Feature selection aims to alleviate this issue by minimizing the number of features in the subset while simultaneously minimizing the classification error rate.Single-objective optimization approaches employ an evaluation function designed as an aggregate function with a parameter,but the results obtained depend on the value of the parameter.To eliminate this parameter’s influence,the problem can be reformulated as a multi-objective optimization problem.The Whale Optimization Algorithm(WOA)is widely used in optimization problems because of its simplicity and easy implementation.In this paper,we propose a multi-strategy assisted multi-objective WOA(MSMOWOA)to address feature selection.To enhance the algorithm’s search ability,we integrate multiple strategies such as Levy flight,Grey Wolf Optimizer,and adaptive mutation into it.Additionally,we utilize an external repository to store non-dominant solution sets and grid technology is used to maintain diversity.Results on fourteen University of California Irvine(UCI)datasets demonstrate that our proposed method effectively removes redundant features and improves classification performance.The source code can be accessed from the website:https://github.com/zc0315/MSMOWOA.

Clinical features and prognostic factors of duodenal neuroendocrine tumours:A comparative study of ampullary and nonampullary regions

BACKGROUND Duodenal neuroendocrine tumours(DNETs)are rare neoplasms.However,the incidence of DNETs has been increasing in recent years,especially as an incidental finding during endoscopic studies.Regrettably,there is no consensus regarding the ideal treatment of DNETs.Even there are few studies on the clinical features and survival analysis of DNETs.AIM To analyze the clinical characteristics and prognostic factors of patients with duodenal neuroendocrine tumours.METHODS The clinical data of DNETs diagnosed in the First Affiliated Hospital of Air Force Military Medical University from June 2011 to July 2022 were collected.Neuroen-docrine tumours located in the ampulla area of the duodenum were divided into the ampullary region group;neuroendocrine tumours in any part of the duo-denum outside the ampullary area were divided into the nonampullary region group.Using a retrospective study,the clinical characteristics of the two groups and risk factors affecting the survival of DNET patients were analysed.RESULTS Twenty-nine DNET patients were screened.The male to female ratio was 1:1.9,and females comprised the majority.The ampullary region group accounted for 24.1%(7/29),while the nonampullary region group accounted for 75.9%(22/29).When diagnosed,the clinical symptoms of the ampullary region group were mainly abdominal pain(85.7%),while those of the nonampullary region groups were mainly abdominal distension(59.1%).There were differences in the composition of staging of tumours between the two groups(Fisher's exact probability method,P=0.001),with nonampullary stage II tumours(68.2%)being the main stage(P<0.05).After the diagnosis of DNETs,the survival rate of the ampullary region group was 14.3%(1/7),which was lower than that of 72.7%(16/22)in the nonampullary region group(Fisher's exact probability method,P=0.011).The survival time of the ampullary region group was shorter than that of the nonampullary region group(P<0.000).The median survival time of the ampullary region group was 10.0 months and that of the nonampullary region group was 451.0 months.Multivariate analysis showed that tumours in the ampulla region and no surgical treatment after diagnosis were independent risk factors for the survival of DNET patients(HR=0.029,95%CI 0.004-0.199,P<0.000;HR=12.609,95%CI:2.889-55.037,P=0.001).Further analysis of nonampullary DNET patients showed that the survival time of patients with a tumour diameter<2 cm was longer than that of patients with a tumour diameter≥2 cm(t=7.243,P=0.048).As of follow-up,6 patients who died of nonampullary DNETs had a tumour diameter that was≥2 cm,and 3 patients in stage IV had liver metastasis.Patients with a tumour diameter<2 cm underwent surgical treatment,and all survived after surgery.CONCLUSION Surgical treatment is a protective factor for prolonging the survival of DNET patients.Compared to DNETs in the ampullary region,patients in the nonampullary region group had a longer survival period.The liver is the organ most susceptible to distant metastasis of nonampullary DNETs.

A Fusion Localization Method Based on Target Measurement Error Feature Complementarity and Its Application

In the multi-radar networking system,aiming at the problem of locating long-distance targets synergistically with difficulty and low accuracy,a dual-station joint positioning method based on the target measurement error feature complementarity is proposed.For dual-station joint positioning,by constructing the target positioning error distribution model and using the complementarity of spatial measurement errors of the same long-distance target,the area with high probability of target existence can be obtained.Then,based on the target distance information,the midpoint of the intersection between the target positioning sphere and the positioning tangent plane can be solved to acquire the target's optimal positioning result.The simulation demonstrates that this method greatly improves the positioning accuracy of target in azimuth direction.Compared with the traditional the dynamic weighted fusion(DWF)algorithm and the filter-based dynamic weighted fusion(FBDWF)algorithm,it not only effectively eliminates the influence of systematic error in the azimuth direction,but also has low computational complexity.Furthermore,for the application scenarios of multi-radar collaborative positioning and multi-sensor data compression filtering in centralized information fusion,it is recommended that using radar with higher ranging accuracy and the lengths of baseline between radars are 20–100 km.

Relationships between Terrain Features and Forecasting Errors of Surface Wind Speeds in a Mesoscale Numerical Weather Prediction Model

Numerical weather prediction(NWP)models have always presented large forecasting errors of surface wind speeds over regions with complex terrain.In this study,surface wind forecasts from an operational NWP model,the SMS-WARR(Shanghai Meteorological Service-WRF ADAS Rapid Refresh System),are analyzed to quantitatively reveal the relationships between the forecasted surface wind speed errors and terrain features,with the intent of providing clues to better apply the NWP model to complex terrain regions.The terrain features are described by three parameters:the standard deviation of the model grid-scale orography,terrain height error of the model,and slope angle.The results show that the forecast bias has a unimodal distribution with a change in the standard deviation of orography.The minimum ME(the mean value of bias)is 1.2 m s^(-1) when the standard deviation is between 60 and 70 m.A positive correlation exists between bias and terrain height error,with the ME increasing by 10%−30%for every 200 m increase in terrain height error.The ME decreases by 65.6%when slope angle increases from(0.5°−1.5°)to larger than 3.5°for uphill winds but increases by 35.4%when the absolute value of slope angle increases from(0.5°−1.5°)to(2.5°−3.5°)for downhill winds.Several sensitivity experiments are carried out with a model output statistical(MOS)calibration model for surface wind speeds and ME(RMSE)has been reduced by 90%(30%)by introducing terrain parameters,demonstrating the value of this study.

Comparing the Structural Parameters of the Milky Way to Other Spiral Galaxies

The structural parameters of a galaxy can be used to gain insight into its formation and evolution history.In this paper,we strive to compare the Milky Way’s structural parameters to other,primarily edge-on,spiral galaxies in order to determine how our Galaxy measures up to the Local Universe.For our comparison,we use the galaxy structural parameters gathered from a variety of literature sources in the optical and near-infrared wave bands.We compare the scale length,scale height,and disk flatness for both the thin and thick disks,the thick-to-thin disk mass ratio,the bulge-to-total luminosity ratio,and the mean pitch angle of the Milky Way’s spiral arms to those in other galaxies.We conclude that many of the Milky Way’s structural parameters are largely ordinary and typical of spiral galaxies in the Local Universe,though the Galaxy’s thick disk appears to be appreciably thinner and less extended than expected from zoom-in cosmological simulations of Milky Way-mass galaxies with a significant contribution of galaxy mergers involving satellite galaxies.

Olive Leaf Disease Detection via Wavelet Transform and Feature Fusion of Pre-Trained Deep Learning Models

Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.

A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.