Self-supervised recalibration network for person re-identification

The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have the following two shortcomings:On the one hand,they mostly use global average pooling to generate context descriptors,without highlighting the guiding role of salient information on descriptor generation,resulting in insufficient ability of the final generated attention mask representation;On the other hand,the design of most attention modules is complicated,which greatly increases the computational cost of the model.To solve these problems,this paper proposes an attention module called self-supervised recalibration(SR)block,which introduces both global and local information through adaptive weighted fusion to generate a more refined attention mask.In particular,a special"Squeeze-Excitation"(SE)unit is designed in the SR block to further process the generated intermediate masks,both for nonlinearizations of the features and for constraint of the resulting computation by controlling the number of channels.Furthermore,we combine the most commonly used Res Net-50 to construct the instantiation model of the SR block,and verify its effectiveness on multiple Re-ID datasets,especially the mean Average Precision(m AP)on the Occluded-Duke dataset exceeds the state-of-the-art(SOTA)algorithm by 4.49%.

Augmented Deep Multi-Granularity Pose-Aware Feature Fusion Network for Visible-Infrared Person Re-Identification

Visible-infrared Cross-modality Person Re-identification(VI-ReID)is a critical technology in smart public facilities such as cities,campuses and libraries.It aims to match pedestrians in visible light and infrared images for video surveillance,which poses a challenge in exploring cross-modal shared information accurately and efficiently.Therefore,multi-granularity feature learning methods have been applied in VI-ReID to extract potential multi-granularity semantic information related to pedestrian body structure attributes.However,existing research mainly uses traditional dual-stream fusion networks and overlooks the core of cross-modal learning networks,the fusion module.This paper introduces a novel network called the Augmented Deep Multi-Granularity Pose-Aware Feature Fusion Network(ADMPFF-Net),incorporating the Multi-Granularity Pose-Aware Feature Fusion(MPFF)module to generate discriminative representations.MPFF efficiently explores and learns global and local features with multi-level semantic information by inserting disentangling and duplicating blocks into the fusion module of the backbone network.ADMPFF-Net also provides a new perspective for designing multi-granularity learning networks.By incorporating the multi-granularity feature disentanglement(mGFD)and posture information segmentation(pIS)strategies,it extracts more representative features concerning body structure information.The Local Information Enhancement(LIE)module augments high-performance features in VI-ReID,and the multi-granularity joint loss supervises model training for objective feature learning.Experimental results on two public datasets show that ADMPFF-Net efficiently constructs pedestrian feature representations and enhances the accuracy of VI-ReID.

Dual-stream coupling network with wavelet transform for cross-resolution person re-identification

Person re-identification is a prevalent technology deployed on intelligent surveillance.There have been remarkable achievements in person re-identification methods based on the assumption that all person images have a sufficiently high resolution,yet such models are not applicable to the open world.In real world,the changing distance between pedestrians and the camera renders the resolution of pedestrians captured by the camera inconsistent.When low-resolution(LR)images in the query set are matched with high-resolution(HR)images in the gallery set,it degrades the performance of the pedestrian matching task due to the absent pedestrian critical information in LR images.To address the above issues,we present a dualstream coupling network with wavelet transform(DSCWT)for the cross-resolution person re-identification task.Firstly,we use the multi-resolution analysis principle of wavelet transform to separately process the low-frequency and high-frequency regions of LR images,which is applied to restore the lost detail information of LR images.Then,we devise a residual knowledge constrained loss function that transfers knowledge between the two streams of LR images and HR images for accessing pedestrian invariant features at various resolutions.Extensive qualitative and quantitative experiments across four benchmark datasets verify the superiority of the proposed approach.

Pure Detail Feature Extraction Network for Visible-Infrared Re-Identification

Cross-modality pedestrian re-identification has important appli-cations in the field of surveillance.Due to variations in posture,camera per-spective,and camera modality,some salient pedestrian features are difficult to provide effective retrieval cues.Therefore,it becomes a challenge to design an effective strategy to extract more discriminative pedestrian detail.Although many effective methods for detailed feature extraction are proposed,there are still some shortcomings in filtering background and modality noise.To further purify the features,a pure detail feature extraction network(PDFENet)is proposed for VI-ReID.PDFENet includes three modules,adaptive detail mask generation module(ADMG),inter-detail interaction module(IDI)and cross-modality cross-entropy(CMCE).ADMG and IDI use human joints and their semantic associations to suppress background noise in features.CMCE guides the model to ignore modality noise by generating modality-shared feature labels.Specifically,ADMG generates masks for pedestrian details based on pose estimation.Masks are used to suppress background information and enhance pedestrian detail information.Besides,IDI mines the semantic relations among details to further refine the features.Finally,CMCE cross-combines classifiers and features to generate modality-shared feature labels to guide model training.Extensive ablation experiments as well as visualization results have demonstrated the effectiveness of PDFENet in eliminating background and modality noise.In addition,comparison experi-ments in two publicly available datasets also show the competitiveness of our approach.

High-speed penetration of ogive-nose projectiles into thick concrete targets:Tests and a projectile nose evolution model

The majority of the projectiles used in the hypersonic penetration study are solid flat-nosed cylindrical projectiles with a diameter of less than 20 mm.This study aims to fill the gap in the experimental and analytical study of the evolution of the nose shape of larger hollow projectiles under hypersonic penetration.In the hypersonic penetration test,eight ogive-nose AerMet100 steel projectiles with a diameter of 40 mm were launched to hit concrete targets with impact velocities that ranged from 1351 to 1877 m/s.Severe erosion of the projectiles was observed during high-speed penetration of heterogeneous targets,and apparent localized mushrooming occurred in the front nose of recovered projectiles.By examining the damage to projectiles,a linear relationship was found between the relative length reduction rate and the initial kinetic energy of projectiles in different penetration tests.Furthermore,microscopic analysis revealed the forming mechanism of the localized mushrooming phenomenon for eroding penetration,i.e.,material spall erosion abrasion mechanism,material flow and redistribution abrasion mechanism and localized radial upsetting deformation mechanism.Finally,a model of highspeed penetration that included erosion was established on the basis of a model of the evolution of the projectile nose that considers radial upsetting;the model was validated by test data from the literature and the present study.Depending upon the impact velocity,v0,the projectile nose may behave as undistorted,radially distorted or hemispherical.Due to the effects of abrasion of the projectile and enhancement of radial upsetting on the duration and amplitude of the secondary rising segment in the pulse shape of projectile deceleration,the predicted DOP had an upper limit.

Visible-infrared person re-identification using query related cluster

Visible-infrared person re-identification(VIPR), is a cross-modal retrieval task that searches a target from a gallery captured by cameras of different spectrums.The severe challenge for VIPR is the large intra-class variation caused by the modal discrepancy between visible and infrared images.For that, this paper proposes a query related cluster(QRC) method for VIPR.Firstly, this paper uses an attention mechanism to calculate the similarity relation between a visible query and infrared images with the same identity in the gallery.Secondly, those infrared images with the same query images are aggregated by using the similarity relation to form a dynamic clustering center corresponding to the query image.Thirdly, QRC loss function is designed to enlarge the similarity between the query image and its dynamic cluster center to achieve query related clustering, so as to compact the intra-class variations.Consequently, in the proposed QRC method, each query has its own dynamic clustering center, which can well characterize intra-class variations in VIPR.Experimental results demonstrate that the proposed QRC method is superior to many state-of-the-art approaches, acquiring a 90.77% rank-1 identification rate on the RegDB dataset.

Real-time Rescue Target Detection Based on UAV Imagery for Flood Emergency Response

Timely acquisition of rescue target information is critical for emergency response after a flood disaster.Unmanned Aerial Vehicles(UAVs)equipped with remote sensing capabilities offer distinct advantages,including high-resolution imagery and exceptional mobility,making them well suited for monitoring flood extent and identifying rescue targets during floods.However,there are some challenges in interpreting rescue information in real time from flood images captured by UAVs,such as the complexity of the scenarios of UAV images,the lack of flood rescue target detection datasets and the limited real-time processing capabilities of the airborne on-board platform.Thus,we propose a real-time rescue target detection method for UAVs that is capable of efficiently delineating flood extent and identifying rescue targets(i.e.,pedestrians and vehicles trapped by floods).The proposed method achieves real-time rescue information extraction for UAV platforms by lightweight processing and fusion of flood extent extraction model and target detection model.The flood inundation range is extracted by the proposed method in real time and detects targets such as people and vehicles to be rescued based on this layer.Our experimental results demonstrate that the Intersection over Union(IoU)for flood water extraction reaches an impressive 80%,and the IoU for real-time flood water extraction stands at a commendable 76.4%.The information on flood stricken targets extracted by this method in real time can be used for flood emergency rescue.

Mitophagy in intracerebral hemorrhage:a new target for therapeutic intervention

Intracerebral hemorrhage is a life-threatening condition with a high fatality rate and severe sequelae.However,there is currently no treatment available for intracerebral hemorrhage,unlike for other stroke subtypes.Recent studies have indicated that mitochondrial dysfunction and mitophagy likely relate to the pathophysiology of intracerebral hemorrhage.Mitophagy,or selective autophagy of mitochondria,is an essential pathway to preserve mitochondrial homeostasis by clearing up damaged mitochondria.Mitophagy markedly contributes to the reduction of secondary brain injury caused by mitochondrial dysfunction after intracerebral hemorrhage.This review provides an overview of the mitochondrial dysfunction that occurs after intracerebral hemorrhage and the underlying mechanisms regarding how mitophagy regulates it,and discusses the new direction of therapeutic strategies targeting mitophagy for intracerebral hemorrhage,aiming to determine the close connection between mitophagy and intracerebral hemorrhage and identify new therapies to modulate mitophagy after intracerebral hemorrhage.In conclusion,although only a small number of drugs modulating mitophagy in intracerebral hemorrhage have been found thus far,most of which are in the preclinical stage and require further investigation,mitophagy is still a very valid and promising therapeutic target for intracerebral hemorrhage in the long run.

Person Re-Identification with Model-Contrastive Federated Learning in Edge-Cloud Environment

Person re-identification(ReID)aims to recognize the same person in multiple images from different camera views.Training person ReID models are time-consuming and resource-intensive;thus,cloud computing is an appropriate model training solution.However,the required massive personal data for training contain private information with a significant risk of data leakage in cloud environments,leading to significant communication overheads.This paper proposes a federated person ReID method with model-contrastive learning(MOON)in an edge-cloud environment,named FRM.Specifically,based on federated partial averaging,MOON warmup is added to correct the local training of individual edge servers and improve the model’s effectiveness by calculating and back-propagating a model-contrastive loss,which represents the similarity between local and global models.In addition,we propose a lightweight person ReID network,named multi-branch combined depth space network(MB-CDNet),to reduce the computing resource usage of the edge device when training and testing the person ReID model.MB-CDNet is a multi-branch version of combined depth space network(CDNet).We add a part branch and a global branch on the basis of CDNet and introduce an attention pyramid to improve the performance of the model.The experimental results on open-access person ReID datasets demonstrate that FRM achieves better performance than existing baseline.

Review of Visible-Infrared Cross-Modality Person Re-Identification

Person re-identification(ReID)is a sub-problem under image retrieval.It is a technology that uses computer vision to identify a specific pedestrian in a collection of pictures or videos.The pedestrian image under cross-device is taken from a monitored pedestrian image.At present,most ReID methods deal with the matching between visible and visible images,but with the continuous improvement of security monitoring system,more and more infrared cameras are used to monitor at night or in dim light.Due to the image differences between infrared camera and RGB camera,there is a huge visual difference between cross-modality images,so the traditional ReID method is difficult to apply in this scene.In view of this situation,studying the pedestrian matching between visible and infrared modalities is particularly crucial.Visible-infrared person re-identification(VI-ReID)was first proposed in 2017,and then attracted more and more attention,and many advanced methods emerged.

Target acquisition performance in the presence of JPEG image compression

This paper presents an investigation on the effect of JPEG compression on the similarity between the target image and the background,where the similarity is further used to determine the degree of clutter in the image.Four new clutter metrics based on image quality assessment are introduced,among which the Haar wavelet-based perceptual similarity index,known as HaarPSI,provides the best target acquisition prediction results.It is shown that the similarity between the target and the background at the boundary between visually lossless and visually lossy compression does not change significantly compared to the case when an uncompressed image is used.In future work,through subjective tests,it is necessary to check whether this presence of compression at the threshold of just noticeable differences will affect the human target acquisition performance.Similarity values are compared with the results of subjective tests of the well-known target Search_2 database,where the degree of agreement between objective and subjective scores,measured through linear correlation,reached a value of 90%.

Potentials of ribosomopathy gene as pharmaceutical targets for cancer treatment

Ribosomopathies encompass a spectrum of disorders arising from impaired ribosome biogenesis and reduced functionality.Mutation or dysexpression of the genes that disturb any finely regulated steps of ribosome biogenesis can result in different types of ribosomopathies in clinic,collectively known as ribosomopathy genes.Emerging data suggest that ribosomopathy patients exhibit a significantly heightened susceptibility to cancer.Abnormal ribosome biogenesis and dysregulation of some ribosomopathy genes have also been found to be intimately associated with cancer development.The correlation between ribosome biogenesis or ribosomopathy and the development of malignancies has been well established.This work aims to review the recent advances in the research of ribosomopathy genes among human cancers and meanwhile,to excavate the potential role of these genes,which have not or rarely been reported in cancer,in the disease development across cancers.We plan to establish a theoretical framework between the ribosomopathy gene and cancer development,to further facilitate the potential of these genes as diagnostic biomarker as well as pharmaceutical targets for cancer treatment.

Target Detection Algorithm in Foggy Scenes Based on Dual Subnets

Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the image by the universal detection network.Thus,a dual subnet based on multi-task collaborative training(DSMCT)is proposed in this paper.Firstly,in the training phase,the Gated Context Aggregation Network(GCANet)is used as the supervisory network of YOLOX to promote the extraction of clean information in foggy scenes.In the test phase,only the YOLOX branch needs to be activated to ensure the detection speed of the model.Secondly,the deformable convolution module is used to improve GCANet to enhance the model’s ability to capture details of non-homogeneous fog.Finally,the Coordinate Attention mechanism is introduced into the Vision Transformer and the backbone network of YOLOX is redesigned.In this way,the feature extraction ability of the network for deep-level information can be enhanced.The experimental results on artificial fog data set FOG_VOC and real fog data set RTTS show that the map value of DSMCT reached 86.56%and 62.39%,respectively,which was 2.27%and 4.41%higher than the current most advanced detection model.The DSMCT network has high practicality and effectiveness for target detection in real foggy scenes.

A Review of Research on Person Re-identification in Surveillance Video

Person re-identification has emerged as a hotspot for computer vision research due to the growing demands of social public safety requirements and the quick development of intelligent surveillance networks.Person re-identification(Re-ID)in video surveillance system can track and identify suspicious people,track and statistically analyze persons.The purpose of person re-identification is to recognize the same person in different cameras.Deep learning-based person re-identification research has produced numerous remarkable outcomes as a result of deep learning's growing popularity.The purpose of this paperis to help researchers better understand where person re-identification research is at the moment and where it is headed.Firstly,this paper arranges the widely used datasets and assessment criteria in person re-identification and reviews the pertinent research on deep learning-based person re-identification techniques conducted in the last several years.Then,the commonly used method techniques are also discussed from four aspects:appearance features,metric learning,local features,and adversarial learning.Finally,future research directions in the field of person re-identification are outlooked.

Targeting BCL9/BCL9L enhances antigen presentation by promoting conventional type 1 dendritic cell(cDC1)activation and tumor infiltration

Conventional type 1 dendritic cells(cDC1)are the essential antigen-presenting DC subset in antitumor immunity.Suppressing B-cell lymphoma 9 and B-cell lymphoma 9-like(BCL9/BCL9L)inhibits tumor growth and boosts immune responses against cancer.However,whether oncogenic BCL9/BCL9L impairs antigen presentation in tumors is still not completely understood.Here,we show that targeting BCL9/BCL9L enhanced antigen presentation by stimulating cDC1 activation and infiltration into tumor.Pharmacological inhibition of BCL9/BCL9L with a novel inhibitor hsBCL9z96 or Bcl9/Bcl9l knockout mice markedly delayed tumor growth and promoted antitumor CD8^(+)T cell responses.Mechanistically,targeting BCL9/BCL9L promoted antigen presentation in tumors.This is due to the increase of cDC1 activation and tumor infiltration by the XCL1-XCR1 axis.Importantly,using single-cell transcriptomics analysis,we found that Bcl9/Bcl9l deficient cDC1 were superior to wild-type(WT)cDC1 at activation and antigen presentation via NF-κB/IRF1 signaling.Together,we demonstrate that targeting BCL9/BCL9L plays a crucial role in cDC1-modulated antigen presentation of tumor-derived antigens,as well as CD8^(+)T cell activation and tumor infiltration.Targeting BCL9/BCL9L to regulate cDC1 function and directly orchestrate a positive feedback loop necessary for optimal antitumor immunity could serve as a potential strategy to counter immune suppression and enhance cancer immunotherapy.

Electromagnetic pulses produced by a picosecond laser interacting with solid targets

A high-power laser ablating solid targets induces giant electromagnetic pulses(EMPs),which are intimately pertinent to laser parameters,such as energy and pulse width.In this study,we reveal the features of EMPs generated from a picosecond(ps)laser irradiating solid targets at the SG-Ⅱpicosecond petawatt(PSPW)laser facility.The laser energy and pulse,as well as target material and thickness,show determinative effects on the EMPs’amplitude.More intense EMPs are detected behind targets compared to those at the other three positions,and the EMP amplitude decreases from 90.09 kV/m to 17.8 kV/m with the gold target thickness increasing from 10μm to 20μm,which is suppressed when the laser pulse width is enlarged.The results are expected to provide more insight into EMPs produced by ps lasers coupling with targets and lay the foundation for an effective EMP shielding design in high-power laser infrastructures.

Improved Weighted Local Contrast Method for Infrared Small Target Detection

In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted local contrast is proposed in this paper.First,the ratio information between the target and local background is utilized as an enhancement factor.The local contrast is calculated by incorporating the heterogeneity between the target and local background.Then,a local product weighted method is designed based on the spatial dissimilarity between target and background to further enhance target while suppressing background.Finally,the location of target is obtained by adaptive threshold segmentation.As experimental results demonstrate,the method shows superior performance in several evaluation metrics compared with six existing algorithms on different datasets containing targets such as unmanned aerial vehicles(UAV).

Distinct molecular targets of ProEGCG from EGCG and superior inhibition of angiogenesis signaling pathways for treatment of endometriosis

Endometriosis is a common chronic gynecological disease with endometrial cell implantation outside the uterus.Angiogenesis is a major pathophysiology in endometriosis.Our previous studies have demonstrated that the prodrug of epigallocatechin gallate(ProEGCG)exhibits superior anti-endometriotic and anti-angiogenic effects compared to epigallocatechin gallate(EGCG).However,their direct binding targets and underlying mechanisms for the differential effects remain unknown.In this study,we demonstrated that oral ProEGCG can be effective in preventing and treating endometriosis.Additionally,1D and 2D Proteome Integral Solubility Alteration assay-based chemical proteomics identified metadherin(MTDH)and PX domain containing serine/threonine kinase-like(PXK)as novel binding targets of EGCG and ProEGCG,respectively.Computational simulation and BioLayer interferometry were used to confirm their binding affinity.Our results showed that MTDH-EGCG inhibited protein kinase B(Akt)-mediated angiogenesis,while PXK-ProEGCG inhibited epidermal growth factor(EGF)-mediated angiogenesis via the EGF/hypoxia-inducible factor(HIF-1a)/vascular endothelial growth factor(VEGF)pathway.In vitro and in vivo knockdown assays and microvascular network imaging further confirmed the involvement of these signaling pathways.Moreover,our study demonstrated that ProEGCG has superior therapeutic effects than EGCG by targeting distinct signal transduction pathways and may act as a novel antiangiogenic therapy for endometriosis.

The functions of exosomes targeting astrocytes and astrocyte-derived exosomes targeting other cell types

Astrocytes are the most abundant glial cells in the central nervous system;they participate in crucial biological processes,maintain brain structure,and regulate nervous system function.Exosomes are cell-derived extracellular vesicles containing various bioactive molecules including proteins,peptides,nucleotides,and lipids secreted from their cellular sources.Increasing evidence shows that exosomes participate in a communication network in the nervous system,in which astrocyte-derived exosomes play important roles.In this review,we have summarized the effects of exosomes targeting astrocytes and the astrocyte-derived exosomes targeting other cell types in the central nervous system.We also discuss the potential research directions of the exosome-based communication network in the nervous system.The exosome-based intercellular communication focused on astrocytes is of great significance to the biological and/or pathological processes in different conditions in the brain.New strategies may be developed for the diagnosis and treatment of neurological disorders by focusing on astrocytes as the central cells and utilizing exosomes as communication mediators.

Spatial and temporal evolution of electromagnetic pulses from solid target irradiated with multi-hundred-terawatt laser pulse inside target chamber

Giant electromagnetic pulses(EMPs) induced by high-power laser irradiating solid targets interfere with various experimental diagnoses and even damage equipment,so unveiling the evolution of EMPs inside the laser chamber is crucial for designing effective EMP shielding.In this work,the transmission characteristics of EMPs as a function of distances from the target chamber center(TCC) are studied using B-dot probes.The mean EMP amplitude generated by picosecond laser-target interaction reaches 561 kV m^(-1),357 kV m^(-1),395 kV m^(-1),and 341 kV m^(-1)at 0.32 m,0.53 m,0.76 m,and 1 m from TCC,which decreases dramatically from 0.32 m to 0.53 m.However,it shows a fluctuation from 0.53 m to 1 m.The temporal features of EMPs indicate that time-domain EMP signals near the target chamber wall have a wider full width at half maximum compared to that close to TCC,mainly due to the echo oscillation of electromagnetic waves inside the target chamber based on simulation and experimentation.The conclusions of this study will provide a new approach to mitigate strong electromagnetic pulses by decreasing the echo oscillation of electromagnetic waves inside the target chamber during laser coupling with targets.