Search

Abstract This study aimed to evaluate the regulatory effect and molecular mechanism of long noncoding RNA small nucleolus RNA host gene 8 (LncRNA SNHG8) in the migration and angiogenesis of primary human umbilical vein endothelial cells (pHUVECs) under high-glucose (HG) conditions. The HG-induced endothelial injury model was established in vitro.The cell model of silencing SNHG8, overexpressing SNHG8, and silencing TRPM7 was established by transfecting SNHG8-siRNA, SNHG8 plasmid and TRPM7-siRNA into cells with liposomes.The SNHG8 level was determined through reverse transcription-quantitative polymerase chain reaction (RT-qPCR). The expression levels of transient receptor potential melastatin 7 (TRPM7), endothelial nitric oxide synthase (eNOS), p-eNOS, extracellular signal-regulated kinase 1/2(ERK1/2), and p-ERK1/2 were assessed through western blot. Nitric oxide (NO) levels were measured with DAF-FM. pHUVEC migration was examined through wound healing and Transwell assay, and pHUVEC angiogenesis was observed through a tube formation assay. Results showed that HG promoted the expression of lncRNA SNHG8 and TRPM7 and decreased the ratio of p-eNOS/eNOS and p-ERK1/2/ERK1/2 in pHUVECs . NO production, migration , and angiogenesis were inhibited in pHUVECs under HG conditions. Silencing lncRNA SNHG8 and TRPM7 could significantly reverse the HG-induced decrease in eNOS activation, NO production , migration, and angiogenesis . SNHG8 and U0126 (ERK pathway inhibitor) overexpression enhanced the HG effects, whereas using U0126 did not affect the TRPM7 expression. In conclusion, lncRNA SNHG8 participates in HG-induced endothelial cell injury and likely regulates NO production, migration, and angiogenesis of pHUVECs via the TRPM7/ERK1/2 signaling axis.

Abstract Public metabolites such as vitamins play critical roles in maintaining the ecological functions of microbial community. However, the biochemical and physiological bases for fine-tuning of public metabolites in the microbiome remain poorly understood. Here, we examine the interactions between myxobacteria and Phytophthora sojae, an oomycete pathogen of soybean. We find that host plant and soil microbes complement P. sojae’s auxotrophy for thiamine. Whereas, myxobacteria inhibits Phytophthora growth by a thiaminase I CcThi1 secreted into extracellular environment via outer membrane vesicles (OMVs). CcThi1 scavenges the required thiamine and thus arrests the thiamine sharing behavior of P. sojae from the supplier, which interferes with amino acid metabolism and expression of pathogenic effectors, probably leading to impairment of P. sojae growth and pathogenicity. Moreover, myxobacteria and CcThi1 are highly effective in regulating the thiamine levels in soil, which is correlated with the incidence of soybean Phytophthora root rot. Our findings unravel a novel ecological tactic employed by myxobacteria to maintain the interspecific equilibrium in soil microbial community.

Abstract Background Pulmonary arterial hypertension (PAH) is a pathophysiological syndrome, characterized by pulmonary vascular remodeling. Immunity and inflammation are progressively recognized properties of PAH, which are crucial for the initiation and maintenance of pulmonary vascular remodeling. This study explored immune cell infiltration characteristics and potential biomarkers of PAH using comprehensive bioinformatics analysis. Methods Microarray data of GSE117261, GSE113439 and GSE53408 datasets were downloaded from Gene Expression Omnibus database. The differentially expressed genes (DEGs) were identified in GSE117261 dataset. The proportions of infiltrated immune cells were evaluated by CIBERSORT algorithm. Feature genes of PAH were selected by least absolute shrinkage and selection operator (LASSO) regression analysis and validated by fivefold cross-validation, random forest and logistic regression. The GSE113439 and GSE53408 datasets were used as validation sets and logistic regression and receiver operating characteristic (ROC) curve analysis were performed to evaluate the prediction value of PAH. The PAH-associated module was identified by weighted gene association network analysis (WGCNA). The intersection of genes in the modules screened and DEGs was used to construct protein–protein interaction (PPI) network and the core genes were selected. After the intersection of feature genes and core genes, the hub genes were identified. The correlation between hub genes and immune cell infiltration was analyzed by Pearson correlation analysis. The expression level of LTBP1 in the lungs of monocrotaline-induced PAH rats was determined by Western blotting. The localization of LTBP1 and CD4 in lungs of PAH was assayed by immunofluorescence. Results A total of 419 DEGs were identified, including 223 upregulated genes and 196 downregulated genes. Functional enrichment analysis revealed that a significant enrichment in inflammation, immune response, and transforming growth factor β (TGFβ) signaling pathway. CIBERSORT analysis showed that ten significantly different types of immune cells were identified between PAH and control. Resting memory CD4+ T cells, CD8+ T cells, γδ T cells, M1 macrophages, and resting mast cells in the lungs of PAH patients were significantly higher than control. Seventeen feature genes were identified by LASSO regression for PAH prediction. WGCNA identified 15 co-expression modules. PPI network was constructed and 100 core genes were obtained. Complement C3b/C4b receptor 1 (CR1), thioredoxin reductase 1 (TXNRD1), latent TGFβ binding protein 1 (LTBP1), and toll-like receptor 1 (TLR1) were identified as hub genes and LTBP1 has the highest diagnostic efficacy for PAH (AUC = 0.968). Pearson correlation analysis showed that LTBP1 was positively correlated with resting memory CD4+ T cells, but negatively correlated with monocytes and neutrophils. Western blotting showed that the protein level of LTBP1 was increased in the lungs of monocrotaline-induced PAH rats. Immunofluorescence of lung tissues from rats with PAH showed increased expression of LTBP1 in pulmonary arteries as compared to control and LTBP1 was partly colocalized with CD4+ cells in the lungs. Conclusion LTBP1 was correlated with immune cell infiltration and identified as the critical diagnostic maker for PAH.

Abstract MnSe and Co0.85Se embedded in nitrogen‐doped carbon nanofibers (MnSe/Co0.85Se/N‐CNFs) were synthesized by electrospinning and high‐temperature calcination, and evaluated for the first time as sodium/potassium‐ion battery anode material via constant current charge/discharge, cyclic voltammetry, electrochemical impedance spectroscopy.Ex‐situ XRD revealed the potassium storage mechanism of MnSe/Co0.85Se/N‐CNFs, indicating that its capacity was mainly provided by the conversion reaction. Compared with MnSe/N‐CNFs and Co0.85Se/N‐CNFs, the reversible capacity and cycling performance of MnSe/Co0.85Se/N‐CNFs were significantly improved due to the synergistic effect of bimetals. The MnSe/Co0.85Se/N‐CNFs electrode showed a charging capacity of 262.3 mAh g−1 after 700 cycles at 1 A g−1 in Na‐ion batteries and a discharge capacity of 183.4 mAh g−1 after 400 cycles at 0.1 A g−1 in K‐ion batteries, The results showed that binder‐free binary metal MnSe/Co0.85Se/N‐CNFs have a certain development prospect as anode for sodium/potassium‐ion batteries.

Background: The aim of this study was to explore the correlation between high-risk human papillomavirus (HR-HPV) infection and changes in vaginal microecology, as well as the severity of cervical intraepithelial lesions (CIN). Methods: A retrospective analysis was conducted on 221 inpatients (aged 23–80 years) who underwent simultaneous testing of vaginal secretions for microecological parameters, HR-HPV genotyping, and cervical tissue biopsy at the Department of Gynecology, Second Affiliated Hospital of Xinjiang Medical University, Urumqi, from October 2021 to January 2023. The study subjects were analyzed to determine the association between HR-HPV infection and alterations in vaginal microecology, as well as CIN. Results: Among the 221 cases, 69 were positive for HR-HPV, resulting in a positivity rate of 31.22% (69/221). Out of the 139 cases with normal vaginal microecology, 26 were positive for HR-HPV, yielding a positivity rate of 18.71% (26/139). Among the 82 cases with abnormal vaginal microecology, 43 were positive for HR-HPV, resulting in a positivity rate of 52.44% (43/82). Out of the 162 cases with normal cervix, 26 were positive for HR-HPV, resulting in a positivity rate of 16.00% (26/162). Among the 59 cases with abnormal cervix, 43 were positive for HR-HPV, resulting in a positivity rate of 72.88% (43/59). In the cases of abnormal cervix, 10 presented cervical inflammation, with a HR-HPV positivity rate of 70.00% (7/10); 20 cases had cervical intraepithelial lesions (CIN) I, with a HR-HPV positivity rate of 70.00% (14/20); 20 cases had CIN II, with a HR-HPV positivity rate of 75.00% (15/20); and 9 cases had CIN III, with a HR-HPV positivity rate of 77.80% (7/9). Moreover, among the 162 cases with normal cervix, 36 had abnormal vaginal microecology, resulting in an abnormality rate of 22.22% (36/162). Among the 59 cases with abnormal cervix, 46 had abnormal vaginal microecology, resulting in an abnormality rate of 77.97% (46/59). In the cases of abnormal cervix, 10 had cervical inflammation, with an abnormal vaginal microecology rate of 70.00% (7/10); 20 cases had CIN I, with an abnormal vaginal microecology rate of 70.00% (14/20); 20 cases had CIN II, with an abnormal vaginal microecology rate of 80.00% (16/20); and 9 cases had CIN III, with an abnormal vaginal microecology rate of 100.00% (9/9). The differences in HR-HPV positivity rates between the group with normal vaginal microecology and the group with abnormal vaginal microecology were statistically significant (p < 0.05). Similarly, the differences in HR-HPV positivity rates for different degrees of CIN were statistically significant (p < 0.05), as well as the differences in abnormal vaginal microecology rates for different degrees of CIN (p < 0.05). Conclusions: HR-HPV infection was found to be significantly associated with alterations in vaginal microecology and CIN.

Background: This study aimed to assess the efficacy and safety of laparoscopic and transvaginal cervical cerclage treatments in patients with cervical insufficiency before and during pregnancy. Methods: A total of 70 patients diagnosed with cervical insufficiency and undergoing cervical cerclage at the Second Affiliated Hospital of Xinjiang Medical University between January 2020 and December 2022 were included. The patients were divided into three groups based on different surgical methods: transvaginal loop during pregnancy (Group 1, n = 30), transabdominal loop before pregnancy (Group 2, n = 20), and transabdominal loop during pregnancy (Group 3, n = 20). The groups were compared in terms of general clinical data, operation time, intraoperative bleeding, hospital stay, delivery gestational weeks, preterm delivery rate, prolonged gestational weeks, and neonatal births. Results: (1) There were no statistically significant differences in age, pregnancy, delivery, number of miscarriages, cervical length, and history of midterm pregnancy loss among the three groups (p > 0.05). (2) Prolonged gestational week, delivery gestational week, term delivery, and neonatal birth weight were higher in Groups 2 and 3 compared to Group 1, with statistically significant differences (p < 0.05). There was no statistically significant difference (p > 0.05) when comparing Group 2 and Group 3. Premature rupture of membranes and preterm delivery were higher in Group 1 compared to Groups 2 and 3, with statistically significant differences (p < 0.05). There was no statistically significant difference when comparing Group 2 and Group 3 (p > 0.05). (3) The amount of surgical bleeding and surgical time showed statistically significant differences (p < 0.05) among the three groups. Group 1 had more surgical bleeding than Groups 2 and 3, with statistically significant differences (p < 0.05). When comparing Group 2 and Group 3, Group 3 had more surgical bleeding than Group 2, with a statistically significant difference (p < 0.05). Group 2 had a shorter surgical time than Group 1 and Group 3, with statistically significant differences (p < 0.05). When comparing Group 1 and Group 3, Group 3 had a longer surgical time than Group 1, with a statistically significant difference (p < 0.05). There was no statistically significant difference in hospital stay when comparing three groups (p > 0.05). Conclusions: Laparoscopic cervical cerclage is a safe and effective treatment option, yielding better pregnancy outcomes than transvaginal cervical cerclage, particularly for patients with previous failed transvaginal cerclage. Preconception laparoscopic cervical cerclage carries lower surgical risks and should be considered for clinical application.

Abstract Diabetes is a potential risk factor for gastric cancer (GC). Pin1, a peptidyl–prolyl cis/trans isomerase, promotes GC cell proliferation and migration. The role and underlying mechanism of the Pin1/BRD4 axis in hyperglycemia-induced proliferation and migration of GC cells were analyzed in vivo and in vitro. Proliferation and migration of GC cells were measured; Pin1 and BRD4 expression of the cell cycle were determined. Pin1 and BRD4 were downregulated by transfecting Pin1 shRNA lentivirus into GC cells and JQ1-intervention GC cells. Tumor formation and lung metastasis were assessed in vivo. Inhibition of Pin1 and BRD4 significantly suppressed high-glucose (HG)-induced GC cell proliferation and migration. HG enhanced G1/S cell-cycle transition, associated with increased Pin1 and BRD4 expression. Silencing Pin1 significantly downregulated the expression of BRD4 and NAP1L1 and upregulated that of P21 in GC cells. In vivo studies indicated that hyperglycemia promotes tumor growth and lung metastasis by inducing Pin1 and BRD4 expression. Thus, Pin1/BRD4 plays an important role in hyperglycemia-promoted tumor growth. The significance of these findings toward improved prognosis of diabetic patients with GC cannot be underestimated.

Background: Corneal fluorescein sodium staining is a valuable diagnostic method for various ocular surface diseases. However, the examination results are highly dependent on the subjective experience of ophthalmologists. Objectives: To develop an artificial intelligence system based on deep learning to provide an accurate quantitative assessment of sodium fluorescein staining score and the size of cornea epithelial patchy defect. Design: A prospective study. Methods: We proposed an artificial intelligence system for automatically evaluating corneal staining scores and accurately measuring patchy corneal epithelial defects based on corneal fluorescein sodium staining images. The design incorporates two segmentation models and a classification model to forecast and assess the stained images. Meanwhile, we compare the evaluation findings from the system with ophthalmologists with varying expertise. Results: For the segmentation task of cornea boundary and cornea epithelial patchy defect area, our proposed method can achieve the performance of dice similarity coefficient (DSC) is 0.98/0.97 and Hausdorff distance (HD) is 3.60/8.39, respectively, when compared with the manually labeled gold standard. This method significantly outperforms the four leading algorithms (Unet, Unet++, Swin-Unet, and TransUnet). For the classification task, our algorithm achieves the best performance in accuracy, recall, and F1-score, which are 91.2%, 78.6%, and 79.2%, respectively. The performance of our developed system exceeds seven different approaches (Inception, ShuffleNet, Xception, EfficientNet_B7, DenseNet, ResNet, and VIT) in classification tasks. In addition, three ophthalmologists were selected to rate corneal staining images. The results showed that the performance of our artificial intelligence system significantly outperformed the junior doctors. Conclusion: The system offers a promising automated assessment method for corneal fluorescein staining, decreasing incorrect evaluations caused by ophthalmologists’ subjective variance and limited knowledge.

Abstract The development of social networking services (SNSs) revealed a surge in image sharing. The sharing mode of multi-page photo collage (MPC), which posts several image collages at a time, can often be observed on many social network platforms, which enables uploading images and arrangement in a logical order. This study focuses on the construction of MPC for an image collection and its formulation as an issue of joint optimization, which involves not only the arrangement in a single collage but also the arrangement among different collages. Novel balance-aware measurements, which merge graphic features and psychological achievements, are introduced. Non-dominated sorting genetic algorithm is adopted to optimize the MPC guided by the measurements. Experiments demonstrate that the proposed method can lead to diverse, visually pleasant, and logically clear MPC results, which are comparable to manually designed MPC results.

Abstract Transformers, the dominant architecture for natural language processing, have also recently attracted much attention from computational visual media researchers due to their capacity for long-range representation and high performance. Transformers are sequence-to-sequence models, which use a self-attention mechanism rather than the RNN sequential structure. Thus, such models can be trained in parallel and can represent global information. This study comprehensively surveys recent visual transformer works. We categorize them according to task scenario: backbone design, high-level vision, low-level vision and generation, and multimodal learning. Their key ideas are also analyzed. Differing from previous surveys, we mainly focus on visual transformer methods in low-level vision and generation. The latest works on backbone design are also reviewed in detail. For ease of understanding, we precisely describe the main contributions of the latest works in the form of tables. As well as giving quantitative comparisons, we also present image results for low-level vision and generation tasks. Computational costs and source code links for various important works are also given in this survey to assist further development.

Abstract Background Cardiac remodeling is one of the major risk factors for heart failure. In patients with type 2 diabetes, sodium–glucose cotransporter 2 (SGLT2) inhibitors reduce the risk of the first hospitalization for heart failure, possibly through glucose-independent mechanisms in part, but the underlying mechanisms remain largely unknown. This study aimed to shed light on the efficacy of dapagliflozin in reducing cardiac remodeling and potential mechanisms. Methods Sprague–Dawley (SD) rats, induced by chronic infusion of Angiotensin II (Ang II) at a dose of 520 ng/kg per minute for 4 weeks with ALZET® mini-osmotic pumps, were treated with either SGLT2 inhibitor dapagliflozin (DAPA) or vehicle alone. Echocardiography was performed to determine cardiac structure and function. Cardiac fibroblasts (CFs) were treated with Ang II (1 μM) with or without the indicated concentration (0.5, 1, 10 μM) of DAPA. The protein levels of collagen and TGF-β1/Smad signaling were measured along with body weight, and blood biochemical indexes. Results DAPA pretreatment resulted in the amelioration of left ventricular dysfunction in Ang II-infused SD rats without affecting blood glucose and blood pressure. Myocardial hypertrophy, fibrosis and increased collagen synthesis caused by Ang II infusion were significantly inhibited by DAPA pretreatment. In vitro, DAPA inhibit the Ang II-induced collagen production of CFs. Immunoblot with heart tissue homogenates from chronic Ang II-infused rats revealed that DAPA inhibited the activation of TGF-β1/Smads signaling. Conclusion DAPA ameliorates Ang II-induced cardiac remodeling by regulating the TGF-β1/Smad signaling in a non-glucose-lowering dependent manner.

Abstract The benefits and harms of corticosteroids for patients with severe coronavirus disease 2019 (COVID-19) remain unclear. We systematically searched PubMed, Embase, and Cochrane Central Register of Controlled Trials from December 31, 2019 to October 1, 2020 to identify randomized controlled trials (RCTs) that evaluated corticosteroids in severe COVID-19 patients. The primary outcome was all-cause mortality at the longest follow-up. Secondary outcomes included a composite disease progression (progression to intubation, ventilation, extracorporeal membrane oxygenation, ICU transfer, or death among those not ventilated at enrollment) and incidence of serious adverse events. A random-effects model was applied to calculate risk ratio (RR) with 95% confidence intervals (CIs). We used the Grading of Recommendations Assessment, Development, and Evaluation approach to evaluate the certainty of the evidence. Seven RCTs involving 6250 patients were included, of which the Randomized Evaluation of COVID-19 Therapy (RECOVERY) trial comprised nearly 78% of all included subjects. Results showed that corticosteroids were associated with a decreased all-cause mortality (27.3 vs. 31.1%; RR: 0.85; 95% CI: 0.73–0.99; P = 0.04; low-certainty evidence). Trial sequential analysis suggested that more trials were still required to confirm the results. However, such survival benefit was absent if RECOVERY trial was excluded (RR: 0.83; 95% CI: 0.65–1.06; P = 0.13). Furthermore, corticosteroids decreased the occurrence of composite disease progression (30.6 vs. 33.3%; RR: 0.77; 95% CI: 0.64–0.92; P = 0.005), but not increased the incidence of serious adverse events (3.5 vs. 3.4%; RR: 1.16; 95% CI: 0.39–3.43; P = 0.79).

Complement C3 plays a prominent role in inflammatory processes, and its increase exacerbates ischemia reperfusion injury (IRI)-induced acute kidney injury (AKI). Infiltrated neutrophils can be stimulated to form neutrophil extracellular traps (NETs), leading to renal injury. However, the relationship between the increase of C3 and the release of NETs in AKI was not clear. Here we found that IRI in the mouse kidney leads to increased neutrophils infiltration and NET formation. Furthermore, neutrophils depletion by anti-Ly6G IgG (1A8) did not reduce C3 activation but reduced kidney injury and inflammation, indicating a link between neutrophils infiltration and renal tissue damage. Pretreatment with 1A8 suppressed ischemia-induced NET formation, proving that extracellular traps (ETs) in renal tissue were mainly derived from neutrophils. Renal ischemia injury also leads to increased expression of C3. Moreover, C3 KO mice (C3 KO) with IRI exhibited attenuated kidney damage and decreased neutrophils and NETs. In vitro, C3a primed neutrophils to form NETs, reflected by amorphous extracellular DNA structures that colocalized with CitH3 and MPO. These data reveal that C3 deficiency can ameliorate AKI by reducing the infiltration of neutrophils and the formation of NETs. Targeting C3 activation may be a new therapeutic strategy for alleviating the necroinflammation of NETs in AKI.

Background. Myocardial ischemia/reperfusion (MI/R) injury is a common pathology in ischemia heart disease. Long noncoding RNAs (lncRNAs) are significant regulators related to many ischemia/reperfusion conditions. This study is aimed at exploring the molecule mechanism of lncRNA-mediated competing endogenous RNA (ceRNA) network in MI/R. Methods. The dataset profiles of MI/R and normal tissues (GSE130217 and GSE124176) were obtained from the GEO database. Integrated bioinformatics were performed to screen out differentially expressed genes (DEGs). Thereafter, an lncRNA-mediated ceRNA network was constructed by the starBase database. The GO annotations and KEGG pathway analysis were conducted to study action mechanism and related pathways of DEGs in MI/R. A model of hypoxia/reoxygenation- (H/R-) treated HL-1 cell was performed to verify the expression of lncRNAs through qRT-PCR. Results. 2406 differentially expressed- (DE-) mRNAs, 70 DE-lncRNAs, and 156 DE-miRNAs were acquired. These DEGs were conducted to construct an lncRNA-mediated ceRNA network, and a subnetwork including lncRNA Xist/miRNA-133c/mRNA (Slc30a9) was screen out. The functional enrichment analyses revealed that the lncRNAs involved in the ceRNA network might functions in oxidative stress and calcium signaling pathway. The lncRNA Xist expression is reduced under H/R conditions, followed by the increased level of miRNA-133c, thus downregulating the expression of Slc30a9. Conclusion. In sum, the identified ceRNA network which included the lncRNA Xist/miR-133c/Slc30a9 axis might contribute a better understanding to the pathogenesis and development of MI/R injury and offer a novel targeted therapy way.

With the availability of easy access to the Internet, and the proliferation of various mobile devices, people can get access to mobile multimedia ubiquitously in order to have a desktop experience. Mobile multimedia refers to different types of multimedia content (e.g., text, images, audios, and videos), which are accessed via heterogeneous mobile devices, such as mobile phones, portable devices, and smartphones. Mobile multimedia services and applications have tremendous potential in the healthcare sector. Currently, as the healthcare sector is increasingly dependent on mobile multimedia services and applications, many challenges remain unsolved for the successful deployment of mobile multimedia services in order to have a balance between power-limited mobile devices and resource hungry medical multimedia content. This Special Section aims to theme innovative research achievements in the field of related techniques, applications, services, and systems for mobile multimedia healthcare.

In this study, the phenomenon of gas removal behaviors in the melt pool and the flow behaviors of melt pool were observed using an in-situ X-ray imaging method. Based on the ultrasonic effects, a novel processing method was developed to reduce porosity and decrease diffusible hydrogen content in the deposited metal. The effects of ultrasonic output power on the size and frequency of gas bubble collapsing were studied. Results showed that with the assistance of ultrasonic, the gas bubble size were smaller and the collapsing frequency was significantly increased. The porosity decreased from 1.4% to 0.5% and the hydrogen diffusible content decreased from 24.5 to 18.6 ml/100 g when the ultrasonic power increased to 720 W. The possible hydrogen removal mechanism was proposed by two aspects including the microcosmic and macrocosmic scale. Keywords: Underwater welding, Ultrasonic melt processing, Solidification, Diffusible hydrogen, In-situ X-ray imaging

The dynamic behavior of the underwater melt pool was firstly in-situ observed with the X-ray transmission method. A method for quantitatively characterizing the melt pool stability was pioneered. Comparing with conventional melt pool composing metal liquid, the pool was filled with bubbles in underwater environment. By observing the X-ray images and charactering the weld pool waveform, it is confirmed that the underwater melt pool was more volatile than onshore melt pool, which was mainly caused by the evolution of large bubble in the pool. Violent fluctuation of melt pool was the basic reason gaining poor weld and multiple defects in the underwater wet welding. To mitigate pool fluctuations by reducing the size of bubble, the ultrasonic vibration was applied directly on the workpiece, which improved the melt pool stability, uniformized the weld formation, and decreased the weld porosity. Keywords: In situ X-ray imaging, Underwater wet welding, Melt pool dynamics, Bubble evolution, Ultrasonic vibration

Multisensory services and technologies play an important role in providing and managing health care services to anyone, anywhere and anytime, seamlessly aiming to build a smart city environment and to improve the quality of life for its citizens. These services and technologies facilitate physicians and other health care professionals to have immediate access to health information for efficient decision making as well as better treatment. Researchers are working to develop various multisensory tools, techniques and services to better support health initiatives to complement the classic scenario with smart cities. In particular, works in health record management, elderly health monitoring, real-time access of medical images and video are of great interest. This Special Section in IEEE A CCESS aims to explore innovative research achievements in the field of related techniques, applications, services and systems for Healthcare in Smart Cities.

Real-time electric signal, matter transfer mode and welding pool behavior were obtained to investigate the effect of wires’ filling rate on arc stability and joints’ appearance during underwater wet flux-cored arc welding (FCAW). The electric signal results showed that arc stability first decreased and then increased rapidly because the raise of filling rate affected the number of charged particles and the electrical conductivity of welding arc atmosphere. Two typical transfer modes, globular repelled transfer mode and surface tension transfer mode, were observed in this study. The ratio of surface tension transition could be increased by adding wires’ filling rate. Meanwhile, the geometry of molten pool was changed and the distance between droplets to welding pool reduced as the filling rate increased. The fusion line became more regular and the radius of curvature increased under the effect of bubbles in the molten pool. As the filling rate improving, more slags on the welds surface were acquired and the welds were much flatter and smoother.

The underwater wet welding (UWW) technology is rapidly developing as a crucial method in the maintenance work of marine equipment and offshore platform. The rapid development of UWW technology has also exposed the problems to be solved urgently. Therefore, the influence of welding parameters on the weld appearance and welding spatters was investigated in this paper. The main welding parameters used in the study are welding current, arc voltage, welding speed and the contact tip-to-work distance (CTWD). Through the orthogonal test, it is found that, as each welding parameter increases within a certain range, the amounts of welding spatter decreases first and then increases, and the weld forming effect first becomes better and then deteriorates. The amount of wet welding spatter is mainly affected by the welding speed. When the welding speed is low, the splash is more, and the change of the welding current and the arc voltage has a little effect on the number of spatters. When the welding speed is large, the spatter is most with a small welding current and a large arc voltage. After evaluating the weld morphology obtained by welding under various parameters, a set of optimal parameters was obtained. The best parameters for the underwater wet welding of stainless steel with self-shielded flux-cored wire are determined to be 200 A-29 V-2.0 mm/s-15 mm (CTWD).

Based on the results from rock thin section observation, casting thin section identification, high-pressure mercury injection, rate-controlled porosimetry, X-ray diffraction, and high resolution field emission CMOS scanning election microscope observation and analysis, influences of feldspar minerals on the storage and permeability conditions in Chang-6 oil layer group in the Yanchang Formation of the Ordos Basin were studied from crystallography and mineralogy perspectives. Due to the differences of crystal structure and chemical composition, the brittleness and solubility of feldspar minerals vary greatly. The results indicate that basic plagioclase such as anorthite tend to split along the cleavage to form new flow channel in formation conditions. Alkaline feldspar rich in potassium such as orthoclase tend to corrode along the cleavage to form secondary porosity. The brittleness and solubility of acid plagioclase, such as albite, are between anorthite and orthoclase. The dominant pore type in Chang-6 oil layer group of Ordos Basin is residual inter-granular pore, the secondary pores generated by corrosion and fracture of feldspar have little contribution to porosity. In the area with higher content of anorthite, the micro-cracks resulted from breaking in cleavage effectively improve the permeability. The contribution of feldspar minerals to permeability is ranked from great to small as anorthite, orthoclase and albite. Key words: Ordos Basin, Chang-6 oil layer group, tight oil, feldspar

We present an integrated framework on personalized sports video customization, which addresses three research issues: semantic video annotation, personalized video retrieval and summarization, and system adaptation. Sports video annotation serves as the foundation of the video customization system. To acquire detailed description of video content, external web text is adopted to align with the related sports video according to their semantic correspondence. Based on the derived semantic annotation, a user-participant multiconstraint 0/1 Knapsack model is designed to model the personalized video customization, which can unify both video retrieval and summarization with different fusion parameters. As a measure to make the system adaptive to the particular user, a social network based system adaptation algorithm is proposed to learn latent user preference implicitly. Both quantitative and qualitative experiments conducted on twelve broadcast basketball and football videos validate the effectiveness of the proposed method.

Background/aims To improve the accuracy of pterygium screening and detection through smartphones, we established a fusion training model by blending a large number of slit-lamp image data with a small proportion of smartphone data. Method Two datasets were used, a slit-lamp image dataset containing 20 987 images and a smartphone-based image dataset containing 1094 images. The RFRC (Faster RCNN based on ResNet101) model for the detection model. The SRU-Net (U-Net based on SE-ResNeXt50) for the segmentation models. The open-cv algorithm measured the width, length and area of pterygium in the cornea. Results The detection model (trained by slit-lamp images) obtained the mean accuracy of 95.24%. The fusion segmentation model (trained by smartphone and slit-lamp images) achieved a microaverage F1 score of 0.8981, sensitivity of 0.8709, specificity of 0.9668 and area under the curve (AUC) of 0.9295. Compared with the same group of patients' smartphone and slit-lamp images, the fusion model performance in smartphone-based images (F1 score of 0.9313, sensitivity of 0.9360, specificity of 0.9613, AUC of 0.9426, accuracy of 92.38%) is close to the model (trained by slit-lamp images) in slit-lamp images (F1 score of 0.9448, sensitivity of 0.9165, specificity of 0.9689, AUC of 0.9569 and accuracy of 94.29%). Conclusion Our fusion model method got high pterygium detection and grading accuracy in insufficient smartphone data, and its performance is comparable to experienced ophthalmologists and works well in different smartphone brands. [ABSTRACT FROM AUTHOR]

To reduce computational redundancies, a common approach is to integrate detection and re-identification (Re-ID) into a single network in multi-object tracking (MOT), referred to as "tracking by detection." Most of the previous research has focused on resolving the conflict between the detection and Re-ID branches, considering it a simple coupling. In our work, we uncover that the entangled state between the detection and Re-ID tasks is much more complex than previous idea, resulting in a form of competition that degrades performance. To address the preceding issue, we propose a feature disentanglement network that deeply disentangles the intricately interwoven latent space of features and provides differentiated feature maps for each individual task. Furthermore, considering the demand for shallow semantic features in the feature re-ID branch, we also introduce a feature re-globalization module to enrich the shallow semantics. By integrating two distinct networks into a one-shot online MOT method, we develop a robust MOT tracker (named HDGTrack). We conduct extensive experiments on a number of benchmarks, and our experimental results demonstrate that our method significantly outperforms state-of-the-art MOT methods. Besides, HDGTrack is efficient and can run at 13.9 (MOT17) and 8.7 (MOT20) frames per second. [ABSTRACT FROM AUTHOR]

Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution--Adversarial Logits Pairing (ALP), we observed in this work that: (1) The inference of adversarially robust model tends to rely on fewer highcontribution features compared with vulnerable ones. (2) The training target of ALP does not fit well to a noticeable part of samples, where the logits pairing loss is overemphasized and obstructs minimizing the classification loss. Motivated by these observations, we design an Adaptive Adversarial Logits Pairing (AALP) solution by modifying the training process and training target of ALP. Specifically, AALP consists of an adaptive feature optimization module with Guided Dropout to systematically pursue fewer high-contribution features, and an adaptive sample weighting module by setting sample-specific training weights to balance between logits pairing loss and classification loss. The proposed AALP solution demonstrates superior defense performance on multiple datasets with extensive experiments. [ABSTRACT FROM AUTHOR]

Earthquakes have a profound impact on social harmony and property, resulting in damage to buildings and infrastructure. Effective earthquake rescue efforts require rapid and accurate determination of whether any survivors are trapped in the rubble of collapsed buildings. While deep learning algorithms can enhance the speed of rescue operations using single-modal data (either visual or audio), they are confronted with two primary challenges: insufficient information provided by single-modal data and catastrophic forgetting. In particular, the complexity of earthquake scenes means that single-modal features may not provide adequate information. Additionally, catastrophic forgetting occurs when the model loses the information learned in a previous task after training on subsequent tasks, due to non-stationary data distributions in changing earthquake scenes. To address these challenges, we propose an innovative approach that utilizes an incremental audio-visual fusion model for person recognition in earthquake rescue scenarios. Firstly, we leverage a cross-modal hybrid attention network to capture discriminative temporal context embedding, which uses self-attention and cross-modal attention mechanisms to combine multi-modality information, enhancing the accuracy and reliability of person recognition. Secondly, an incremental learning model is proposed to overcome catastrophic forgetting, which includes elastic weight consolidation and feature replay modules. Specifically, the elastic weight consolidation module slows down learning on certain weights based on their importance to previously learned tasks. The feature replay module reviews the learned knowledge by reusing the features conserved from the previous task, thus preventing catastrophic forgetting in dynamic environments. To validate the proposed algorithm, we collected the Audio-Visual Earthquake Person Recognition (AVEPR) dataset from earthquake films and real scenes. Furthermore, the proposed method gets 85.41% accuracy while learning the 10th new task, which demonstrates the effectiveness of the proposed method and highlights its potential to significantly improve earthquake rescue efforts. [ABSTRACT FROM AUTHOR]

This work presents Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, that can fit in most existing arbitrary image style transfer models, such as CNN-based, ViT-based, and flow-based methods. As the key component in image style transfer tasks, a suitable style representation is essential to achieve satisfactory results. Existing approaches based on deep neural networks typically use second-order statistics to generate the output. However, these hand-crafted features computed from a single image cannot leverage style information sufficiently, which leads to artifacts such as local distortions and style inconsistency. To address these issues, we learn style representation directly from a large number of images based on contrastive learning by considering the relationships between specific styles and the holistic style distribution. Specifically, we present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components: a parallel contrastive learning scheme for style representation and transfer, a domain enhancement (DE) module for effective learning of style distribution, and a generative network for style transfer. Qualitative and quantitative evaluations show the results of our approach are superior to those obtained via state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Humans can easily infer the motivations behind human actions from only visual data by comprehensively analyzing the complex context information and utilizing abundant life experiences. Inspired by humans’ reasoning ability, existing motivation prediction methods have improved image-based deep classification models using the commonsense knowledge learned by pre-trained language models. However, the knowledge learned from public text corpora is probably incompatible with the task-specific data of the motivation prediction, which may impact the model performance. To address this problem, this paper proposes a dual scene graph convolutional network (dual-SGCN) to comprehensively explore the complex visual information and semantic context prior from the image data for motivation prediction. The proposed dual-SGCN has a visual branch and a semantic branch. For the visual branch, we build a visual graph based on scene graph where object nodes and relation edges are represented by visual features. For the semantic branch, we build a semantic graph where nodes and edges are directly represented by the word embeddings of the object and relation labels. In each branch, node-oriented and edge-oriented message passing is adopted to propagate interaction information between different nodes and edges. Besides, a multi-modal interactive attention mechanism is adopted to cooperatively attend and fuse the visual and semantic information. The proposed dual-SGCN is learned in an end-to-end form by a multi-task co-training scheme. In the inference stage, Total Direct Effect is adopted to alleviate the bias caused by the semantic context prior. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Recently, user cold-start recommendations have attracted a lot of attention from industry and academia. In user cold-start recommendation systems, the user attribute information is often used by existing approaches to learn user preferences due to the unavailability of user action data. However, most existing recommendation methods often ignore the sparsity of user attributes in cold-start recommendation systems. To tackle this limitation, this article proposes a novel Inductive Heterogeneous Graph Neural Network (IHGNN) model, which utilizes the relational information in user cold-start recommendation systems to alleviate the sparsity of user attributes. Our model converts new users, items, and associated multimodal information into a Modalityaware Heterogeneous Graph (M-HG) that preserves the rich and heterogeneous relationship information among them. Specifically, to utilize rich and heterogeneous relational information in an M-HG for enriching the sparse attribute information of new users, we design a strategy based on random walk operations to collect associated neighbors of new users by multiple times sampling operation. Then, a well-designed multiple hierarchical attention aggregationmodel consisting of the intra- and inter-type attention aggregating module is proposed, focusing on useful connected neighbors and neglecting meaningless and noisy connected neighbors to generate high-quality representations for user cold-start recommendations. Experimental results on three real datasets demonstrate that the IHGNN outperforms the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

As a crucial part of natural language processing, event-centered commonsense inference task has attracted increasing attention. With a given observed event, the intention and reaction of the people involved in the event are required to be inferred with artificial intelligent algorithms. To solve this problem, sequence-tosequence methods are widely studied, where the event is first encoded into a specific representation and then decoded to generate the results. However, all the existing methods learn the event representation only with the textual information, while the visual information is ignored, which is actually helpful for the commonsense reference. In this article, we first define a new task of multi-modal commonsense reference with both textual and visual information. A new event-centered multi-modal dataset is also provided. Then we propose a multi-source knowledge reasoning graph network to solve this task, where three kinds of relational knowledge are considered. Multi-modal correlations are learned to get the event's multi-modal representation from a global perspective. Intra-event object relations are explored to capture the fine-grained event feature with an object graph. Inter-event semantic relations are also explored through the external knowledge to understand the semantic associations among events with an event graph. We conduct extensive experiments on the new dataset, and the results show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Metal responsive transcription factor 1 (MTF-1) is a zinc-dependent transcription factor involved in the development of pulmonary arterial hypertension (PAH), which is a life-threatening disease characterized by elevated pulmonary artery pressure and pulmonary vascular remodeling. However, little is known about the role and regulatory signaling of MTF-1 in PAH. This study aimed to investigate the effect and mechanism of MTF-1 on the proliferation of pulmonary arterial smooth muscle cells (PASMCs). Several techniques including intracellular-free zinc detected by fluorescent indicator-fluozinc-3-AM, western blot, luciferase reporter, and cell proliferation assay were conducted to perform a comprehensive analysis of MTF-1 in proliferation of PASMCs in PAH. Increased cytosolic zinc was shown in monocrotaline (MCT)-PASMCs and ZnSO4-treated PASMCs, which led to overexpression and overactivation of MTF-1, followed by the up-regulation of placental growth factor (PlGF). Elevated MTF-1 and PlGF were observed in western blot, and high transcriptional activity of MTF-1 was confirmed by luciferase reporter in ZnSO4-treated cells. Further investigation of cell proliferation revealed a favorable impact of zinc ions on PASMCs proliferation, with the deletion of Mtf-1/Plgf attenuating ZnSO4-induced proliferation. Flow cytometry analysis showed that blockade of PKC signaling inhibited the cell cycle of MCT-PASMCs and ZnSO4-treated PASMCs. The Zinc/PKC/MTF-1/PlGF pathway is involved in the up-regulatory effect on the PASMCs proliferation in the process of PAH. This study provided novel insight into zinc homeostasis in the pathogenesis of PAHs, and the regulation of MTF-1 might be a potential target for therapeutic intervention in PAH. [ABSTRACT FROM AUTHOR]

Image caption editing, which aims at editing the inaccurate descriptions of the images, is an interdisciplinary task of computer vision and natural language processing. As the task requires encoding the image and its corresponding inaccurate caption simultaneously and decoding to generate an accurate image caption, the encoder-decoder framework is widely adopted for image caption editing. However, existing methods mostly focus on the decoder, yet ignore a big challenge on the encoder: the semantic inconsistency between image and caption. To this end, we propose a novel Adaptive Text Denoising Network (ATD-Net) to filter out noises at the word level and improve the model's robustness at sentence level. Specifically, at the word level, we design a cross-attention mechanism called Textual Attention Mechanism (TAM), to differentiate the misdescriptive words. The TAM is designed to encode the inaccurate caption word by word based on the content of both image and caption. At the sentence level, in order to minimize the influence of misdescriptive words on the semantic of an entire caption, we introduce a Bidirectional Encoder to extract the correct semantic representation from the raw caption. The Bidirectional Encoder is able to model the global semantics of the raw caption, which enhances the robustness of the framework. We extensively evaluate our proposals on the MS-COCO image captioning dataset and prove the effectiveness of our method when compared with the state-of-the-arts. [ABSTRACT FROM AUTHOR]

With the rapid development of online recipe sharing platforms, food recommendation is emerging as an important application. Although recent studies have made great progress on food recommendation, they have two shortcomings that are likely to affect the recommendation performance. (1) The relations between ingredients are not considered, which may lead to sub-optimal representations of recipes and further result in the neglect of the user's personalized ingredient combination preference. (2) Existing methods do not consider the impact of users' preferences on calories in users' food decision-making process. In this article, we propose a Self-supervised Calorie-aware Heterogeneous Graph Network (SCHGN) to model the relations between ingredients and incorporate calories of food simultaneously. Specifically, we first incorporate users, recipes, ingredients, and calories into a heterogeneous graph and explicitly present the complex relations among them with directed edges. Then, we explore the co-occurrence relation of ingredients in different recipes via self-supervised ingredient prediction. To capture users' dynamic preferences on calories of food, we learn calorie-aware user representations by hierarchical message passing and compute a comprehensive user-guided recipe representation by attention mechanism. The final food recommendation is accomplished based on the similarity between a user's calorie-aware representation and the user-guided representation of a recipe. Extensive experiment results on benchmark datasets demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The β-1,6-glucan is the key linker between mannoproteins in the outermost part of the cell wall and β-1,3-glucan/chitin polysaccharide to maintain the rigid structure of the cell wall. The β-1,6-glucanase GluM, which was purified from the fermentation supernatant of Corallococcus sp. EGB, was able to inhibit the germination of Fusarium oxysporum f. sp. cucumerinum conidia at a minimum concentration of 2.0 U/mL (0.08 μg/mL). The survival rates of GluM-treated conidia and monohyphae were 10.4% and 30.7%, respectively, which were significantly lower than that of β-1,3-glucanase treatment (Zymolyase, 20.0 U/mL; equate to 1.0 mg/mL) (72.9% and 73.9%). In contrast to β-1,3-glucanase treatment, the high-osmolarity glycerol (HOG) pathway of F. oxysporum f. sp. cucumerinum cells was activated after GluM treatment, and the intracellular glycerol content was increased by 2.6-fold. Moreover, the accumulation of reactive oxygen species (ROS) in F. oxysporum f. sp. cucumerinum cells after GluM treatment induced apoptosis, but it was not associated with the increased intracellular glycerol content. Together, the results indicate that β-1,6-glucan is a promising target for the development of novel broad-spectrum antifungal agents. [ABSTRACT FROM AUTHOR]

Medicine recommendation systems target to recommend a set of medicines given a set of symptoms which play a crucial role in assisting doctors in their daily clinics. Existing approaches are either rule-based or supervised. However, the former heavily relies on expert labeling, which is time-consuming and costly to collect, and the latter suffers from the data sparse problem. To automate medicine recommendation on sparse data, we propose MedRec, which introduces two graphs in modeling: (1) a knowledge graph connecting diseases, medicines, symptoms, and examinations; (2) an attribute graph connecting medicines via shared attributes and molecular structures. These two graphs enhance the connectivity between symptoms and medicines, which thus alleviate the data sparse problem. By learning the interrelationship between diseases, medicines, symptoms and examinations and the inner relationship within medicine, we can acquire unified embedding representations of symptoms and medicines which can be used in medicine recommendation. The experimental results show that the proposed model outperforms state-of-the-art methods. In addition, we find that these two tasks: learning graph representation and medical recommendation can benefit each other. [ABSTRACT FROM AUTHOR]

This article explores the problem of image-based personality questionnaire design. Compared with the traditional text-based personality questionnaire, the image-based personality questionnaire is more natural, truthful, and language insensitive. Instead of responding to textual questions, the subjects are provided a set of "choose-your-favorite-image" visual questions. With each question, consisting of image options describing the same semantic concept, the subjects are requested to choose their favorite image. Based on responses to typically 15 to 25 questions, we can accurately estimate the subjects' personality traits in five dimensions. The solution to design such an image-based personality questionnaire consists of concept-question identification and image-option selection. We have presented a preliminary framework to regularize these two steps in this exploratory study. A demo automatically adapting between desktop and mobile devices is available at http://120.27.209.14/vbfi. Subjective and objective evaluations have demonstrated the feasibility of accurately estimating a subject's personality in a limited round of questions. [ABSTRACT FROM AUTHOR]

Great progress has been achieved in domain adaptation in decades. Existing works are always based on an ideal assumption that testing target domains are independent and identically distributed with training target domains. However, due to unpredictable corruptions (e.g., noise and blur) in real data, such as web images and real-world object detection, domain adaptation methods are increasingly required to be corruption robust on target domains. We investigate a new task, corruption-agnostic robust domain adaptation (CRDA), to be accurate on original data and robust against unavailable-for-training corruptions on target domains. This task is non-trivial due to the large domain discrepancy and unsupervised target domains. We observe that simple combinations of popular methods of domain adaptation and corruption robustness have suboptimal CRDA results. We propose a newapproach based on two technical insights into CRDA, as follows: (1) an easy-to-plug module called domain discrepancy generator (DDG) that generates samples that enlarge domain discrepancy to mimic unpredictable corruptions; (2) a simple but effective teacher-student scheme with contrastive loss to enhance the constraints on target domains. Experiments verify that DDG maintains or even improves its performance on original data and achieves better corruption robustness than baselines. [ABSTRACT FROM AUTHOR]

Domain adaptation aims to generalize a model from a source domain to tackle tasks in a related but different target domain. Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain. However, these algorithms will be infeasible when only a few labeled data exist in the source domain, thus the performance decreases significantly. To address this challenge, we propose a Domain-invariant Graph Learning (DGL) approach for domain adaptation with only a few labeled source samples. Firstly, DGL introduces the Nyström method to construct a plastic graph that shares similar geometric property with the target domain. Then, DGL flexibly employs the Nyström approximation error to measure the divergence between the plastic graph and source graph to formalize the distribution mismatch from the geometric perspective. Through minimizing the approximation error, DGL learns a domain-invariant geometric graph to bridge the source and target domains. Finally, we integrate the learned domain-invariant graph with the semi-supervised learning and further propose an adaptive semi-supervised model to handle the cross-domain problems. The results of extensive experiments on popular datasets verify the superiority of DGL, especially when only a few labeled source samples are available. [ABSTRACT FROM AUTHOR]

The cold-start recommendation is an urgent problem in contemporary online applications. It aims to provide users whose behaviors are literally sparse with as accurate recommendations as possible. Many data-driven algorithms, such as the widely used matrix factorization, underperform because of data sparseness. This work adopts the idea of meta-learning to solve the user's cold-start recommendation problem. We propose a meta-learning-based cold-start sequential recommendation framework called metaCSR, including three main components:Diffusion Representer for learning better user/item embedding through information diffusion on the interaction graph; Sequential Recommender for capturing temporal dependencies of behavior sequences; and Meta Learner for extracting and propagating transferable knowledge of prior users and learning a good initialization for new users. metaCSR holds the ability to learn the common patterns from regular users' behaviors and optimize the initialization so that the model can quickly adapt to new users after one or a few gradient updates to achieve optimal performance. The extensive quantitative experiments on three widely used datasets show the remarkable performance of metaCSR in dealing with the user cold-start problem. Meanwhile, a series of qualitative analysis demonstrates that the proposed metaCSR has good generalization. [ABSTRACT FROM AUTHOR]

Composing Text and Image to Image Retrieval (CTI-IR) is an emerging task in computer vision, which allows retrieving images relevant to a query image with text describing desired modifications to the query image. Most conventional cross-modal retrieval approaches usually take one modality data as the query to retrieve relevant data of another modality. Different from the existing methods, in this article, we propose an endto-end trainable network for simultaneous image generation and CTI-IR. The proposed model is based on Generative Adversarial Network (GAN) and enjoys several merits. First, it can learn a generative and discriminative feature for the query (a query image with text description) by jointly training a generative model and a retrieval model. Second, our model can automatically manipulate the visual features of the reference image in terms of the text description by the adversarial learning between the synthesized image and target image. Third, global-local collaborative discriminators and attention-based generators are exploited, allowing our approach to focus on both the global and local differences between the query image and the target image. As a result, the semantic consistency and fine-grained details of the generated images can be better enhanced in our model. The generated image can also be used to interpret and empower our retrieval model. Quantitative and qualitative evaluations on three benchmark datasets demonstrate that the proposed algorithm performs favorably against state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The explosive growth of video data has brought great challenges to video retrieval, which aims to find out related videos from a video collection. Most users are usually not interested in all the content of retrieved videos but have a more fine-grained need. In the meantime, most existing methods can only return a ranked list of retrieved videos lacking a proper way to present the video content. In this paper, we introduce a distinctively new task, namely One-Stop Video Delivery (OSVD) aiming to realize a comprehensive retrieval system with the following merits: it not only retrieves the relevant videos but also filters out irrelevant information and presents compact video content to users, given a natural language query and video collection. To solve this task, we propose an end-to-end Hierarchical Video Graph Reasoning framework (HVGR), which considers relations of different video levels and jointly accomplishes the one-stop delivery task. Specifically, we decompose the video into three levels, namely the video-level, moment-level, and the clip-level in a coarse-to-fine manner, and apply Graph Neural Networks (GNNs) on the hierarchical graph to model the relations. Furthermore, a pairwise ranking loss named Progressively Refined Loss is proposed based on prior knowledge that there is a relative order of the similarity of query-video, query-moment, and query-clip due to the different granularity of matched information. Extensive experimental results on benchmark datasets demonstrate that the proposed method achieves superior performance compared with baseline methods. [ABSTRACT FROM AUTHOR]

Health management is getting increasing attention all over the world. However, existing health management mainly relies on hospital examination and treatment, which are complicated and untimely. The emergence of mobile devices provides the possibility to manage people's health status in a convenient and instant way. Estimation of health status can be achieved with various kinds of data streams continuously collected from wearable sensors. However, these data streams are multi-source and heterogeneous, containing complex temporal structures with local contextual and global temporal aspects, which makes the feature learning and data joint utilization challenging. We propose to model the behavior-related multi-source data streams with a local-global graph, which contains multiple local context sub-graphs to learn short-term local context information with heterogeneous graph neural networks and a global temporal sub-graph to learn long-term dependency with self-attention networks. Then health status is predicted based on the structure-aware representation learned from the local-global behavior graph. We take experiments on the StudentLife dataset, and extensive results demonstrate the effectiveness of our proposed model. [ABSTRACT FROM AUTHOR]

Multimodal and multi-domain stylization are two important problems in the field of image style transfer. Currently, there are few methods that can perform multimodal and multi-domain stylization simultaneously. In this study, we propose a unified framework for multimodal and multi-domain style transfer with the support of both exemplar-based reference and randomly sampled guidance. The key component of our method is a novel style distribution alignment module that eliminates the explicit distribution gaps between various style domains and reduces the risk of mode collapse. The multimodal diversity is ensured by either guidance from multiple images or random style codes, while the multi-domain controllability is directly achieved by using a domain label. We validate our proposed framework on painting style transfer with various artistic styles and genres. Qualitative and quantitative comparisons with state-of-the-art methods demonstrate that our method can generate high-quality results of multi-domain styles and multimodal instances from reference style guidance or a random sampled style. [ABSTRACT FROM AUTHOR]

Over the past few years, graph representation learning (GRL) has received widespread attention on the feature representations of the non-Euclidean data. As a typical model of GRL, graph convolutional networks (GCN) fuse the graph Laplacian-based static sample structural information. GCN thus generalizes convolutional neural networks to acquire the sample representations with the variously high-order structures. However, most of existing GCN-based variants depend on the static data structural relationships. It will result in the extracted data features lacking of representativeness during the convolution process. To solve this problem, dynamic graph learning convolutional networks (DGLCN) on the application of semi-supervised classification are proposed. First, we introduce a definition of dynamic spectral graph convolution operation. It constantly optimizes the high-order structural relationships between data points according to the loss values of the loss function, and then fits the local geometry information of data exactly. After optimizing our proposed definition with the one-order Chebyshev polynomial, we can obtain a single-layer convolution rule of DGLCN. Due to the fusion of the optimized structural information in the learning process, multi-layer DGLCN can extract richer sample features to improve classification performance. Substantial experiments are conducted on citation network datasets to prove the effectiveness of DGLCN. Experiment results demonstrate that the proposed DGLCN obtains a superior classification performance compared to several existing semi-supervised classification models. [ABSTRACT FROM AUTHOR]

Generalizing the electroencephalogram (EEG) decoding methods to unseen subjects is an important research direction for realizing practical application of brain-computer interfaces (BCIs). Since distribution shifts across subjects, the performance of most current deep neural networks for decoding EEG signals degrades when dealing with unseen subjects. Domain generalization (DG) aims to tackle this issue by learning invariant representations across subjects. To this end, we propose a novel domain-generalized EEG classification framework, named FDCL, to generalize EEG decoding through category-relevant and -irrelevant Feature Decorrelation and Cross-view invariant feature Learning. Specifically, we first devise data augmented regularization through mixing the segments of same-category features from multiple subjects, which increases the diversity of EEG data by spanning the space of subjects. Furthermore, we introduce feature decorrelation regularization to learn the weights of the augmented EEG trials to remove the dependencies between their features, so that the true mapping relationship between relevant features and corresponding labels can be better established. To further distill subject-invariant EEG feature representations, cross-view consistency learning regularization is introduced to encourage consistent predictions of category-relevant features induced from different augmented EEG views. We seamlessly integrate three complementary regularizations into a unified DG framework to jointly improve the generalizability and robustness of the model on unseen subjects. Experimental results on motor imagery (MI) based EEG datasets validate that the proposed FDCL outperforms the available state-of-the-art methods.

Person re-identification aims to match person of interest under non-overlapping camera views. Therefore, how to generate a robust and discriminative representation is crucial for person re-identification. Mining local clues from human body parts to describe pedestrians has been extensively studied in existing methods. However, existing methods locate human body parts coarsely and do not consider the relations among different local parts. To address the above problem, we propose a Part-based Structured Representation Learning (PSRL) for better exploiting local clues to improve the person representation. There are two important modules in our architecture: Local Semantic Feature Extraction and Structured Person Representation Learning. The Local Semantic Feature Extraction module is designed to extract local features from human body semantic regions. After obtaining the local features, the Structured Person Representation Learning is proposed to fuse the local features by considering the person structure. To model the underlying person structure, a graph convolutional network is employed to capture the relations of different semantic regions. The generated structured feature encodes underlying person structure information, and local semantic feature can solve the misalignment problem caused by pose variations in feature matching. By combining them together, we can improve the descriptive ability of the generated representation. Extensive evaluations on four standard benchmarks show that our proposed method achieves competitive performance against state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recognizing activities from egocentric multimodal data collected by wearable cameras and sensors, is gaining interest, as multimodal methods always benefit from the complementarity of different modalities. However, since high-dimensional videos contain rich high-level semantic information while low-dimensional sensor signals describe simple motion patterns of the wearer, the large modality gap between the videos and the sensor signals raises a challenge for fusing the raw data. Moreover, the lack of large-scale egocentric multimodal datasets due to the cost of data collection and annotation processes makes another challenge for employing complex deep learning models. To jointly deal with the above two challenges, we propose a knowledge-driven multimodal activity recognition framework that exploits external knowledge to fuse multimodal data and reduce the dependence on large-scale training samples. Specifically, we design a dual-GCLSTM (Graph Convolutional LSTM) and a multi-layer GCN (Graph Convolutional Network) to collectively model the relations among activities and intermediate objects. The dual-GCLSTM is designed to fuse temporal multimodal features with top-down relation-aware guidance. In addition, we apply a co-attention mechanism to adaptively attend to the features of different modalities at different timesteps. The multi-layer GCN aims to learn relation-aware classifiers of activity categories. Experimental results on three publicly available egocentric multimodal datasets show the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

It is critical to comprehensively and efficiently learn user preferences for an effective sequential recommender system. Existing sequential recommendation methods mainly focus on modeling local preference from users' historical behaviors, which largely ignore the global context information from the heterogeneous information network. This prevents a comprehensive user preference representation. To address these issues, we propose a joint learning approach to incorporate global context with local preferences efficiently. The proposed approach introduces meta-paths from a heterogeneous information network to capture the global context information, and the position-based self-attention mechanism is adopted to model the local preference representation efficiently. Compared with the methods that only consider the local preference, our proposed method takes the advantages of incorporating global context information, which extracts structural features that captures relevant semantics to construct users' global preference representation for the sequential recommendation. We further adopt a co-attention mechanism to model complex interactions between global context and users' historical behaviors for better user representations. Quantitative and qualitative experimental evaluations are conducted on nine large-scale Amazon datasets and a multi-modal Zhihu dataset. The promising results demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]