Complementary Network Research Articles

Complementary spatial transformer network for real-time 3D object recognition

Complementary spatial transformer network for real-time 3D object recognition

Autistic Symptoms, Irritability, and Executive Dysfunctions: Symptom Dynamics from Multi-Network Models.

Socio-cognitive difficulties in individuals with autism spectrum disorder (ASD) are heterogenuous and often co-occur with irritability symptoms, such as angry/grouchy mood and temper outbursts. However, the specific relations between individual symptoms are not well-represented in conventional methods analyzing aggregated autistic symptoms and ASD diagnosis. Moreover, the cognitive-behavioral mechanisms linking ASD to irritability are largely unknown. This study investigated the dynamics between autistic (Social Responsiveness Scale) and irritability (Affective Reactivity Index) symptoms and executive functions (Cambridge Neuropsychological Test Automated Battery) in a sample of children and adolescents with ASD, their unaffected siblings, and neurotypical peers (N = 345, aged 6-18years, 78.6% male). Three complementary networks across the entire sample were computed: (1) Gaussian graphical network estimating the conditional correlations between symptom nodes; (2) Relative importance network computing relative influence between symptoms; (3) Bayesian directed acyclic graph estimating predictive directionality between symptoms. Networks revealed numerous partial correlations within autistic (rs = .07-.56) and irritability (rs = .01-.45) symptoms and executive functions (rs = -.83 to .67) but weak connections between clusters. This segregated pattern converged in all directed and supplementary networks. Plausible predictive paths were found between social communication difficulties to autism mannerisms and between "angry frequently" to "lose temper easily." Autistic and irritability symptoms are two relatively independent families of symptoms. It is unlikely that executive dysfunctions explain elevated irritability in ASD. Findings underscore the need for researching other mood and cognitive-behavioral bridge symptoms, which may inform individualized treatments for co-occurring irritability in ASD.

Edge Computing With Complementary Capsule Networks for Mental State Detection in Underground Mining Industry

Most safety accidents are caused by human factor in underground resource mining industry. This is because the non-uniform lighted and noisy and dangerous environment easily evokes the negative mental state and results in nonstandard production operation. This paper proposes an edge computing mental state framework of the internet of things in the underground mining industry. Moreover, a filtering algorithm using a defined threshold function is developed. Furthermore, a complemented capsule network model is constructed by using two residual modules. In addition, a two-stage mental state fusion algorithm is proposed with EEG signals and facial expression. At last, the mental state variation characteristics are explored with the illuminating and coloring. Experiments show that the mental state detection accuracy is increased by 2.6%. The higher mental arousal is at the illumination between 320 Lx and 330 Lx.

Forgery Detection by Weighted Complementarity between Significant Invariance and Detail Enhancement

Generative adversarial networks have shown impressive results in the modeling of movies and games, but what if such powerful image generation capability is used to harm the Multimedia? The face replacement methods represented by Deepfakes are becoming a threat to everyone, so the development of image authenticity detection methods has become a top priority. For achieving accurate detection resistant to compression effects, we propose a weighted complementary dual-stream detection method. Firstly, to alleviate the influence of image compression on manipulation detection, we propose the concept of pixel-wise saliency invariance. We map fake images onto saliency maps via Quaternary Fourier Transform, which discovers the invariant properties of image phase spectra on different compressions. Meanwhile, to capture boundary traces more easily, we propose the concept of pixel-wise detail enhancement. We apply Bilateral Filtering to preserve the texture edges of fake images and amplify the fake boundaries. Finally, to take full advantage of the two proposed concepts, a weighted complementary dual-stream network (WCD Network) is designed as a classifier to fuse features and identify real and fake. On different benchmarks like FaceForensics++(FF++), Celeb-DF and DFDC, the experimental results show that the proposed method has the average best detection accuracy compared to existing methods.

SiamCAF: Complementary Attention Fusion-Based Siamese Network for RGBT Tracking

The tracking community is increasingly focused on RGBT tracking, which leverages the complementary strengths of corresponding visible light and thermal infrared images. The most well-known RGBT trackers, however, are unable to balance performance and speed at the same time for UAV tracking. In this paper, an innovative RGBT Siamese tracker named SiamCAF is proposed, which utilizes multi-modal features with a beyond-real-time running speed. Specifically, we used a dual-modal Siamese subnetwork to extract features. In addition, to extract similar features and reduce the modality differences for fusing features efficiently, we designed the Complementary Coupling Feature fusion module (CCF). Simultaneously, the Residual Channel Attention Enhanced module (RCAE) was designed to enhance the extracted features and representational power. Furthermore, the Maximum Fusion Prediction module (MFP) was constructed to boost performance in the response map fusion stage. Finally, comprehensive experiments on three real RGBT tracking datasets and one visible–thermal UAV tracking dataset showed that SiamCAF outperforms other tracking methods, with a remarkable tracking speed of over 105 frames per second.

Dual-task complementary networks for single-image deraining

Dual-task complementary networks for single-image deraining

Complimentary electrostatics dominate T-cell receptor binding to a psoriasis-associated peptide antigen presented by human leukocyte antigen C∗06:02

Psoriasis is a chronic skin disease characterized by hyperproliferative epidermal lesions infiltrated by autoreactive T cells. Individuals expressing the human leukocyte antigen (HLA) C∗06:02 allele are at highest risk for developing psoriasis. An autoreactive T cell clone (termed Vα3S1/Vβ13S1) isolated from psoriatic plaques is selective for HLA-C∗06:02, presenting a peptide derived from the melanocyte-specific autoantigen ADAMTSL5 (VRSRRCLRL). Here we determine the crystal structure of this psoriatic TCR-HLA-C∗06:02 ADAMTSL5 complex with a stabilized peptide. Docking of the TCR involves an extensive complementary charge network formed between negatively charged TCR residues interleaving with exposed arginine residues from the self-peptide and the HLA-C∗06:02 α1 helix. We probed these interactions through mutagenesis and activation assays. The charged interface spans the polymorphic region of the C1/C2 HLA group. Notably the peptide-binding groove of HLA-C∗06:02 appears exquisitely suited for presenting highly charged Arg-rich epitopes recognized by this acidic psoriatic TCR. Overall, we provide a structural basis for understanding the engagement of melanocyte antigen-presenting cells by a TCR implicated in psoriasis while simultaneously expanding our knowledge of how TCRs engage HLA-C.

Two-stage learning-based prediction of bronchopulmonary dysplasia in very low birth weight infants: a nationwide cohort study.

The aim of this study is to develop an enhanced machine learning-based prediction models for bronchopulmonary dysplasia (BPD) and its severity through a two-stage approach integrated with the duration of respiratory support (RSd) using prenatal and early postnatal variables from a nationwide very low birth weight (VLBW) infant cohort. We included 16,384 VLBW infants admitted to the neonatal intensive care unit (NICU) of the Korean Neonatal Network (KNN), a nationwide VLBW infant registry (2013-2020). Overall, 45 prenatal and early perinatal clinical variables were selected. A multilayer perceptron (MLP)-based network analysis, which was recently introduced to predict diseases in preterm infants, was used for modeling and a stepwise approach. Additionally, we applied a complementary MLP network and established new BPD prediction models (PMbpd). The performances of the models were compared using the area under the receiver operating characteristic curve (AUROC) values. The Shapley method was used to determine the contribution of each variable. We included 11,177 VLBW infants (3,724 without BPD (BPD 0), 3,383 with mild BPD (BPD 1), 1,375 with moderate BPD (BPD 2), and 2,695 with severe BPD (BPD 3) cases). Compared to conventional machine learning (ML) models, our PMbpd and two-stage PMbpd with RSd (TS-PMbpd) model outperformed both binary (0 vs. 1,2,3; 0,1 vs. 2,3; 0,1,2 vs. 3) and each severity (0 vs. 1 vs. 2 vs. 3) prediction (AUROC = 0.895 and 0.897, 0.824 and 0.825, 0.828 and 0.823, 0.783, and 0.786, respectively). GA, birth weight, and patent ductus arteriosus (PDA) treatment were significant variables for the occurrence of BPD. Birth weight, low blood pressure, and intraventricular hemorrhage were significant for BPD ≥2, birth weight, low blood pressure, and PDA ligation for BPD ≥3. GA, birth weight, and pulmonary hypertension were the principal variables that predicted BPD severity in VLBW infants. We developed a new two-stage ML model reflecting crucial BPD indicators (RSd) and found significant clinical variables for the early prediction of BPD and its severity with high predictive accuracy. Our model can be used as an adjunctive predictive model in the practical NICU field.

Cooperative behavior in blockchain-based complementary currency networks through time: The Sarafu case study

The effort to reach the 17 Sustainable Development Goals by the United Nations has incentivized the adoption of IT solutions in many fields. Many systems for sustainable economic development are now relying on a digital form making them more accessible and provides the access to new functionalities. A very interesting example of such systems are complementary currencies i.e. cooperative currency systems that support national economies to provide humanitarian aid and promote sustainable development. While there are many studies on the principles and case studies of successful complementary currencies, many aspects are still unexplored, especially regarding cooperative behavior. Cooperative behavior in these systems is a key aspect, as complementary currencies are often born out of cooperation among members that face a period of crisis or they usually have the objective of creating bonds of reciprocity and integrating social networks between people, which should lead to increased cooperation. However, there is a lack of studies on many aspects of cooperative behavior in complementary currencies, such as how such behavior changes over time, especially in times of a crisis like the COVID-19 pandemic. Moreover how cooperation behavior is affected by time and different geographical locations is still unclear. In this work, we analyze Sarafu, a complementary currency that went digital and now relies on blockchain technology. Sarafu is a successful case of a complementary currency that was used for humanitarian aid during the COVID-19 pandemic. Moreover, Sarafu is a perfect case study for the study of cooperative behavior, as it implements a special type of account, the group account, to support cooperation groups. This feature supports the study of group dynamics and behavior. What we find is that Sarafu users exhibit strong reliance on cooperation groups; we also observe that the interaction of users and cooperation groups is influenced by both time and geographical location. The study of group accounts and in general mechanisms that promote cooperation can be useful for other humanitarian or community development projects. Moreover, similar cooperation enhancers could have an important role in other social development projects, and in general, in any setting where there is a strong need to foster cooperation for reaching social good.

Viewport-Sphere-Branch Network for Blind Quality Assessment of Stitched 360° Omnidirectional Images

Compared with conventional images/videos, omni-directional data records rich information with higher resolution and wider Field-of-View. Moreover, the stitching distortions introduced in the panoramic content generation process make the quality assessment task more challenging. Targeting at designing an accurate and fast stitched 360° omnidirectional image quality evaluator, we propose a Viewport-Sphere-Branch Network (VSBNet) via dual-branch quality estimation. Specifically, for the viewport quality estimation, we extract distorted viewports around the stitching seams and conduct distortion rectification through a progressively complementary network to obtain pseudo-reference viewports. The qualitative and quantitative experiments validate that pseudo-reference viewports are reliable. Then, the differences between distorted and pseudo-reference viewports are quantified through transformer architecture to obtain quality scores of viewports. The introduction of pseudo-reference viewports can effectively improve the performance of the viewport quality prediction branch. To establish general scenario awareness and accurately evaluate the immersive experience, we extract feature representation through deformable convolutions to eliminate 2D-to-Sphere intrinsic sampling distortions and use multilayer perceptron to predict score of the whole sphere. The final prediction score is obtained by aggregating the quality scores from viewport and sphere branches. We evaluate the proposed VSBNet on two benchmark databases and results demonstrate that the combination of two branches can obtain more accurate results. Overall, our method is superior to existing full reference and no reference models designed for conventional images and 360° omnidirectional images.

Single image super-resolution by cascading parallel-structure units through a deep-shallow CNN

Nowadays, single image super-resolution based on deep learning algorithms is reaching state-of-the-art performance. Nevertheless, most frameworks suffer from needing huge sample set and powerful computing hardware for training. Therefore, this paper presents Cascading Parallel-structure units through a Deep-Shallow (CPDS) CNN which provides satisfactory results not only with small sample set but also low computational cost with the goal of fully using the network design capabilities. In the proposed deep-shallow CNN, an approximated image is reconstructed via the lightweight shallow network, and the missing high-frequency details are retrieved by its complementary deep network. Regarding this, deep CNN is designed based on cascading parallel-structure units in the whole parts of the model to reduce the depth of the model and the number of network parameters. Besides, in the proposed cascading strategy, feature disappearance is restricted by concatenating and fusing features. Based on the parallel-structure of deep CNN, the initial features are firstly extracted using two parallel feature extractor units. Moreover, deep CNN applies a multi-scale fashion to detect and extract coarse-to-fine features simultaneously. Finally, the strategy of combining upsampling methods of deconvolution layer and pixelshuffle is adopted to ensure the high-resolution image reconstruction is accurately validated. Experimental results demonstrate the proposed end-to-end approach outperforms most state-of-the-art methods in terms of training specifications, evaluation metrics, and visual performance.

Segmentation of retinal detachment and retinoschisis in OCT images based on complementary multi-class segmentation networks

Retinal detachment (RD) and retinoschisis (RS) are the main complications leading to vision loss in high myopia. Accurate segmentation of RD and RS, including its subcategories (outer, middle, and inner retinoschisis) in optical coherence tomography images is of great clinical significance in the diagnosis and management of high myopia. For this multi-class segmentation task, we propose a novel framework named complementary multi-class segmentation networks. Based on domain knowledge, a three-class segmentation path (TSP) and a five-class segmentation path (FSP) are designed, and their outputs are integrated through additional decision fusion layers to achieve improved segmentation in a complementary manner. In TSP, a cross-fusion global feature module is adopted to achieve global receptive field. In FSP, a novel three-dimensional contextual information perception module is proposed to capture long-range contexts, and a classification branch is designed to provide useful features for segmentation. A new category loss is also proposed in FSP to help better identify the lesion categories. Experiment results show that the proposed method achieves superior performance for joint segmentation of RD and the three subcategories of RS, with an average Dice coefficient of 84.83%.

Degradation-controlling mechanisms in natural organic acid solutions of CaO–Al2O3–SiO2–B2O3 glass-ceramics by partially substituting Ca2+ with Ba2+ and Sr2+

The degradation of environmentally friendly CaO–Al2O3–SiO2–B2O3 (CASB) glass-ceramics, which consist of anorthite and glass phase, was investigated in three natural organic acid solutions. The results indicated that citric acid had the most significant effect on the degradation of CASB glass-ceramics. While the chemical stability of anorthite is relatively poor, the glass phase also contributed significantly to the effective degradation of CASB glass-ceramics. Subsequently, Ba2+ or Sr2+ was used for full or partial substitution of Ca2+ in CASB glass-ceramics, and the degradation-controlling mechanism of the substituted CASB glass-ceramics was further researched. The full substitution of Ca2+ in CASB glass-ceramics by the two cations resulted in the occurrence of borate [BO4] units in the glass phases, and the interlinkage of [BO4] with broken silicate [SiO4] network structures caused a complementary network effect. Consequently, the degradation of CASB glass-ceramics by organic acids was reduced due to the improvements in the chemical stability of the modified glass-ceramics. Additionally, degradation control can also be achieved based on a mixed-alkali effect, originating from the partial substitution of Ca2+ in CASB glass-ceramics by Ba2+ or Sr2+. The degradable glass-ceramics have the potential to be applied in low-temperature co-fired ceramic technology because of their good physical properties, which include a dielectric constant of 3–5, a dielectric loss as low as 10−3, a coefficient of thermal expansion of 3–9 × 10−6/°C, and an average bending strength of about 47 MPa. Noticeably, the development of the degradable glass-ceramics is helpful to the low-cost and pollution-free recycling of valuable metal electrodes, which is significant for the sustainable development of electronic packaging technologies.

Genetic risk shared across 24 chronic pain conditions: identification and characterization with genomic structural equation modeling.

Chronic pain conditions frequently co-occur, suggesting common risks and paths to prevention and treatment. Previous studies have reported genetic correlations among specific groups of pain conditions and reported genetic risk for within-individual multisite pain counts (≤7). Here, we identified genetic risk for multiple distinct pain disorders across individuals using 24 chronic pain conditions and genomic structural equation modeling (Genomic SEM). First, we ran individual genome-wide association studies (GWASs) on all 24 conditions in the UK Biobank ( N ≤ 436,000) and estimated their pairwise genetic correlations. Then we used these correlations to model their genetic factor structure in Genomic SEM, using both hypothesis- and data-driven exploratory approaches. A complementary network analysis enabled us to visualize these genetic relationships in an unstructured manner. Genomic SEM analysis revealed a general factor explaining most of the shared genetic variance across all pain conditions and a second, more specific factor explaining genetic covariance across musculoskeletal pain conditions. Network analysis revealed a large cluster of conditions and identified arthropathic, back, and neck pain as potential hubs for cross-condition chronic pain. Additionally, we ran GWASs on both factors extracted in Genomic SEM and annotated them functionally. Annotation identified pathways associated with organogenesis, metabolism, transcription, and DNA repair, with overrepresentation of strongly associated genes exclusively in brain tissues. Cross-reference with previous GWASs showed genetic overlap with cognition, mood, and brain structure. These results identify common genetic risks and suggest neurobiological and psychosocial mechanisms that should be targeted to prevent and treat cross-condition chronic pain.

A complementary and contrastive network for stimulus segmentation and generalization

SummaryExisting convolutional neural networks (CNNs) have achieved remarkable performance in medical image segmentation tasks. However, they still fail to generalize well to unseen datasets due to the limited size and diversity of training data as well as distribution shifts. Meanwhile, CNN-based methods have inherent limitations in capturing global contexts and suffer semantic dilution issues in the decoder stage, which leads to suboptimal predictions especially under low inter-class discrepancy and complex backgrounds. In this paper, we propose a novel framework named CCNet that learns complementary and contrastive features for accurate segmentation. Firstly, a novel complementary feature extraction module is formulated to learn global–local features by coordinating Transformer and CNN-style parallel branches. Secondly, a global context refinement module is constructed to adaptively generate a set of layer-specific global maps, so as to remedy semantic dilution. Thirdly, a mutual attentive module is designed to alleviate background confusion, in which contrastive cues are mutually captured from the foreground and background view by cascaded dual attention blocks. Moreover, we implement synthetic data augmentation to deal with training data scarcity and distribution shifts, thereby improving the out-of-distribution generalization of our model. Extensive experiments demonstrate that our CCNet achieves outstanding performance in polyp, skin lesion, and nuclei segmentation tasks, outperforming the state-of-the-arts.

Multilayer Network Community Detection: A Novel Multi-Objective Evolutionary Algorithm Based on Consensus Prior Information [Feature

In recent years, multilayer networks have served as effective models for addressing and analyzing real-world systems with multiple relationships. Among these scenarios, the community detection (CD) problem is one of the most prominent research hotspots. Although some research on multilayer network CD (MCD) has been proposed to address this problem, most studies focus only on topological structures. Therefore, their algorithms cannot extract the most out of complementary network information, such as node similarities and low-rank features, which may lead to unsatisfactory accuracy. To tackle this problem, this paper proposes a novel multi-objective evolutionary algorithm based on consensus prior information (MOEA-CPI). The proposed algorithm takes full advantage of prior information to guide the MOEA with respect to topological structures, initializations, and the optimization process. More specifically, this paper first extracts two kinds of prior information, i.e., graph-level and node-level information, based on Node2vec and Jaccard similarity, respectively. Then, the prior layer and a high-quality initial population are constructed on the basis of the graph-level information. During the optimization process, the genetic operator, which integrates the weighting strategy and node-level information, is applied to guide the algorithm to distribute similar nodes into the same community. Extensive experiments are implemented to prove the superior performance of MOEA-CPI over the state-of-the-art methods.

Network topology of interlocked chiral particles.

Self-assembly of chiral particles with an L-shape is explored by Monte-Carlo computer simulations in two spatial dimensions. For sufficiently high packing densities in confinement, a carpet-like texture emerges due to the interlocking of L-shaped particles, resembling a distorted smectic liquid crystalline layer pattern. From the positions of either of the two axes of the particles, two different types of layers can be extracted, which form distinct but complementary entangled networks. These coarse-grained network structures are then analyzed from a topological point of view. We propose a global charge conservation law by using an analogy to uniaxial smectics and show that the individual network topology can be steered by both confinement and particle geometry. Our topological analysis provides a general classification framework for applications to other intertwined dual networks.

Complementary networks for person re-identification

Recently, person re-identification (re-ID) has gained much attention for its extensive applications in public security. In order to mine more detailed information, some researches have attempted to extract local representations from important regions through human semantic parsing. However, some valuable visual cues beyond human body, such as backpacks and handbags, which can provide complementary information for recognition, may be misclassified as background noise. In addition, when meeting low-quality captured images or severe occlusions, the semantic regions generated by parsing model are not accurate enough, even resulting in disturbance. In this paper, we present complementary networks for person re-ID, which aims to extract more discriminative and robust local representations with complementary clues. Our model contains two branches and one of which aims to mine potential discriminative information in the background that is useful for identifying a person, as a complement for foreground semantics of human body parts. Another branch is designed to capture the salient regions in global scope so as to make up for the problem of poor discrimination of representations caused by the inaccurate semantic confidence maps of former branch. Experiments show that our model achieves competitive performance in many cases.

Geometric and topological properties of the complementary prism networks

The complementary prism of , denoted by , is the graph obtained from the disjoint union of and by adding edges between the corresponding vertices of and . In this paper, we study the hyperbolicity constant of . In particular, we obtain upper and lower bounds for the hyperbolicity constant, and we compute its precise value for many graphs. Moreover, we obtain bounds and closed formulas for the general topological indices and (where denotes the degree of the vertex is a symmetric function with real values, and is a function with real values), and the generalized Wiener index , of complementary prisms networks. Finally, we performed a numerical study of the generalized Wiener index on random graphs.

Complementary Attention Network for Weakly Supervised Temporal Action Localization

Complementary Attention Network for Weakly Supervised Temporal Action Localization