Unified Objective Research Articles

A Closer Look at the Joint Training of Object Detection and Re-identification in Multi-Object Tracking.

Unifying object detection and re-identification (ReID) into a single network enables faster multi-object tracking (MOT), while this multi-task setting poses challenges for training. In this work, we dissect the joint training of detection and ReID from two dimensions: label assignment and loss function. We find previous works generally overlook them and directly borrow the practices from object detection, inevitably causing inferior performance. Specifically, we identify a qualified label assignment for MOT should: 1) have the assignment cost aware of ReID cost, not just detection cost; 2) provide sufficient positive samples for robust feature learning while avoiding ambiguous positives (i.e., the positives shared by different ground-truth objects). To achieve the above goals, we first propose Identity-aware Label Assignment, which jointly considers the assignment cost of detection and ReID to select positive samples for each instance without ambiguities. Moreover, we advance a novel Discriminative Focal Loss that integrates ReID predictions with Focal Loss to focus the training on the discriminative samples. Finally, we upgrade the strong baseline FairMOT with our techniques and achieve up to 7.0 MOTA / 54.1% IDs improvements on MOT16/17/20 benchmarks under favorable inference speed, which verifies our tailored label assignment and loss function for MOT are superior to those inherited from object detection.

Neural and computational evidence that category-selective visual regions are facets of a unified object space

Neural and computational evidence that category-selective visual regions are facets of a unified object space

Seeking commonness and inconsistencies: A jointly smoothed approach to multi-view subspace clustering

Multi-view subspace clustering aims to discover the hidden subspace structures from multiple views for robust clustering, and has been attracting considerable attention in recent years. Despite significant progress, most of the previous multi-view subspace clustering algorithms are still faced with two limitations. First, they usually focus on the consistency (or commonness) of multiple views, yet often lack the ability to capture the cross-view inconsistencies in subspace representations. Second, many of them overlook the local structures of multiple views and cannot jointly leverage multiple local structures to enhance the subspace representation learning. To address these two limitations, in this paper, we propose a jointly smoothed multi-view subspace clustering (JSMC) approach. Specifically, we simultaneously incorporate the cross-view commonness and inconsistencies into the subspace representation learning. The view-consensus grouping effect is presented to jointly exploit the local structures of multiple views to regularize the view-commonness representation, which is further associated with the low-rank constraint via the nuclear norm to strengthen its cluster structure. Thus the cross-view commonness and inconsistencies, the view-consensus grouping effect, and the low-rank representation are seamlessly incorporated into a unified objective function, upon which an alternating optimization algorithm is performed to achieve a robust subspace representation for clustering. Experimental results on a variety of real-world multi-view datasets confirm the superiority of our approach. Code available: .

Tissue Specificity Based Isoform Function Prediction.

Alternative splicing enables a gene spliced into different isoforms and hence protein variants. Identifying individual functions of these isoforms help deciphering the functional diversity of proteins. Although much efforts have been made for automatic gene function prediction, few efforts have been moved toward computational isoform function prediction, mainly due to the unavailable (or scanty) functional annotations of isoforms. Existing efforts directly combine multiple RNA-seq datasets without account of the important tissue specificity of alternative splicing. To bridge this gap, we introduce a novel approach called TS-Isofun to predict the functions of isoforms by integrating multiple functional association networks with respect to tissue specificity. TS-Isofun first constructs tissue-specific isoform functional association networks using multiple RNA-seq datasets from tissue-wise. Next, TS-Isofun assigns weights to these networks and models the tissue specificity by selectively integrating them with adaptive weights. It then introduces a joint matrix factorization-based data fusion model to leverage the integrated network, gene-level data and functional annotations of genes to infer the functions of isoforms. To achieve coherent weight assignment and isoform function prediction, TS-Isofun jointly optimizes the weights of individual networks and the isoform function prediction in a unified objective function. Experimental results show that TS-Isofun significantly outperforms state-of-the-art methods and the account of tissue specificity contributes to more accurate isoform function prediction.

US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexes.

Structure comparison and alignment are of fundamental importance in structural biology studies. We developed the first universal platform, US-align, to uniformly align monomer and complex structures of different macromolecules-proteins, RNAs and DNAs. The pipeline is built on a uniform TM-score objective function coupled with a heuristic alignment searching algorithm. Large-scale benchmarks demonstrated consistent advantages of US-align over state-of-the-art methods in pairwise and multiple structure alignments of different molecules. Detailed analyses showed that the main advantage of US-align lies in the extensive optimization of the unified objective function powered by efficient heuristic search iterations, which substantially improve the accuracy and speed of the structural alignment process. Meanwhile, the universal protocol fusing different molecular and structural types helps facilitate the heterogeneous oligomer structure comparison and template-based protein-protein and protein-RNA/DNA docking.

Complementary Segmentation of Primary Video Objects with Reversible Flows

Segmenting primary objects in a video is an important yet challenging problem in intelligent video surveillance, as it exhibits various levels of foreground/background ambiguities. To reduce such ambiguities, we propose a novel formulation via exploiting foreground and background context as well as their complementary constraint. Under this formulation, a unified objective function is further defined to encode each cue. For implementation, we design a complementary segmentation network (CSNet) with two separate branches, which can simultaneously encode the foreground and background information along with joint spatial constraints. The CSNet is trained on massive images with manually annotated salient objects in an end-to-end manner. By applying CSNet on each video frame, the spatial foreground and background maps can be initialized. To enforce temporal consistency effectively and efficiently, we divide each frame into superpixels and construct a neighborhood reversible flow that reflects the most reliable temporal correspondences between superpixels in far-away frames. With such a flow, the initialized foregroundness and backgroundness can be propagated along the temporal dimension so that primary video objects gradually pop out and distractors are well suppressed. Extensive experimental results on three video datasets show that the proposed approach achieves impressive performance in comparisons with 22 state-of-the-art models.

Serial dependence occurs at the level of both features and integrated object representations.

Object perception depends on mechanisms that transform the information received by our sensory receptors into a coherent and meaningful experience. Visual objects are made up of visual features (e.g., shape, color, orientation), which are, in large part, processed in parallel across different brain areas. The experience of unified objects thus requires binding features and brain signals. Our perception of objects is remarkably stable and constant, despite changes in the proximal stimulus caused by eye and body movements or changes in ambient lighting. Such spurious changes are not perceived. Object perception thus also depends on a mechanism that smooths perceptual samples across time, which has been called the continuity field and is quantified by serial dependence. In two studies, the relative levels of feature binding and serial dependence were examined. Participants reported perceived shape or emotional expression; reports were attracted to stimuli seen in the recent past. Results further show that serial dependence occurs both at the level of features and at the level of objects defined by a conjunction of features. The relative level of serial dependence depends on the type of feature or object: Serial dependence of shape occurs mostly independently of other features that define an object, whereas serial dependence of emotional expression occurs on the object-level representation that integrates several features. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Research on adaptive speed control method of an autonomous vehicle passing a speed bump on the highway based on a genetic algorithm

Abstract. When autonomous vehicles pass through uneven roads, especially the consecutive speed control humps (SCHs) on expressways, the speed of them will have a significant influence on the safety and comfort of driving. How to automatically select the most appropriate speed has become a practical research subject. This paper studies the nonlinear vibration process of the suspension system when the autonomous vehicle passes through the SCHs on a highway. Firstly, the paper establishes a four-degree-of-freedom (4-DOF) nonlinear half-vehicle model and a stimulation function of trapezoidal SCHs and then uses the Runge–Kutta method to numerically solve the differential equations of motion of the suspension system. In the next part, the paper chooses the genetic algorithm to build a multi-objective optimization problem model, which selects the vertical displacement of the vehicle body, the suspension's dynamic deflection and the dynamic load of the tire as optimization objectives and combines the method of the unified objective function to find the optimal passing speed. Finally, the paper designs and carries out the solution process of the multi-objective optimization problem for the vehicle under three scenarios, conventional passive suspension, semi-active suspension, active suspension, and compares the optimized state with the pre-optimized state to prove the effectiveness of the optimization model.

Broadband characteristics of high-performance energy-harvesting phononic crystals with point defect

As an artificial periodic material, phononic crystals (PnCs) are suitable for energy harvesting from vibration and noise environments of equipments. A two-dimensional (2D) PnC with a point defect is presented to design a piezoelectric energy-harvesting (PEH) device. Using finite element (FE) simulations, bandwidth and electric power of the initial supercell using the PnC are obtained but do not attain the optimal performance. Therefore, five geometric parameters are considered to perform the numerical experiment using a five-factor and seven-level experimental design. The two relationships between the five geometric parameters and PnCs bandwidth, the five geometric parameters, and output power are finally obtained. The two functional relationships are regarded as a unified objective function to further optimize five geometric parameters. The optimized PnC-based PEH device will achieve better output power within broadband. It is expected to be used to design PEH devices to achieve better output power in wider bandwidth.

THE APPLICABLE LAW REGARDING MATERNAL CUSTODY

The phenomenon of child abduction after divorce due to mixed marriages has spread widely, as the legal texts governing the issue of custody through mixed marriages differ between countries, so the issue of conflict of laws in custody has been strongly raised. In many countries, the legislator did not set unified objective rules governing custody, which gives the legal and practical justification for opening the door to jurisprudential differences and differing judicial rulings because the child is the basis for the relationship between the father and mother after divorce. This prompted a study of the legal nature of custody, to determine the legal adaptation of custody, to set rules of attribution for custody, and to determine the eligibility of the custodian for the child., to determine the applicable law, the statement of its objective rules, the position of international agreements on custody and the extent of the commitment of states to implement them. The same applies in the case of the application of public order and morals, the domicile or place of residence of the child in custody and the criteria for the interests of the child, and other issues.

The Integrative Curriculum Management with a Boarding System in High Schools

This research addresses the pressing need for an integrated madrasah-Islamic boarding school curriculum as a strategic response to the contemporary challenges demanding graduates with both extensive knowledge and profound religious understanding. With the imperative for cognitive and spiritual intelligence in the disruptive era, the study focuses on MAN 2 Malang City, utilizing a qualitative case study approach involving observations, interviews, and document analysis. The research reveals essential aspects of the integrated curriculum, encompassing unified objectives and organized content planning. The implementation phase includes the integration of academic calendars and a structured supervision framework. The study also emphasizes the significance of an evaluative process covering contextual, input, process, and outcome dimensions. Ultimately, this research underscores the critical role of an integrated curriculum in nurturing well-rounded individuals equipped to navigate the complexities of the modern world, offering valuable insights for educational practitioners and policymakers.

Optimization Design for Suspension System Based on Response Surface Method and NCGA Algorithm

For effective and quick selection of hard point coordinate parameters of suspension to improve the handling stability of vehicles, an optimization method was put forward to some certain suspension system by combining the response surface method and NCGA algorithm. A dynamics simulation model was established first to the Macpherson suspension system of some certain mini-van and the sensitivity analysis was carried out to hard point coordinates of the corresponding suspension to find the coordinate parameters whose sensitivities are higher; moreover, an approximate mathematical model was established between the wheel alignment parameters and the selected coordinate parameters in accordance with the response surface method and the corresponding accuracy verification was carried out; and the positioning parameters were grouped rationally and the unified objective function was established by utilizing the direct weighting method; in addition, optimization design was carried out to the established objective function by combining the neighborhood cultivation genetic algorithm (NCGA). Results indicate that the optimized positioning parameter variables are reduced in different degrees so as to further improve the handling stability of vehicles and verify some certain effectiveness of our methods.

Assessing the Grip of Solar Energy Systems on Environmental Sustainability- A Review

: A sustainable energy production system fulfills its goal while being environmentally, socially, and technically sound. The intermittent availability and viability of renewable energy makes this vision a gradual and long-suffering process. In the rapid result-oriented economy, concerns regarding the environment are treated with desperate solutions that may add fuel to the fire. Although substantial research has been going on in the development of emerging technologies and refinement of established systems, we need to be reminded of the larger goal in mind: a benign and sustainable environment. Closing a door on a problem and not opening several new ones is what we must yearn to achieve. Renewable energy systems and their utility may unintentionally harm a different subset of the ecosystem. Solar energy systems are a more recent candidate with a high annual growth rate and thus, are still in the nascent stage to realise the bruised potential of the technology. By 2050, 60 million tons of solar waste will be produced if it is not resolved efficiently. To achieve environmental sustainability, it is imperative to work towards recycling redundant systems, establishing producer responsibility, fulfilling social needs and optimising future technology. By integrating aspects of the research on solar energy systems, their environmental risks, and their potential to create a sustainable ecosystem, this review article attempts to cater to environmental decision making and direct the eventual research and analysis towards their original unified objective.

A multi-scale neurodynamic implementation of incremental grouping

Incremental grouping is a process entailing serial binding of distal image elements into a unified object representation. At the neural level, incremental grouping involves propagation of the enhanced firing rate among feature-tuned neurons in the early visual cortex. Here, we developed a multi-resolution neural model of incremental grouping. In the model, propagation of the enhanced firing rate is achieved by computing the activity difference between two sets of units: attentional or A-units, whose firing rate is modulated by their horizontal collaterals, and non-attentional or N-units that receive only feedforward input. The activity difference is computed on dendrites that act as independent computational subunits. The proposed model employs multiple spatial scales to account for a variable speed of incremental grouping. In addition, the model incorporates the L-junction detection network that enables incremental grouping over L-junctions. Computer simulations show that the timing of attentional modulations in the model is comparable with neurophysiological measurements in monkey primary visual cortex.

Visual sensitivity filtering based local maximum variation prior for blind image deblurring

Blind image deblurring aims to recover the latent sharp image from a given blurred image when the blur kernel is unknown. To solve this ill-posed problem, many researchers have studied various priors to guide the deblurring process. However, whether the image is sharp or not is mostly based on the subjective judgment of human eyes, and there is no unified objective standard. Since the response of blur to visual sensitivity can be modeled by a filtering method, we use human visual system (HVS) convolution filter to filter the target image to simulate the corresponding visual sensitivity. At the same time, we find that the local maximum variation values of the filtered image will be reduced after blurring process. Therefore, we propose a local maximum variation prior (LMV) based on visual sensitivity filtering and construct a new energy function according to LMV. Our method performs well in various scenarios. Compared with the most advanced algorithms, our model achieves good results on both benchmark datasets and natural images.

Low-rank dictionary learning for unsupervised feature selection

There are many high-dimensional data in real-world applications such as biology, computer vision, and social networks. Feature selection approaches are devised to confront high-dimensional data challenges with the aim of efficient learning technologies as well as reduction of models complexity. Due to the hardship of labeling on these datasets, there are a variety of approaches for the feature selection process in an unsupervised setting by considering some important characteristics of data. In this paper, we introduce a novel unsupervised feature selection approach by applying dictionary learning idea in a low-rank representation. Low-rank dictionary learning not only enables us to provide a new data representation but also maintains feature correlation. Then, spectral analysis is employed to preserve sample similarities. Finally, a unified objective function for unsupervised feature selection is proposed in a sparse way by an ℓ2,1-norm regularization. Furthermore, an efficient numerical algorithm is designed to solve the corresponding optimization problem. We demonstrate the performance of the proposed method based on a variety of standard datasets from different applied domains. Our experimental findings reveal that the proposed method outperforms the state-of-the-art algorithms.

Robust Latent Common Subspace Learning for Transferable Feature Representation

This paper proposes a novel robust latent common subspace learning (RLCSL) method by integrating low-rank and sparse constraints into a joint learning framework. Specifically, we transform the data from source and target domains into a latent common subspace to perform the data reconstruction, i.e., the transformed source data is used to reconstruct the transformed target data. We impose joint low-rank and sparse constraints on the reconstruction coefficient matrix which can achieve following objectives: (1) the data from different domains can be interlaced by using the low-rank constraint; (2) the data from different domains but with the same label can be aligned together by using the sparse constraint. In this way, the new feature representation in the latent common subspace is discriminative and transferable. To learn a suitable classifier, we also integrate the classifier learning and feature representation learning into a unified objective and thus the high-level semantics label (data label) is fully used to guide the learning process of these two tasks. Experiments are conducted on diverse data sets for image, object, and document classifications, and encouraging experimental results show that the proposed method outperforms some state-of-the-arts methods.

Outcome-Guided Sparse K-Means for Disease Subtype Discovery via Integrating Phenotypic Data with High-Dimensional Transcriptomic Data

Abstract The discovery of disease subtypes is an essential step for developing precision medicine, and disease subtyping via omics data has become a popular approach. While promising, subtypes obtained from existing approaches are not necessarily associated with clinical outcomes. With the rich clinical data along with the omics data in modern epidemiology cohorts, it is urgent to develop an outcome-guided clustering algorithm to fully integrate the phenotypic data with the high-dimensional omics data. Hence, we extended a sparse K-means method to an outcome-guided sparse K-means (GuidedSparseKmeans) method. An unified objective function was proposed, which was comprised of (i) weighted K-means to perform sample clusterings; (ii) lasso regularizations to perform gene selection from the high-dimensional omics data; and (iii) incorporation of a phenotypic variable from the clinical dataset to facilitate biologically meaningful clustering results. By iteratively optimizing the objective function, we will simultaneously obtain a phenotype-related sample clustering results and gene selection results. We demonstrated the superior performance of the GuidedSparseKmeans by comparing with existing clustering methods in simulations and applications of high-dimensional transcriptomic data of breast cancer and Alzheimer's disease. Our algorithm has been implemented into an R package, which is publicly available on GitHub ( https://github.com/LingsongMeng/GuidedSparseKmeans).

Active recursive Bayesian inference using Rényi information measures

• An active recursive inference method based on Rényi information measures. • Posterior probability changes can enhance both query optimization and stopping criterion in the RBI process. • Using Rényi entropy and α -divergence unifies the multi-objective RBI problem. • The proposed unified framework enhances both speed and accuracy, in the presence of an adversarial prior. Recursive Bayesian inference (RBI) framework provides optimal Bayesian latent variable estimates in real-time settings with streaming noisy observations. Active RBI attempts to effectively select queries that lead to more informative observations to reduce uncertainty until the process is stopped at a certain confidence level. However, the mismatch between querying objective and stopping criterion creates the conundrum of improving the performance of one objective at the expense of deteriorating the other. Moreover, conventional active querying methods stagger in the presence of misleading prior information. Inspired by information theoretic approaches, we propose an active RBI framework where query and stopping criterion are jointly selected through a unified objective based on Rényi information measures. The proposed unified formulation enables us to jointly enhance speed and accuracy in the RBI process. We theoretically demonstrate that the proposed objective encourages exploration in the presence of misleading prior. Furthermore, we motivate our framework by proving a geometrical representation for active querying and decision making on a probability simplex. We provide empirical and experimental studies on two applications including restaurant recommendation and brain-computer interface (BCI) typing systems and demonstrate that our method outperforms comparable approaches by improving both speed and accuracy.

Geometric parameters optimization of a two-dimensional phoxonic crystal with dual forbidden band characteristics

In this paper, a novel phoxonic crystal (PxC) structure composed of silicon, with optimal dual phononic band gap (PNBG) and photonic band gap (PTBG), is presented. Using the finite element analysis method, both the transmission characteristics and dispersion relation of PNBG and PTBG are calculated, and the existence of dual BGs is demonstrated by the means of the analysis of transmission for the PxC structure. The influences of structural parameters on the dual forbidden band characteristics are further explored, the sensitive structure parameters can be determined: the width of elastic beams, the length of square silicon, and the length of square hole. Using the orthogonal test, 25 experimental runs based on 3-factor and 5-level experiment are performed to finish the numerical experimental design and analysis. Four functional relationships can be acquired between the three sensitive parameters and dual BGs. Finally, the unified objective function method is employed to perform the construction of the single objective optimization model for the purpose of obtaining the optimal dual BGs and the corresponding optimal parameter combinations of the PxC structure. Such scheme can be used as the potential optimization way, which may find wide application in the development and design of PxCs.