Misalignment Problem Research Articles

New insights into Korea's trade relations: A comprehensive FNARDL analysis with 18 global partners

This study applied the Fourier nonlinear autoregressive distributed lag (FNARDL) model to investigate the bilateral J-curve effect between Korea and 18 trading partners. As a result, negative asymmetric effects of changes in the real exchange rate were detected in some cases in the short run. However, in other cases, these effects were positive or exhibited both positive and negative trends. This variation stemmed from the heterogeneity of import and export products and the diverse reactions of exporters to exchange rate fluctuations. By contrast, positive asymmetric effects were evident in most cases in the long run. Through the Fourier function, the FNARDL model better captured the J-curve effect compared to the standard NARDL model. Furthermore, by using bilateral trade data, this study mitigated the problem of aggregate misalignment, compared to using a country's gross trade data with the rest of the world. Therefore, the hidden effects of the real exchange rate were unveiled. This study's findings will enhance policymakers' awareness of formulating exchange rate management strategies.

BCAN: Bidirectional Correct Attention Network for Cross-Modal Retrieval.

As a fundamental topic in bridging the gap between vision and language, cross-modal retrieval purposes to obtain the correspondences' relationship between fragments, i.e., subregions in images and words in texts. Compared with earlier methods that focus on learning the visual semantic embedding from images and sentences to the shared embedding space, the existing methods tend to learn the correspondences between words and regions via cross-modal attention. However, such attention-based approaches invariably result in semantic misalignment between subfragments for two reasons: 1) without modeling the relationship between subfragments and the semantics of the entire images or sentences, it will be hard for such approaches to distinguish images or sentences with multiple same semantic fragments and 2) such approaches focus attention evenly on all subfragments, including nonvisual words and a lot of redundant regions, which also will face the problem of semantic misalignment. To solve these problems, this article proposes a bidirectional correct attention network (BCAN), which introduces a novel concept of the relevance between subfragments and the semantics of the entire images or sentences and designs a novel correct attention mechanism by modeling the local and global similarity between images and sentences to correct the attention weights focused on the wrong fragments. Specifically, we introduce a concept about the semantic relationship between subfragments and entire images or sentences and use this concept to solve the semantic misalignment from two aspects. In our correct attention mechanism, we design two independent units to correct the weight of attention focused on the wrong fragments. Global correct unit (GCU) with modeling the global similarity between images and sentences into the attention mechanism to solve the semantic misalignment problem caused by focusing attention on relevant subfragments in irrelevant pairs (RI) and the local correct unit (LCU) consider the difference in the attention weights between fragments among two steps to solve the semantic misalignment problem caused by focusing attention on irrelevant subfragments in relevant pairs (IR). Extensive experiments on large-scale MS-COCO and Flickr30K show that our proposed method outperforms all the attention-based methods and is competitive to the state-of-the-art. Our code and pretrained model are publicly available at: https://github.com/liuyyy111/BCAN.

Center-enhanced video captioning model with multimodal semantic alignment

Video captioning aims at automatically generating descriptive sentences based on the given video, establishing an association between the visual contents and textual languages, has attracted great attention and plays a significant role in many practical applications. Previous researches focus more on the aspect of caption generation, ignoring the alignment of multimodal feature and just simply concatenating them. Besides, video feature extraction is usually done in an off-line manner, which leads to the fact that the extracted feature may not adapted to the subsequent caption generation task. To improve the applicability of extracted features for downstream caption generation and to address the issue of multimodal semantic alignment fusion, we propose an end-to-end center-enhanced video captioning model with multimodal semantic alignment, which integrates feature extraction and caption generation task into a unified framework. In order to enhance the completeness of semantic features, we design a center enhancement strategy where the visual–textual deep joint semantic feature can be captured via incremental clustering, then the cluster centers can serve as the guidance for better caption generation. Moreover, we propose to promote the visual–textual multimodal alignment fusion by learning the visual and textual representation in a shared latent semantic space, so as to alleviate the multimodal misalignment problem. Experimental results on two popular datasets MSVD and MSR-VTT demonstrate that the proposed model could outperform the state-of-the-art methods, obtaining higher-quality caption results.

Spatial attention inference model for cascaded siamese tracking with dynamic residual update strategy

Target representation is crucial for visual tracking. Most Siamese-based trackers try their best to establish target models by using various deep networks. However, they neglect the exploration of correlation among features, which leads to the inability to learn more representative features. In this paper, we propose a spatial attention inference model for cascaded Siamese tracking with dynamic residual update strategy. First, a spatial attention inference model is constructed. The model fuses interlayer multi-scale features generated by dilation convolution to enhance the spatial representation ability of features. On this basis, we use self-attention to capture interaction between target and context, and use cross-attention to aggregate interdependencies between target and background. The model infers potential feature information by exploiting the correlations among features for building better appearance models. Second, a cascaded localization-aware network is introduced to bridge a gap between classification and regression. We propose an alignment-aware branch to resample and learn object-aware features from the predicted bounding boxes for obtaining localization confidence, which is used to correct the classification confidence by weighted integration. This cascaded strategy alleviates the misalignment problem between classification and regression. Finally, a dynamic residual update strategy is proposed. This strategy utilizes the Context Fusion Network (CFNet) to fuse the templates of historical and current frames to generate the optimal templates. Meanwhile, we use a dynamic threshold function to determine when to update by judging the tracking results. The strategy uses temporal context to fully explore the intrinsic properties of the target, which enhances the adaptability to changes in the target’s appearance. We conducted extensive experiments on seven tracking benchmarks, including OTB100, UAV123, TC128, VOT2016, VOT2018, GOT10k and LaSOT, to validate the effectiveness of our proposed algorithm.

Development and Analysis of a Novel Bio-syncretic Parallel Hip Exoskeleton Based on Torque Requirements

Abstract This paper presents a novel bio-syncretic parallel hip exoskeleton (BsPH-Exo) to address the rehabilitation exercise needs of individuals with lower limb motor dysfunction. BsPH-Exo has six degrees of freedom and can generate all three kinds of rotations that the hip joint can naturally realize. BsPH-Exo effectively solves the problem of misalignment between human and exoskeleton joints, eliminating the need for patients to perform any alignment operations. Considering the varying maximum torque requirements for hip joint rehabilitation in different directions, the limbs of BsPH-Exo are specially arranged to ensure that the maximum torque provided by BsPH-Exo in each direction follows the same law as that of the required torque. As a result, BsPH-Exo exhibits excellent output torque performance, specifically in the flexion/extension direction. Moreover, BsPH-Exo demonstrates weak coupling characteristics in the flexion/extension direction and decoupling characteristics in the adduction/abduction direction, which reduces the difficulty in its control. Compared to currently available parallel hip exoskeletons, BsPH-Exo has several distinct advantages that make it particularly well-suited for rehabilitation applications.

Presence of an included mesiodens. Report of a case

Introduction: Supernumerary teeth are additional teeth to the normal formula, in turn these can be retained; that is to say that they are prevented from erupting due to anomalies of position or situation. Objective: The objective of this work is to report the clinical case of an included mesiodens, its affectations in the oral cavity and the surgical treatment. Case report: A 20 year old male patient presented several dental malpositions; in addition to the radiographic examination (panoramic x-ray) the presence of a supernumerary tooth compatible with a mesiodens was observed, which due to its location was affecting the roots of the teeth and caused the partial extrusion of tooth 2.1 and the widening of its periodontal ligament. An occlusal radiograph was requested to establish the best approach. After the radiological diagnosis of the supernumerary tooth, surgical treatment was performed. Conlusion: In the present clinical case, the presence of impacted teeth is observed, indicating that some teeth have failed to fully emerge into the oral cavity. These impacted teeth may be causing dental misalignment, malposition and possible bite problems. Detailed radiographic evaluation and clinical analysis suggest the need to consider treatment options, such as extraction or surgical intervention, to allow proper eruption and restore optimal dental function and esthetics

CrowdAlign: Shared-weight dual-level alignment fusion for RGB-T crowd counting

The combination of visible and thermal images has been proven to be effective in improving accuracy for crowd counting in illumination-unconstrained scenes. However, the challenging problem of misalignment in RGB-T image pairs has not been extensively explored in this context. This study aims to address the issue of misalignment between RGB and thermal image pairs to enhance the counting accuracy of cross-modal models. Specifically, we propose CrowdAlign, a cross-modal feature alignment fusion network that utilizes a shared-weight strategy for efficient feature extraction. Additionally, CrowdAlign addresses alignment adjustments through two stages: pre-fusion and post-fusion alignment. For pre-fusion feature extraction, we design a dual-level spatial-semantic parallel alignment module, while for post-fusion feature extraction, a low-frequency feature attention filtering module is developed. This two-stage alignment approach enables cross-modal feature alignment without requiring additional supervision. Experiments on the public benchmarks demonstrate that our method is effective under RGB-T misalignment or dark conditions. We hope CrowdAlign will inspire researchers to focus on and explore the issue of misalignment between RGB image and thermal image for cross-modal crowd counting.

Design and implementation of a high misalignment-tolerance wireless charger for an electric vehicle with control of the constant current/voltage charging

Wireless charging of Electric Vehicles (EVs) has been extensively researched in the realm of electric cars, offering a convenient method. Nonetheless, there has been a scarcity of experiments conducted on low-power electric vehicles. To establish a wireless power transfer system for an electric vehicle, optimal power and transmission efficiency necessitate arranging the coils coaxially. In wireless charging systems, coils often experience angular and lateral misalignments. In this paper, a new alignment strategy is introduced to tackle the misalignment problem between the transmitter and receiver coils in the wireless charging of Electric Vehicles (EVs). The study involves the design and analysis of a coil, considering factors such as mutual inductance and efficiency. Wireless coils with angular misalignment are modelled in Ansys Maxwell simulation software. The proposed practical EV system aims to align the coils using angular motion, effectively reducing misalignment during the parking of two-wheelers. This is achieved by tilting the transmitter coil in the desired direction. Furthermore, micro sensing coils are employed to identify misalignment and facilitate automatic alignment. Additionally, adopting a power control technique becomes essential to achieve both constant current (CC) and constant voltage (CV) modes during battery charging. Integrating CC and CV modes is crucial for efficiently charging lithium-ion batteries, ensuring prolonged lifespan and optimal capacity utilization. The developed system can improve the efficiency of the wireless charging system to 90.3% with a 24 V, 16 Ah Lithium Ion Phosphate (LiFePO4) battery at a 160 mm distance between the coils.

Detail-preserving image warping by enforcing smooth image sampling

Multi-phase dynamic contrast-enhanced magnetic resonance imaging image registration makes a substantial contribution to medical image analysis. However, existing methods (e.g., VoxelMorph, CycleMorph) often encounter the problem of image information misalignment in deformable registration tasks, posing challenges to the practical application. To address this issue, we propose a novel smooth image sampling method to align full organic information to realize detail-preserving image warping. In this paper, we clarify that the phenomenon about image information mismatch is attributed to imbalanced sampling. Then, a sampling frequency map constructed by sampling frequency estimators is utilized to instruct smooth sampling by reducing the spatial gradient and discrepancy between all-ones matrix and sampling frequency map. In addition, our estimator determines the sampling frequency of a grid voxel in the moving image by aggregating the sum of interpolation weights from warped non-grid sampling points in its vicinity and vectorially constructs sampling frequency map through projection and scatteration. We evaluate the effectiveness of our approach through experiments on two in-house datasets. The results showcase that our method preserves nearly complete details with ideal registration accuracy compared with several state-of-the-art registration methods. Additionally, our method exhibits a statistically significant difference in the regularity of the registration field compared to other methods, at a significance level of p < 0.05. Our code will be released at https://github.com/QingRui-Sha/SFM.

Exploration and application of welding technology for misalignment of pressure pipe orifices in a pumped storage power station

Abstract Pumped storage power stations are currently the most economical and clean large-scale energy storage method. Pumped storage power stations have flexible start and stop, rapid response, and have six major functions, including peak shaving, valley filling, frequency regulation, phase modulation, emergency backup, and black start. With the transformation of the energy system towards clean, low-carbon, safe and efficient, the operational characteristics of the power system will undergo significant changes, requiring sufficient flexible regulation of power sources and energy storage facilities. It is more urgent to accelerate the development and construction of pumped storage energy. Due to the characteristics of pumped storage installation, high-strength pressure steel pipes are required on the upstream side of the power station units as the water diversion pipeline. This article takes a pumped storage power station as an example to analyze and handle the problem of pipe misalignment encountered during the welding process of pressure steel pipes in the power station. Satisfactory results have been achieved, ensuring the welding quality and providing reference for other engineering projects.

Situational diversity in video person re-identification: introducing MSA-BUPT dataset

Thanks to the success of deep learning over the past few years, the video person re-identification (ReID) algorithms have achieved high accuracy on multiple public benchmark datasets. However, the available video person ReID datasets cover a limited range of real-world scenarios, and they have several obvious limitations: limited camera viewing angles, tiny variations of the shooting scene, and even errors in manual labels. These disadvantages prevent video person ReID from being widely used in real-life scenarios. In this work, a new high-quality multi-situation video person ReID dataset, named MSA-BUPT, is built to promote the video person ReID task in large-scale urban surveillance. Specifically, MSA-BUPT contains 684 identities, 2,665 trajectories, and nearly 250,000 frames from 200-h videos across various complex scenarios. Person attribute annotations and unannotated video data are also provided for other research perspectives, such as cross-modality ReID, cross-domain ReID, and so on. Furthermore, two plug-and-play components are used to improve retrieval capabilities: a new scenario-based data augmentation method is proposed to alleviate the person misalignment problem; a re-ranking strategy based on person attribute is applied to make secondary adjustments to the content to the results of the model. The extensive experimental results show that the above methods improve the performance of some representative state-of-the-art models on the new dataset.

Capacitive PVC gel pressure sensors with various interlinked microstructural dielectric middle layers

Our sharp tactile sense is largely attributable to an undulating layer of microstructures between the epidermis and dermis, amplifying tactile signals. Taking inspiration from the biological template, we propose a design of flexible capacitive pressure sensors with various microstructural dielectric middle layers, fabricated using a casting-based approach. This is the first confirmed use of microstructural polyvinyl chloride (PVC) gel in dielectric layers and the first example of casting in the fabrication of capacitive sensors. Notably, on account of its flexibility, the sensor also addresses the problem of microstructure fracture and misalignment during sensor bending. These sensors can achieve a maximum sensitivity of 1.34 kPa−1 (under 10 kPa) with a fast response time (50 ms), good cyclic stability (> 1000 cycles), and a wide pressure sensing range (0 ∼ 290 kPa). When attached to a cup or balloon, this study reveals that these sensors can detect the weight and rigidity of the objects, demonstrating their potential in human-machine interaction, as well as in wearable applications.

Optimizing intrinsic representation for tracking

Learning target representations dedicated to tracking tasks is a promising direction in visual object tracking. Current state-of-the-art approaches exploit pixel appearance reconstruction of auto-encoders for representation training. Such pixel ways are redundant for the high-level semantics of tracking and suffer from an optimization gap where better appearance reconstruction does not correspond to better tracking performance. This article explores the problem of reconstruction misalignment of target representations in Siamese network architectures. We propose an optimization framework for intrinsic representation that restores the high-level feature loss between the networks on the reconstruction side and the target side. This intrinsic representation is generated by feeding the masked image tokens to the target side branch. Unlike the pixel ways, our approach learns to reconstruct the semantic latent level of representation for tracking objects. Moreover, we investigate feeding strategies from the information bottleneck perspective for masked patches to increase the masking performance yet reduce the computational complexity. Additionally, robust propagation mechanisms for the weight parameters of two-sided networks are also explored. Comprehensive evaluations on seven tracking benchmarks demonstrate our effectiveness: GOT-10k, LaSOT, TrackingNet, NFS, UAV123, TNL2K, and OTB100. Compared to the previous best pixel tracker, we outperform it on all seven datasets, with a maximum absolute score of 5.9% on average overlap and a Graphics Processing Unit (GPU) speed of 109 frames per second.

Biomimetic porous wick with efficient fluid transport and excellent heat transfer for loop heat pipes

The porous wick, as a core component of the loop heat pipe (LHP), serves as a source of circulation power. Inspired by the transport system of plant vessels, a radially stacked polyethersulfone (PES) porous wick was designed using PES membranes with an anisotropic porous structure. The PES membranes exhibited excellent capillary force and high permeability. However, the supply capacity of the axially stacked wick was far inferior to that of sintered wick due to the problem of contact gaps and pore misalignment between layers. From the bionic point of view, a laminar winding special transport structure, which is perpendicular to the direction of liquid transport was proposed. The method effectively avoids the adverse effects of gap and pore misalignment on liquid transport. Combining experimental and simulation methods, the heat transfer characteristics and liquid transport characteristics of the radial stacking polyethersulfone wick (RPES) were studied and compared with those of traditional axial stacking polyethersulfone wick (APES) and sintered nickel wick. The results showed that the heat transfer performance of RPES-LHP was significantly improved, with the heating surface temperature maintained at 54.1 °C and thermal resistance of 0.095 °C/W under a heat load of 400 W, which was respectively 26.6 °C and 0.066 °C/W lower than that of the APES-LHP. The evaporator thermal resistance of RPES-LHP also ranked among the top in existing research on wicks. Simulation results indicated that the radial stacking method avoided capillary force weakening and flow resistance increase caused by gap and pore misalignment, thereby enhancing the supply capacity of RPES. The concept of regulating the stacking orientation of the wick to be perpendicular to the direction of liquid transport can strengthen the supply capacity and provide light on the design of porous wicks in the future.

Application of LA-UNet network model in remote sensing classification of urban green space

The accurate identification and monitoring of urban green space is of great significance in urban planning and ecological management. In view of the complex background of urban green space, the traditional remote sensing classification technology is prone to the problem of misalignment and adhesion. Taking Yuhua District of Changsha City as the research area and Gaofen-2 (GF-2) remote sensing image as the data source, we proposed a remote sensing classification method for urban green space based on the LA-UNet model, which was based on the UNet model. We introduced the DWTCA channel attention mechanism module to improve the attention of the network to green space information, and used the CARAFE module to up sample the extracted features to achieve accurate classification of trees, shrubs and other land types in the complex background of the city. The results showed that the LA-UNet model had the best classification effect of urban green space when using standard false color remote sensing images. The overall accuracy and mean intersection over union were 96.3% and 90.9%, which were 2.8% and 6.1% higher than the UNet model, respectively. In the Potsdam public dataset, the overall accuracy and mean intersection over union of the LA-UNet model were also better than those of the UNet model, which increased by 0.9% and 1.8%, respectively, indicating that the LA-UNet model had good robustness and versatility. In summary, the proposed LA-UNet model could effectively alleviate the problems of misalignment and adhesion of urban green space, with advantages in the remote sensing classification of urban green space. The improved LA-UNet model had a smaller parameter volume than the UNet model, which could effectively improve the classification accuracy of urban green space. This study would provide a methodological reference for the accurate classification and understanding the spatial distribution of urban green space.

Triple alignment-enhanced complex question answering over knowledge bases

Program induction is a crucial paradigm for complex question answering over knowledge bases. In the existing learning framework, the predicted program is required to strictly align (word-by-word) with a gold program, which could cause over penalization for minor deviations. Meanwhile, due to the existence of synonyms, program induction question answering often fails to retrieve answer from the knowledge base because individual function argument cannot perfectly replicate the target argument. To address above misalignment problems, we propose a triple alignment-enhanced complex question answering (TACQA) method by incorporating global token alignment, function alignment, and argument alignment. First, apart from the classical global token alignment, the predicted functions are extracted and aligned separately with the gold functions, enabling efficient learning of implicit structural information related to the query framework of program from input questions. Second, an argument alignment is introduced to correct the ambiguous function arguments, which enhances the disambiguation processing efficiency of multi-argument by optimizing candidate pool construction and similarity calculation. The experiments on KQA Pro show that our method consistently outperforms the SOTA methods, demonstrating the effectiveness of triple alignment processing mechanism for simultaneously addressing function misalignment and argument ambiguity in program induction and further improving the model performance.

Self-reconstruction network for fine-grained few-shot classification

Metric-based methods are one of the most common methods to solve the problem of few-shot image classification. However, traditional metric-based few-shot methods suffer from overfitting and local feature misalignment. The recently proposed feature reconstruction-based approach, which reconstructs query image features from the support set features of a given class and compares the distance between the original query features and the reconstructed query features as the classification criterion, effectively solves the feature misalignment problem. However, the issue of overfitting still has not been considered. To this end, we propose a self-reconstruction metric module for diversifying query features and a restrained cross-entropy loss for avoiding over-confident predictions. By introducing them, the proposed self-reconstruction network can effectively alleviate overfitting. Extensive experiments on five benchmark fine-grained datasets demonstrate that our proposed method achieves state-of-the-art performance on both 5-way 1-shot and 5-way 5-shot classification tasks. Code is available at https://github.com/liz-lut/SRM-main.

OIF-Net: An Optical Flow Registration-Based PET/MR Cross-Modal Interactive Fusion Network for Low-Count Brain PET Image Denoising.

The short frames of low-count positron emission tomography (PET) images generally cause high levels of statistical noise. Thus, improving the quality of low-count images by using image postprocessing algorithms to achieve better clinical diagnoses has attracted widespread attention in the medical imaging community. Most existing deep learning-based low-count PET image enhancement methods have achieved satisfying results, however, few of them focus on denoising low-count PET images with the magnetic resonance (MR) image modality as guidance. The prior context features contained in MR images can provide abundant and complementary information for single low-count PET image denoising, especially in ultralow-count (2.5%) cases. To this end, we propose a novel two-stream dual PET/MR cross-modal interactive fusion network with an optical flow pre-alignment module, namely, OIF-Net. Specifically, the learnable optical flow registration module enables the spatial manipulation of MR imaging inputs within the network without any extra training supervision. Registered MR images fundamentally solve the problem of feature misalignment in the multimodal fusion stage, which greatly benefits the subsequent denoising process. In addition, we design a spatial-channel feature enhancement module (SC-FEM) that considers the interactive impacts of multiple modalities and provides additional information flexibility in both the spatial and channel dimensions. Furthermore, instead of simply concatenating two extracted features from these two modalities as an intermediate fusion method, the proposed cross-modal feature fusion module (CM-FFM) adopts cross-attention at multiple feature levels and greatly improves the two modalities' feature fusion procedure. Extensive experimental assessments conducted on real clinical datasets, as well as an independent clinical testing dataset, demonstrate that the proposed OIF-Net outperforms the state-of-the-art methods.

Multi-Granularity Aggregation with Spatiotemporal Consistency for Video-Based Person Re-Identification.

Video-based person re-identification (ReID) aims to exploit relevant features from spatial and temporal knowledge. Widely used methods include the part- and attention-based approaches for suppressing irrelevant spatial-temporal features. However, it is still challenging to overcome inconsistencies across video frames due to occlusion and imperfect detection. These mismatches make temporal processing ineffective and create an imbalance of crucial spatial information. To address these problems, we propose the Spatiotemporal Multi-Granularity Aggregation (ST-MGA) method, which is specifically designed to accumulate relevant features with spatiotemporally consistent cues. The proposed framework consists of three main stages: extraction, which extracts spatiotemporally consistent partial information; augmentation, which augments the partial information with different granularity levels; and aggregation, which effectively aggregates the augmented spatiotemporal information. We first introduce the consistent part-attention (CPA) module, which extracts spatiotemporally consistent and well-aligned attentive parts. Sub-parts derived from CPA provide temporally consistent semantic information, solving misalignment problems in videos due to occlusion or inaccurate detection, and maximize the efficiency of aggregation through uniform partial information. To enhance the diversity of spatial and temporal cues, we introduce the Multi-Attention Part Augmentation (MA-PA) block, which incorporates fine parts at various granular levels, and the Long-/Short-term Temporal Augmentation (LS-TA) block, designed to capture both long- and short-term temporal relations. Using densely separated part cues, ST-MGA fully exploits and aggregates the spatiotemporal multi-granular patterns by comparing relations between parts and scales. In the experiments, the proposed ST-MGA renders state-of-the-art performance on several video-based ReID benchmarks (i.e., MARS, DukeMTMC-VideoReID, and LS-VID).

Global semantic-guided graph attention network for Siamese tracking with ranking loss

Most Siamese trackers based on graph attention models focus on the topology between nodes when extracting features. These approaches ignore contextual information regarding the overall structure of the target, resulting in a diminished capacity for target discrimination. In this paper, to resolve this issue, we propose a global semantic-guided graph attention network for Siamese tracking. Firstly, in order to balance the node constraints with the overall information of the target, a global semantic awareness module (GSA) is proposed. It utilizes the attention strategy to focus on the overall characteristics of the target, aiming to mine the relationship of the target context. Incorporating it into the semantic-guided graph attention network through cross-correlation operations can avoid the problem of focusing only the information between nodes without being able to effectively characterize the target. Secondly, to enhance the accuracy of single-point feature regression results, a novel extreme point feature aggregation module (EPA) is proposed. We obtain feature information of the extreme points on the bounding box and combine them with single-point features for the bounding box feature representation to improve the regression accuracy. Finally, to establish a connection or bridge between the classification and regression subnetworks, a categorical regression alignment network is designed. An IOU-guided ranking loss is introduced to align the classification confidence with the IOU of the corresponding positive sample localization prediction to solve the problem of misalignment of the classification branch with the regression branch effectively. Experiments conducted on five challenging benchmarks datasets, namely GOT-10K, OTB-100, LaSOT, UAV123, and TC128, demonstrate that our approach exhibits superior performance compared to other tracking methods in terms of tracking accuracy and execution efficiency.