High-level Features Research Articles

Face Manipulation Detection

The rise of digital manipulation techniques has led to the proliferation of deepfakes and other manipulated facial images, posing significant challenges to online trust and security. This paper proposes a novel deep learning model aimed at efficiently and effectively detecting face manipulations. The architecture combines the strengths of Efficient Net, a convolutional neural network (CNN) renowned for its accuracy and efficiency, with Long Short-Term Memory (LSTM) networks. Efficient Net is utilized for extracting high-level features from facial images, enabling the model to capture subtle inconsistencies that may indicate manipulation. These features serve as crucial inputs to the subsequent analysis performed by LSTM networks. LSTMs excel at capturing temporal dependencies within sequences of data, making them particularly well-suited for detecting manipulations in video sequences. By leveraging the power of CNNs for feature extraction and the sequential learning capabilities of LSTMs, the proposed hybrid approach aims to achieve superior performance in face manipulation detection. This combination allows the model to effectively analyse both spatial and temporal aspects of facial images, enhancing its ability to detect various forms of manipulation accurately

A Scene Unmixing Deep Learning Network for Local Climate Zone Mapping and Analysis Using Very High Resolution Remote Sensing Imagery

Abstract. With the acceleration of urbanization, the environment and climate necessary for our survival have gradually deteriorated, leading to the increasing prominence of the Urban Heat Island (UHI) effect. Local Climate Zone (LCZ) classification, as a standard of urban morphology, has become an essential tool for monitoring the UHI effect and conducting temperature studies. Deep Learning (DL) models have the ability to represent high-level semantic features. Therefore, this paper proposes amixed scene unmixing DL framework for LCZ mapping and analysis using Very High Resolution (VHR) remote sensing images. This framework consists of a two-stream deep network, including a pure scene classification network (PS-Net) and a mixed scene unmixing network (MSU-Net). We conducted random sampling tests in Wuhan, China in the experiment A. The results show that this model achieved a satisfactory accuracy with the Overall Accuracies (OAs) is 96.78% and a mixed scene unmixing Mean Absolute Error (MAE) of 0.0495. Furthermore, we applied the proposed model to generate LCZ map for five districts in Wuhan in the experiment B. The test accuracy between two experiments differs very slightly. These results demonstrate the applicability and potential of our model for LCZ mapping and urban climate analysis.

Deep Convolutional Network Based on Attention Mechanism for Matching Optical and SAR Images

Abstract. Complex geometric distortions and nonlinear radiation differences between optical and synthetic aperture radar (SAR) images present challenges for the matching of sufficient and evenly distributed corresponding points. To address this problem, this paper proposes a deep convolutional network based on an attention mechanism for matching optical and SAR images. In order to obtain robust feature points, we employ phase consistency instead of image intensity and gradient information for feature detection. A deep convolutional network (DCN) is designed to extract high-level semantic features between optical and SAR images, providing robustness to geometric distortion and nonlinear radiation changes. Notably, incorporating multiple inverted residual structures in the DCN facilitates efficient extraction of local and global features, promoting feature reuse, and reducing the loss of key features. Furthermore, a dense feature fusion module based on coordinate attention is designed, focusing on the spatial positional information of effective features, integrating key features into deep descriptors to enhance the robustness of deep descriptors to nonlinear radiometric differences. A coarse-to-fine strategy is then employed to enhance accuracy by eliminating mismatches. Experimental results demonstrate that the proposed network performs better than the manually designed descriptors-based methods and the stateof- the-art deep learning networks in both matching effectiveness and accuracy. Specifically, the number of matches achieved is approximately 2 times greater than that of other methods, with a 10% improvement in F-measure.

A novel code representation for detecting Java code clones using high-level and abstract compiled code representations.

In software development, it's common to reuse existing source code by copying and pasting, resulting in the proliferation of numerous code clones-similar or identical code fragments-that detrimentally affect software quality and maintainability. Although several techniques for code clone detection exist, many encounter challenges in effectively identifying semantic clones due to their inability to extract syntax and semantics information. Fewer techniques leverage low-level source code representations like bytecode or assembly for clone detection. This work introduces a novel code representation for identifying syntactic and semantic clones in Java source code. It integrates high-level features extracted from the Abstract Syntax Tree with low-level features derived from intermediate representations generated by static analysis tools, like the Soot framework. Leveraging this combined representation, fifteen machine-learning models are trained to effectively detect code clones. Evaluation on a large dataset demonstrates the models' efficacy in accurately identifying semantic clones. Among these classifiers, ensemble classifiers, such as the LightGBM classifier, exhibit exceptional accuracy. Linearly combining features enhances the effectiveness of the models compared to multiplication and distance combination techniques. The experimental findings indicate that the proposed method can outperform the current clone detection techniques in detecting semantic clones.

Deep Feature Retention Module Network for Texture Classification

Texture describes the unique features of an image. Therefore, texture classification is a crucial task in computer vision. Various CNN-based deep learning methods have been developed to classify textures. During training, the deep-learning model undergoes an end-to-end procedure of learning features from low to high levels. Most CNN architectures depend on high-level features for the final classification. Hence, other low- and mid-level information was not prioritized for the final classification. However, in the case of texture classification, it is essential to determine detailed feature information within the pattern to classify textures as they have diversity and irregularity in images within the same class. Therefore, the feature information at the low- and mid-levels can also provide meaningful information to distinguish the classes. In this study, we introduce a CNN model with a feature retention module (FRM) to utilize features from numerous levels. FRM maintains the texture information extracted at each level and extracts feature information through filters of various sizes. We used three texture datasets to evaluate the proposed model combined with the FRM. The experimental results showed that learning using different levels of features together assists in improving learning performance more than learning using high-level features.

Lung cancer computed tomography image classification using Attention based Capsule Network with dispersed dynamic routing

AbstractLung cancer is relying as one of the significant and leading cause for the deaths which are based on cancer. So, an effective diagnosis is a crucial step to save the patients who are all dying due to lung cancer. Moreover, the diagnosis must be performed based on the severity of lung cancer and the severity can be addressed with the help of an optimal classification approach. So, this research introduced an Attention based Capsule Network (A‐Caps Net) with dispersed dynamic routing to perform in‐depth classification of the disease affected partitions of the image and results in better classification results. The attention layer with dispersed dynamic routing evaluates the digit capsule from feature vector in a constant manner. As the first stage, data acquisitioned from datasets such as Lung Nodule Analysis‐16 (LUNA‐16), The Cancer Imaging Archive (TCIA) dataset and Lung Image Database Consortium and Image Database Resource Initiative (LIDC‐IDRI). After acquisitioning data, pre‐processing is done to enhance the resolution of the image using Generative Adversarial Network. The pre‐processed output is given as output for extraction of features that takes place using GLCM and VGG‐16 which extracts the low level features and high level features respectively. Finally, categorization of lung cancer is performed using Attention based Capsule Network (A‐Caps Net) with dispersed dynamic routing which categorize the lung cancer as benign and malignant. The results obtained through experimental analysis exhibits that proposed approach attained better accuracy of 99.57%, 99.91% and 99.29% for LUNA‐16, LIDC‐IDRI and TCIA dataset respectively. The classification accuracy achieved by the proposed approach for LUNA‐16 dataset is 99.57% which is comparably higher than DBN, 3D CNN, Squeeze Nodule Net and 3D‐DCNN with multi‐layered filter with accuracies of 99.16%, 97.17% and 94.1% respectively.

Multi-Scale Fusion Siamese Network Based on Three-Branch Attention Mechanism for High-Resolution Remote Sensing Image Change Detection

Remote sensing image change detection (CD) is an important means in remote sensing data analysis tasks, which can help us understand the surface changes in high-resolution (HR) remote sensing images. Traditional pixel-based and object-based methods are only suitable for low- and medium-resolution images, and are still challenging for complex texture features and detailed image detail processing in HR images. At present, the method based on deep learning has problems such as inconsistent fusion and difficult model training in the combination of the difference feature information of the deep and shallow layers and the attention mechanism, which leads to errors in the distinction between the changing region and the invariant region, edge detection and small target detection. In order to solve the above problems of inconsistent fusions of feature information aggregation and attention mechanisms, and indistinguishable change areas, we propose a multi-scale feature fusion Siamese network based on attention mechanism (ABMFNet). To tackle the issues of inconsistent fusion and alignment difficulties when integrating multi-scale fusion and attention mechanisms, we introduce the attention-based multi-scale feature fusion module (AMFFM). This module not only addresses insufficient feature fusion and connection between different-scale feature layers, but also enables the model to automatically learn and prioritize important features or regions in the image. Additionally, we design the cross-scale fusion module (CFM) and the difference feature enhancement pyramid structure (DEFPN) to assist the AMFFM module in integrating differential information effectively. These modules bridge the spatial disparity between low-level and high-level features, ensuring efficient connection and fusion of spatial difference information. Furthermore, we enhance the representation and inference speed of the feature pyramid by incorporating a feature enhancement module (FEM) into DEFPN. Finally, the BICD dataset proposed by the laboratory and public datasets LEVIR-CD and BCDD are compared and tested. We use F1 score and MIoU values as evaluation metrics. For AMBMFNet, the F1 scores on the three datasets are 77.69%, 81.57%, and 77.91%, respectively, while the MIoU values are 84.65%, 85.84%, and 84.54%, respectively. The experimental results show that ABMFNet has better effectiveness and robustness.

Range-Spread Target Detection Networks Using HRRPs

Range-spread target (RST) detection is an important issue for high-resolution radar (HRR). Traditional detectors relying on manually designed detection statistics have their performance limitations. Therefore, in this work, two deep learning-based detectors are proposed for RST detection using HRRPs, i.e., an NLS detector and DFCW detector. The NLS detector leverages domain knowledge from the traditional detector, treating the input HRRP as a low-level feature vector for target detection. An interpretable NLS module is designed to perform noise reduction for the input HRRP. The DFCW detector takes advantage of the extracted high-level feature map of the input HRRP to improve detection performance. It incorporates a feature cross-weighting module for element-wise feature weighting within the feature map, considering the channel and spatial information jointly. Additionally, a nonlinear accumulation module is proposed to replace the conventional noncoherent accumulation operation in the double-HRRP detection scenario. Considering the influence of the target spread characteristic on detector performance, signal sparseness is introduced as a measure and used to assist in generating two datasets, i.e., a simulated dataset and measured dataset incorporating real target echoes. Experiments based on the two datasets are conducted to confirm the contribution of the designed modules to detector performance. The effectiveness of the two proposed detectors is verified through performance comparison with traditional and deep learning-based detectors.

EXPRESS: Modeling the Impact of Single vs Dual Presentation on Visual Discrimination Across Resolutions.

Visual categorisation relies on our ability to extract useful diagnostic information from complex stimuli. To do this, we can utilise both the 'high-level' and 'low-level' information in a stimulus, however the extent to which changes in these properties impact the decision-making process is less clear. We manipulated participants' access to high-level category features via gradated reductions to image resolution while exploring the impact of access to additional category features through a dual stimulus presentation when compared to single stimulus presentation. Results showed that while increasing image resolution consistently resulted in better choice performance, no benefit was found for dual presentation over single presentation, despite responses for dual presentation being slower compared to single presentation. Applying the diffusion decision model revealed increases in drift rate as a function of resolution, but no change in drift rate for single versus dual presentation. The increase in response time for dual presentation was instead accounted for by an increase in response caution for dual presentations. These findings suggest that while increasing access to high-level features (via increased resolution) can improve participants' categorisation performance, increasing access to both high- and low-level features (via an additional stimulus) does not.

A Multi-Feature Fusion Method for Urban Functional Regions Identification: A Case Study of Xi’an, China

Research on the identification of urban functional regions is of great significance for the understanding of urban structure, spatial planning, resource allocation, and promoting sustainable urban development. However, achieving high-precision urban functional region recognition has always been a research challenge in this field. For this purpose, this paper proposes an urban functional region identification method called ASOE (activity–scene–object–economy), which integrates the features from multi-source data to perceive the spatial differentiation of urban human and geographic elements. First, we utilize VGG16 (Visual Geometry Group 16) to extract high-level semantic features from the remote sensing images with 1.2 m spatial resolution. Then, using scraped building footprints, we extract building object features such as area, perimeter, and structural ratios. Socioeconomic features and population activity features are extracted from Point of Interest (POI) and Weibo data, respectively. Finally, integrating the aforementioned features and using the Random Forest method for classification, the identification results of urban functional regions in the main urban area of Xi’an are obtained. After comparing with the actual land use map, our method achieves an identification accuracy of 91.74%, which is higher than other comparative methods, making it effectively identify four typical urban functional regions in the main urban area of Xi’an (e.g., residential regions, industrial regions, commercial regions, and public regions). The research indicates that the method of fusing multi-source data can fully leverage the advantages of big data, achieving high-precision identification of urban functional regions.

Drug repositioning based on tripartite cross-network embedding and graph convolutional network

Drug-disease association prediction is an important part of drug discovery, which can help researchers uncover potential drug candidates and disease targets more accurately to deal with the drawbacks of inefficiency and high cost of traditional methods. In contrast, past drug-disease prediction processes often overlooked the associations between drugs and side effects and the impact of proteins on diseases. These issues hindered models from fully learning the potential information within the network. Hence, a method capable of comprehensively learning from multi-source heterogeneous information and extracting high-level features of biological associations is needed. To overcome these challenges, proposes a drug repositioning method based on a tripartite cross-network embedding graph convolutional network, called TGCNDR, to predict the associations between drugs and diseases. Firstly, we construct a tripartite cross-network of drug-disease associations, drug-protein associations, and drug-side effect associations. TGCNDR employs graph convolutional networks to capture information from different nodes to learn drug embedding. Subsequently, TGCNDR uses anchor links for knowledge transfer, and different networks use the Self-attention mechanism to represent drug importance. Experiments on benchmark datasets demonstrate that TGCNDR exhibits good performance (the average AUROC is 0.922, the average AUPR is 0.916, and the average F1-score is 0.860) compared with state-of-the-art methods. In the case study, we perform molecular docking experiments on the predicted drug candidates and identify newly approved drugs for osteosarcoma, which suggests that TGCNDR is an effective tool for drug repositioning.

MVT: Multi-Vision Transformer for Event-Based Small Target Detection

MVT: Multi-Vision Transformer for Event-Based Small Target Detection

Dynamic identification of coupler force of heavy haul locomotive: An effective and long-term intelligent measurement method

Longitudinal impulse, as a common dynamic problem of heavy haul trains, could induce the lateral instability of the coupler and the separation of the locomotive and wagon connection and thus seriously hinder the train running safety. The coupler force undergoes complex changes during longitudinal impulse transmission and exhibits strong nonlinear characteristics, which poses significant challenges to the identification of the coupler force. To address these issues, this paper reports a novel quantitative method for the coupler force identification of heavy haul locomotives. Firstly, the moving average filtering method is used to preprocess the signal of longitudinal relative displacement between the coupler and carbody (LRDCC), and the approximate relative velocity (ARV) feature is also extracted from the preprocessed signal. Then, a Convolutional Neural Network (CNN) model is constructed to extract high-level features from LRDCC and ARV. The model with randomly initialized weight parameters does not require additional training and thus reduces the computational cost. Finally, an Extreme Learning Machine (ELM) is used as the regression layer to process the extracted high-level features and further improve the identification performance. Additionally, the dung beetle algorithm is used to obtain the optimal model parameters to improve the coupler force identification performance. Not only a dynamics simulation but a field test is carried out to show that the proposed method could accurately detect the coupler force of heavy haul locomotives. Furthermore, the proposed method shows promising prospects in replacing the traditional monitoring method under the actual long-term working conditions of trains.

An effective method for small objects detection based on MDFFAM and LKSPP

Object detection is one of the research hotspots in computer vision. However, most existing object detectors struggle with the identification of small targets. Therefore, the paper proposes two modules: the MDFFAM (Multi-Directional Feature Fusion Attention Mechanism) and the LKSPP (Large Kernel Spatial Pyramid Pooling), to enhance the detector's effectiveness in identifying subtle faults on the surface of mechanical equipment. LKSPP aims to expand the receptive field to capture high-level semantic features through large kernels. Meanwhile, the MDFFAM allows the network to efficiently utilize spatial location information and adaptively recognize detection priorities. In the detection task, MDFFAM effectively captures feature information in three spatial directions: width, height, and channel, with the location information fully utilized to establish stable long-range dependencies. Moreover, LKSPP boasts a larger receptive field and imposes less computational burden compared to the SPPCSPC by YOLOv7. Finally, experiments demonstrate that the proposed module effectively improves the detection accuracy for small targets, surpassing the state-of-the-art object detector, YOLOv7. Remarkably, MDFFAM incurs almost negligible computational overhead.

G2ViT: Graph Neural Network-Guided Vision Transformer Enhanced Network for retinal vessel and coronary angiograph segmentation

Blood vessel segmentation is a crucial stage in extracting morphological characteristics of vessels for the clinical diagnosis of fundus and coronary artery disease. However, traditional convolutional neural networks (CNNs) are confined to learning local vessel features, making it challenging to capture the graph structural information and fail to perceive the global context of vessels. Therefore, we propose a novel graph neural network-guided vision transformer enhanced network (G2ViT) for vessel segmentation. G2ViT skillfully orchestrates the Convolutional Neural Network, Graph Neural Network, and Vision Transformer to enhance comprehension of the entire graphical structure of blood vessels. To achieve deeper insights into the global graph structure and higher-level global context cognizance, we investigate a graph neural network-guided vision transformer module. This module constructs graph-structured representation in an unprecedented manner using the high-level features extracted by CNNs for graph reasoning. To increase the receptive field while ensuring minimal loss of edge information, G2ViT introduces a multi-scale edge feature attention module (MEFA), leveraging dilated convolutions with different dilation rates and the Sobel edge detection algorithm to obtain multi-scale edge information of vessels. To avoid critical information loss during upsampling and downsampling, we design a multi-level feature fusion module (MLF2) to fuse complementary information between coarse and fine features. Experiments on retinal vessel datasets (DRIVE, STARE, CHASE_DB1, and HRF) and coronary angiography datasets (DCA1 and CHUAC) indicate that the G2ViT excels in robustness, generality, and applicability. Furthermore, it has acceptable inference time and computational complexity and presents a new solution for blood vessel segmentation.

Fine-Grained Feature Perception for Unmanned Aerial Vehicle Target Detection Algorithm

Unmanned aerial vehicle (UAV) aerial images often present challenges such as small target sizes, high target density, varied shooting angles, and dynamic poses. Existing target detection algorithms exhibit a noticeable performance decline when confronted with UAV aerial images compared to general scenes. This paper proposes an outstanding small target detection algorithm for UAVs, named Fine-Grained Feature Perception YOLOv8s-P2 (FGFP-YOLOv8s-P2), based on YOLOv8s-P2 architecture. We specialize in improving inspection accuracy while meeting real-time inspection requirements. First, we enhance the targets’ pixel information by utilizing slice-assisted training and inference techniques, thereby reducing missed detections. Then, we propose a feature extraction module with deformable convolutions. Decoupling the learning process of offset and modulation scalar enables better adaptation to variations in the size and shape of diverse targets. In addition, we introduce a large kernel spatial pyramid pooling module. By cascading convolutions, we leverage the advantages of large kernels to flexibly adjust the model’s attention to various regions of high-level feature maps, better adapting to complex visual scenes and circumventing the cost drawbacks associated with large kernels. To match the excellent real-time detection performance of the baseline model, we propose an improved Random FasterNet Block. This block introduces randomness during convolution and captures spatial features of non-linear transformation channels, enriching feature representations and enhancing model efficiency. Extensive experiments and comprehensive evaluations on the VisDrone2019 and DOTA-v1.0 datasets demonstrate the effectiveness of FGFP-YOLOv8s-P2. This achievement provides robust technical support for efficient small target detection by UAVs in complex scenarios.

Parallel feature enhancement and adaptive weighted feature fusion for semantic segmentation

To tackle the challenges posed by the insensitivity of current multi-scale networks to image detailed information and their limited capacity to model contextual relationships, our paper proposes a novel semantic segmentation network called LEFNet. It is based on Parallel Feature Enhancement (PFE) and Adaptive Weighted Feature Fusion (AWFF). In the coding stage, the PFE module performs posterior enhancement of multi-scale features by Detail Sharpening Attention (DSA) and High-level Dilation Fusion (HDF) methods. The DSA guides the learning of detailed information in low-level features. The HDF broadens the perceptual field, enabling the acquisition of richer high-level features. In the decoding stage, the AWFF module supersedes the conventional feature fusion methods. The AWFF module constructs perceptual factors for each multi-scale feature map, enabling weighted learning of features. It emphasizes features with stronger semantic information, making them more decisive in pixel classification. It integrates features more reasonably based on the relevance of global contextual information, fully releasing the expressive potential of encoded features. Our method achieves mIoU scores of 82.8%, 49.3%, and 45.4% on the Cityscapes, ADE 20 K, and COCO-Stuff 164 K datasets, respectively, reaching an advanced level on popular benchmarks. The experimental results show that LEFNet alleviates the challenge of insensitivity of multi-scale networks to image detailed information, improves its ability to model contextual relationships, and significantly improves segmentation performance.

Use of the International IFOMPT Cervical Framework to inform clinical reasoning in postgraduate level physiotherapy students: a qualitative study using think aloud methodology

BackgroundVascular pathologies of the head and neck are rare but can present as musculoskeletal problems. The International Federation of Orthopedic Manipulative Physical Therapists (IFOMPT) Cervical Framework (Framework) aims to assist evidence-based clinical reasoning for safe assessment and management of the cervical spine considering potential for vascular pathology. Clinical reasoning is critical to physiotherapy, and developing high-level clinical reasoning is a priority for postgraduate (post-licensure) educational programs.ObjectiveTo explore the influence of the Framework on clinical reasoning processes in postgraduate physiotherapy students.MethodsQualitative case study design using think aloud methodology and interpretive description, informed by COnsolidated criteria for REporting Qualitative research. Participants were postgraduate musculoskeletal physiotherapy students who learned about the Framework through standardized delivery. Two cervical spine cases explored clinical reasoning processes. Coding and analysis of transcripts were guided by Elstein’s diagnostic reasoning components and the Postgraduate Musculoskeletal Physiotherapy Practice model. Data were analyzed using thematic analysis (inductive and deductive) for individuals and then across participants, enabling analysis of key steps in clinical reasoning processes and use of the Framework. Trustworthiness was enhanced with multiple strategies (e.g., second researcher challenged codes).ResultsFor all participants (n = 8), the Framework supported clinical reasoning using primarily hypothetico-deductive processes. It informed vascular hypothesis generation in the patient history and testing the vascular hypothesis through patient history questions and selection of physical examination tests, to inform clarity and support for diagnosis and management. Most participant’s clinical reasoning processes were characterized by high-level features (e.g., prioritization), however there was a continuum of proficiency. Clinical reasoning processes were informed by deep knowledge of the Framework integrated with a breadth of wider knowledge and supported by a range of personal characteristics (e.g., reflection).ConclusionsFindings support use of the Framework as an educational resource in postgraduate physiotherapy programs to inform clinical reasoning processes for safe and effective assessment and management of cervical spine presentations considering potential for vascular pathology. Individualized approaches may be required to support students, owing to a continuum of clinical reasoning proficiency. Future research is required to explore use of the Framework to inform clinical reasoning processes in learners at different levels.

Visual smoke recognition based on an inverse-radiating attention pyramid network

In thermal power generation systems, the exhaust gases produced during the process of power generation should be fully burnt before being discharged into the air through a high-altitude chimney, to help maintain safe production and to avoid pollution. A thermal power generation system will emit white smoke when operating normally; otherwise, under abnormal conditions: (1) large amounts of dark smoke may be released into the air due to incomplete combustion of the exhaust gases, leading to hazards to public health and the environment; (2) colorless smoke can be emitted if toxic exhaust gases are directly released into the air, also causing dangerous pollution. To address these issues, we have developed an inverse-radiating attention pyramid network (IRAP-Net) for visual smoke recognition, directed towards monitoring thermal power generation systems. The proposed IRAP-Net exploits various visual smoke features. IRAP-Net is based on three pyramid blocks, composed of 3, 4 and 5 convolution modules, respectively. An attention mechanism is introduced into each pyramid block selective of features. Lastly, an inverse-radiating connection converges all the outputs of the pyramid blocks in a feedforward manner, thereby merging low-level and high-level features. Experiments on a large smoke image database show that the proposed IRAP-Net achieves a recognition rate exceeding 95.5%, superior to other state-of-the-art (SOTA) models.

Longitudinally Consistent Registration and Parcellation of Cortical Surfaces Using Semi-Supervised Learning

Temporally consistent and accurate registration and parcellation of longitudinal cortical surfaces is of great importance in studying longitudinal morphological and functional changes of human brains. However, most existing methods are developed for registration or parcellation of a single cortical surface. When applying to longitudinal studies, these methods independently register/parcellate each surface from longitudinal scans, thus often generating longitudinally inconsistent and inaccurate results, especially in small or ambiguous cortical regions. Essentially, longitudinal cortical surface registration and parcellation are highly correlated tasks with inherently shared constraints on both spatial and temporal feature representations, which are unfortunately ignored in existing methods. To this end, we unprecedentedly propose a novel semi-supervised learning framework to exploit these inherent relationships from limited labeled data and extensive unlabeled data for more robust and consistent registration and parcellation of longitudinal cortical surfaces. Our method utilizes the spherical topology characteristic of cortical surfaces. It employs a spherical network to function as an encoder, which extracts high-level cortical features. Subsequently, we build two specialized decoders dedicated to the tasks of registration and parcellation, respectively. To extract more meaningful spatial features, we design a novel parcellation map similarity loss to utilize the relationship between registration and parcellation tasks, i.e., the parcellation map warped by the deformation field in registration should match the atlas parcellation map, thereby providing extra supervision for the registration task and augmented data for parcellation task by warping the atlas parcellation map to unlabeled surfaces. To enable temporally more consistent feature representation, we additionally enforce longitudinal consistency among longitudinal surfaces after registering them together using their concatenated features. Experiments on two longitudinal datasets of infants and adults have shown that our method achieves significant improvements on both registration/parcellation accuracy and longitudinal consistency compared to existing methods, especially in small and challenging cortical regions.