Face detection accuracy significantly decreases under rotational variations, including in-plane (RIP) and out-of-plane (ROP) rotations. ROP is particularly problematic due to its impact on landmark distortion, which leads to inaccurate face center localization. Meanwhile, many existing rotation-invariant models are primarily designed to handle RIP, they often fail under ROP because they lack the ability to capture semantic and topological relationships. Moreover, existing datasets frequently suffer from unreliable landmark annotations caused by imperfect ground truth labeling, the absence of precise center annotations, and imbalanced data across different rotation angles. To address these challenges, we propose a topology-guided semantic face center estimation method that leverages graph-based landmark relationships to preserve structural integrity under both RIP and ROP. Additionally, we construct a rotation-aware face dataset with accurate face center annotations and balanced rotational diversity to support training under extreme pose conditions. Next, we introduce a Hybrid-ViT model that fuses CNN spatial features with transformer-based global context and employ a center-guided module for robust landmark localization under extreme rotations. In order to evaluate center quality, we further design a hybrid metric that combines topological geometry with semantic perception for a more comprehensive evaluation of face center accuracy. Finally, experimental results demonstrate that our method outperforms state-of-the-art models in cross-dataset evaluations. Code: https://github.com/Catster111/TCE_RIFD.

Chest X-Ray Vision-Language pretraining (VLP) leverages large-scale radiograph-report pairs to develop joint image-text representations, demonstrating significant potential for medical image diagnosis. However, existing VLP approaches often overlook the multi-view nature of chest X-Rays, and some multi-view methods apply uniform feature fusion, neglecting view-key semantic contributions. Moreover, random cross-modal Masked Language Modeling (MLM) fails to facilitate effective interactions, impeding representation alignment. Additionally, global alignment in VLP may lead to the false-negative problem. To address these limitations, we propose a novel medical VLP framework comprising three core components. First, a Key Semantics-enhanced Multi-view MLM module aggregates pathology-relevant patches across views, providing semantically rich supervision for MLM. A local semantics enhancing approach, which identifies and aggregates pathology-relevant key patches across views to guide MLM. Second, a Frontal-Lateral Alignment module extracts view-specific pathological features, ensuring semantic consistency and preserving critical information during aggregation. This module independently extracts pathological features from both views to preserve view-specific information while ensuring semantic consistency, which mitigates the loss of crucial information during aggregation. Third, a High-order Semantic Alignment approach mitigates false-negative issues by aligning features with semantically consistent clusters, enhancing global alignment through prototype-level semantics. Extensive experiments across seven public datasets demonstrate that our framework outperforms state-of-the-art methods in four downstream tasks, validating its efficacy. The code is available at https://github.com/sajiutea/F-L.

The accurate segmentation of brain tumor is significant in clinical practice. Convolutional Neural Network (CNN)-based methods have made great progress in brain tumor segmentation due to powerful local modeling ability. However, brain tumors are frequently pattern-agnostic, i.e. variable in shape, size and location, which can not be effectively matched by traditional CNN-based methods with local and regular receptive fields. To address the above issues, we propose a shape-scale co-awareness network (S2CA-Net) for brain tumor segmentation, which can efficiently learn shape-aware and scale-aware features simultaneously to enhance pattern-agnostic representations. Primarily, three key components are proposed to accomplish the co-awareness of shape and scale. The Local-Global Scale Mixer (LGSM) decouples the extraction of local and global context by adopting the CNN-Former parallel structure, which contributes to obtaining finer hierarchical features. The Multi-level Context Aggregator (MCA) enriches the scale diversity of input patches by modeling global features across multiple receptive fields. The Multi-Scale Attentive Deformable Convolution (MS-ADC) learns the target deformation based on the multiscale inputs, which motivates the network to enforce feature constraints both in terms of scale and shape for optimal feature matching. Overall, LGSM and MCA focus on enhancing the scale-awareness of the network to cope with the size and location variations, while MS-ADC focuses on capturing deformation information for optimal shape matching. Finally, their effective integration prompts the network to perceive variations in shape and scale simultaneously, which can robustly tackle the variations in patterns of brain tumors. The experimental results on BraTS 2019, BraTS 2020, MSD BTS Task and BraTS2023-MEN show that S2CA-Net has superior overall performance in accuracy and efficiency compared to other state-of-the-art methods. Code: https://github.com/jiangyu945/S2CA-Net.

In visual tracking, unreliable samples always exist because of occlusion, illumination variation, motion blur, etc. Existing studies have effectively improved the performance of trackers by enhancing the quality of online samples. However, an underappreciated view is that not all samples are equally essential to model training. In this paper, we propose a Sample-Aware Adaptive Updating (SAAU) strategy which can actively adjust the update formula by sensing the reliability of samples. Specifically, the Sample-Reliability Awareness (SRA) module can quantify sample reliability by calculating three specific indicators, where the Residual Peak-to-Correlation Energy (RPCE) is designed to cooperate with the other two introduced indicators to obtain credit scores on each sample. Besides, the Self-Guided Update (SGU) module provides a tracker with an unfixed learning rate that matches with the reliability label during updating, where our label annotator generates the label. Extensive experiments on several public benchmarks demonstrate the outstanding compatibility of SAAU and the superiority of our tracker (SAAU-CF) over state-of-the-art approaches.

Facial expression recognition (FER) based on the convolutional neural network (CNN) in the wild have numerous challenges. For instance, the complexity of the network model makes FER tasks difficult to deploy on portable devices. Some approaches design lightweight networks to reduce the model size, while the intrinsic imbalance of the existing facial emotion datasets is still ignored. In order to overcome the above problems, the lightweight CNN based on sample equalization method for FER is designed to reduce the network parameters sharply while maintaining the identification accuracy. Specifically, to reduce the number of network parameters, a lightweight network framework (SDNet) is designed with separable convolution layers and dense blocks, which can significantly reduce network parameters. Second, the adaptive class weights are proposed to solve the imbalance of sample numbers. Moreover, a resist overfitting (RO) loss function is proposed to improve the classification accuracy. Extensive experiments are conducted on lab-controlled datasets (CK+, Oulu-CASIA) and in-the-wild datasets (FER2013, SFEW). Experimental results show that our method is superior to several state-of-the-art FER methods.

Facial expression recognition (FER) has been a challenging task in the field of artificial intelligence. In this paper, we propose a novel model, named regional self-attention convolutional neural network (RSACNN), for FER. Different from the previous methods, RSACNN makes full use of the facial texture of expression salient region, so yields a robust feature representation for FER. The proposed model contains two novel parts: regional local multiple pattern (RLMP) based on the improved K-means algorithm and the regional self-attention module (RSAM). First, RLMP uses the improved K-means algorithm to dynamically cluster the pixels to ensure the robustness of texture features with expression salient variation. Besides, the texture description is enhanced by extending the binary pattern to the multiple patterns and integrating the information of gray difference between pixels in the region. Next, RSAM can adaptively form weights for each region through the self-attention mechanism, and use rank regularization loss (RRLoss) to constrain the weights of different regions. By jointly combining RLMP and RSAM, RSACNN can effectively enhance the feature representation of expression salient regions, so that the performance of expression recognition can be improved. Extensive experiments on public datasets, i.e. CK[Formula: see text], Oulu-CASIA, Fer2013 and SFEW, prove the superiority of our method over state-of-the-art approaches.

Current state-of-the-art detectors achieved impressive performance in detection accuracy with the use of deep learning. However, most of such detectors cannot detect objects in real time due to heavy computational cost, which limits their wide application. Although some one-stage detectors are designed to accelerate the detection speed, it is still not satisfied for task in high-resolution remote sensing images. To address this problem, a lightweight one-stage approach based on YOLOv3 is proposed in this paper, which is named Squeeze-and-Excitation YOLOv3 (SE-YOLOv3). The proposed algorithm maintains high efficiency and effectiveness simultaneously. With an aim to reduce the number of parameters and increase the ability of feature description, two customized modules, lightweight feature extraction and attention-aware feature augmentation, are embedded by utilizing global information and suppressing redundancy features, respectively. To meet the scale invariance, a spatial pyramid pooling method is used to aggregate local features. The evaluation experiments on two remote sensing image data sets, DOTA and NWPU VHR-10, reveal that the proposed approach achieves more competitive detection effect with less computational consumption.

One primary challenge in face anti-spoofing refers to suffering a sharp performance drop in cross-domain scenes, where training and testing images are collected from different datasets. Recent methods have achieved promising results by aligning the features of all images among the available source domains. However, due to significant distribution discrepancies among non-face regions of all images, it is challenging to capture domain-invariant features for these regions. In this paper, we propose a novel Selective Domain-invariant Feature Alignment Network (SDFANet) for cross-domain face anti-spoofing, which aims to seek common feature representations by fully exploring the generalization of different regions of images. Different from previous works that align the whole features directly, the proposed SDFANet leverages multiple domain discriminators with the same architecture to balance the generalization of different regions of the all images. Specifically, we firstly design a multi-grained feature alignment network composed of a local-region and global-image alignment subnetworks to learn more generalized feature space for real faces. Besides, the domain adapter module, which aims to alleviate the large domain discrepancy with the help of the domain attention strategy, is adopted to facilitate the learning of our multi-grained feature alignment network. In addition, a multi-scale attention fusion module is designed in our feature generator to refine the different levels of features effectively. Experimental results show that the proposed SDFANet can greatly improve the generalization ability of face anti-spoofing, and that is superior to the existing methods.

With the increase in the morbidity of liver cancer and its high mortality rate, liver segmentation in abdominal computed tomography (CT) scan images has received extensive attention. Segmentation results play an important role in computer-assisted diagnosis and therapy. However, it remains a challenging task because of the complexity of the liver’s anatomy, low contrast between the liver and its adjacent organs, and presence of lesions. This study presents an automatic method for liver segmentation from CT scan images based on the convex–concave point for tree structured part model (CCP–TSPM). First, TSPM is utilized as a coarse segmentation tool for capturing the topological shape variation. Then, the proposed CCP is implemented to adjust the position between adjacent points dynamically. As a result, the CCP–TSPM can locate the liver boundary adaptively. Furthermore, color space data provide abundant feature information, which can further improve the method’s effectiveness and efficiency. Finally, the curve is evolved by an iteration level set function to obtain the fine segmentation results. The experimental results show that the proposed method can extract the liver boundary successfully. Furthermore, a comparison of the results with those of the state-of-the-art methods demonstrates the superior performance of the proposed method.

Local binary pattern (LBP) operator offers an efficient way to recognize face under varying illumination, while it has the drawback of abandoning some important texture features. Local multiple patterns (LMP) has alleviated the problem by a hierarchical model. However, the LMP method can bring out the rapid expansion of feature dimension, so a special feature encoding method is adopted by this paper. Meanwhile, we find that the LMP features of different layers can be used to recognize face independently so that it would preserve more abundant recognition information. Most importantly, the contribution of the LMP features from different layers is blurry under varying illumination. We propose a fuzzy framework to fuse the recognition result of different layers and use adaptive weights to calculate contribution rates of different layers under varying illumination. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on four databases such as Yale B, Extended Yale B, CMU PIE and Outdoor.