Depressive disorder has evolved into a major public health issue. However, its diagnosis is predominantly based on subjective clinical evaluation, leading to frequent misdiagnosis. Although multimodal methods have demonstrated potential, they still remain limited in their ability to model long-range temporal dependencies, reconcile semantic heterogeneity across modalities (e.g., facial landmarksvs.gaze behavior), and capture deep inter-modal interactions. To address these challenges, we propose a novel multi-task audiovisual network, termed Bi-CFNet, which is built upon a powerful temporal modeling backbone to capture long-range dependencies and integrates visual enhancement and cross-feedback for depression detection. In addition to the primary binary classification task, we establish a multi-task learning framework to predict item-level clinical scores as an auxiliary task. This design provides supplementary supervisory signals, encouraging the model to learn semantically meaningful representations and mitigate the impact of subjective bias. The visual enhancement module (VEM) employs gated attention to integrate gaze vectors with facial features, yielding temporally aligned and semantically enriched visual representations that are more sensitive to depressive indicators. Furthermore, the cross-feedback mechanism (CFM) facilitates the injection of highlevel semantic features from one modality into the early layers of another, thereby integrating global temporal context into local processing and promoting deep cross-modal re-learning. Finally, extensive experiments on the DAIC-WOZ dataset show that our model achieves an F1-score of 0.85 and a recall of 0.87, surpassing several state-of-the-art trimodal baselines. The proposed framework demonstrates the potential of utilizing audiovisual cues for objective depression analysis, providing a technical foundation for future computer-aided clinical screening systems.

Accurate segmentation of malformed teeth from 3D intraoral scans is critical for computer-aided orthodontic diagnosis. While deep learning-based methods have advanced dental arch segmentation, their performance deteriorates when applied to malformed teeth, often resulting in incomplete shape segmentation and pronounced speckle noise. To address these limitations, we propose IEEnhanceNet, a novel 3D tooth segmentation framework featuring two key innovations: (1) An Implicit Enhancement Module (IEM) that leverages full-arch segmentation data to implicitly constrain the loss function, synergized with an Adaptive Channel Attention mechanism (ACA) to improve morphological feature capture; and (2) An Explicit Enhancement Module (EEM) that introduces architectural-level constraints through an auxiliary full-arch segmentation branch, effectively suppressing noise while enhancing fine-grained accuracy. Specifically, for method validation, we reannotate the 3D-IOSSeg dataset with specialized labels for malformed teeth, normal teeth, and gingiva—the first such effort focused on malformed tooth segmentation. Finally, extensive experiments demonstrate that IEEn-hanceNet achieves state-of-the-art performance, significantly outperforming existing methods in both Overall Accuracy (OA) and Mean Intersection over Union (mIoU) metrics. This work provides a robust computational tool for orthodontic applications involving dental anomalies.

Multi-Camera Multi-Target Tracking (MCMT) aims to achieve robust identity association of objects across cameras under diverse and challenging real-world conditions, such as varying viewpoints and occlusions. Current mainstream approaches often rely on deploying large-scale models with extensive feature extraction capabilities. However, the high computational demands of these models make them impractical for real-world MCMT scenarios where efficiency is critical. To address these challenges, we propose a novel Dual-Retrieval Knowledge Distillation (DRKD) framework, which enhances the student’s feature representation learning by leveraging multi-teacher guidance and dual-retrieval optimization. Unlike traditional knowledge distillation (KD) methods focusing primarily on feature alignment, DRKD introduces the Cross Triplet Loss, which optimizes the feature space for cross-camera identity association by enhancing intra-class compactness and inter-class separability. This dual-retrieval optimization ensures that the student model learns from the teacher’s feature representations and develops strong retrieval capabilities, which are crucial for robust identity association in MCMT. Additionally, we present the Dynamic Feature Fusion (DFF) module, which integrates short-term and historical features to balance the trade-off between responsiveness in single-camera tracking (SCT) and stability in multi-camera tracking (MCT). To further improve adaptability, we design Scene-Aware Regularization, which dynamically adjusts feature contributions in DFF based on temporal gaps and appearance variations. Extensive experiments on the HST and AI City Challenge S02 datasets demonstrate the effectiveness of our approach. The proposed DRKD framework with DFF achieves state-of-the-art performance, with IDF1 scores of 67.13 and MOTA scores of 60.50, while maintaining high inference speeds of up to 62 FPS. These results highlight the ability of DRKD to combine accuracy, robustness, and efficiency, making it a promising solution for real-world MCMT applications.

Multi-view stereo (MVS) reconstruction is a fundamental task in computer vision. While learning-based multi-view stereo methods have demonstrated excellent performance, insufficient attention has been paid to areas with significant depth estimation uncertainty. To address this issue, we propose an attention-enhanced network with probabilistic depth variance refinement for multi-view stereo reconstruction called AE-DR-MVSNet. Specifically, it contains two kernel modules: a diverse attention fusion module(DAFM) and a probability depth variance refinement module(PDVRM). The DAFM is designed by fusing the Bi-Level routing attention and the efficient multi-scale attention to achieve robust multi-scale features. The PDVRM is advanced to enhance depth estimation accuracy and adaptability by dynamically adjusting the depth hypothesis range based on depth distribution variance. Finally, extensive experiments conducted on benchmark datasets, including DTU and Blend-edMVS, demonstrate that AE-DR-MVSNet achieves competitive performance compared to lots of traditional and learning-based methods.

The goal of hashing for image and video retrieval is to encode multimedia data into compact binary codes, allowing for efficient approximate nearest neighbor search by ensuring that similar images or videos have closely related codes in Hamming space. To improve the effectiveness of hashing, we propose introducing a classification task to assist in training the hash network and enhance the discriminability of predicted hash codes. Unlike conventional multi-task learning approaches, we propose a HashNeck structure for the classification branch that utilizes the similarities between the expected and predicted hash codes to determine whether a neuron should participate in the classification task. By only guiding neurons with correctly predicted hash codes through the classification task, we effectively resolve the conflict between the hash and classification tasks. We evaluated the effectiveness of our proposed method on benchmark image and video datasets, including ImageNet100, MS COCO, NUS-WIDE, UCF-101, and HMDB51. The experimental results on image and video retrieval tasks demonstrate that our method outperforms state-of-the-art hashing methods in terms of retrieval performance. These compelling results demonstrate the superiority of our algorithm and its potential for improving the field of deep learning to hashing.

Multi-view stereo (MVS) has emerged as a pivotal algorithm in 3D reconstruction, garnering significant research attention over the past several decades. While recent coarse-to-fine methods have demonstrated promising results in enhancing the reconstruction quality of traditional algorithms, they often neglect the crucial aspect of feature layer refinement. Additionally, these methods face the challenge of low-cost feature matching. To address these limitations, we propose a novel learning-based MVS framework(EE-MVSNet). Firstly, we propose a novel approach incorporating an explicit visual center (EVC) module within the feature pyramid network (FPN), strengthening the adjustment within feature layers and improving model accuracy. Furthermore, we introduce the ECA+3DCNN module, which utilizes channel attention to alleviate the problem of low-cost feature matching. Finally, our model achieves competitive performance through extensive experimentation on the DTU dataset, showcasing its high-quality 3D reconstruction.

Person re-identification is challenging due to the presence of variations in pose and occlusion, which significantly impact the matching of visual features across different camera views and pose considerable difficulty for accurate person re-identification. This paper proposes a novel method for occluded person re-identification by introducing point-level feature learning based on vision transformers. Our approach utilizes a pose estimator to detect the keypoints of the human body and employs these points to locate intermediate features. These intermediate features of keypoints are input to a pose-based transformer branch to learn point-level features. Then, we design a part-based transformer branch to learn part-level features that capture visual features of different image parts, further enhancing the discriminative power of the learned features. Additionally, we employ a global branch to learn the global-level feature by treating the person's image as a single entity. Finally, we integrate point-level, part-level, and global-level features to represent a person's features. The experimental results on occluded and partial person re-identification datasets demonstrate the effectiveness of our proposed approach in improving re-identification. Our approach shows potential for improving person re-identification in scenarios with occlusion and pose variations.

Abstract Logo detection has a wide range of applications in the multimedia field, such as video advertising research, brand awareness monitoring and analysis, trademark infringement detection, autonomous driving and intelligent transportation. Compared with other types of images, logo images in the real world have greater diversity in appearance and more complex backgrounds. Therefore, identifying logos from images is a challenge. A strong baseline method Trinity‐Yolo, is proposed, which incorporates attention mechanism, stripe pooling and weighted boxes fusion (WBF) into the state‐of‐the‐art Yolov4 framework for large‐scale logo detection. The attention mechanism improves the feature extraction ability of the deep detection model, the stripe pooling expands the field of view of the model and the weighted boxes fusion enables the model to obtain excellent corrections when outputting the prediction boxes. Trinity‐Yolo can solve the problems of lack of training data, multi‐scale objects and inconsistent bounding‐box regression. On the dataset LogoDet‐3K, the average performance of Trinity‐Yolo is 3% higher than that of Yolov4. Compared with other deep detection models, the performance of Trinity‐Yolo is improved more. The experimental performance on other existing datasets verifies the effectiveness of this method.

In large-scale natural disasters and special criminal cases, surface features of bodies, such as faces and fingerprints, are easily destroyed. Teeth possess strong high-temperature resistance, corrosion resistance, and high hardness, which can compensate for the shortcomings of the aforementioned situations. This paper proposes an identification method based on the aggregated features of multi-scale dental impression images. Firstly, a method exploiting the adaptive object detection method based on YOLOv8 is proposed to segment toothprints. Next, a novel geometric feature named calibrated offset distance is extracted, combined with the SIFT feature method, to extract multi-scale and multi-dimensional features from the global toothprint, local toothprints, and single-tooth prints. Finally, all features are aggregated to enhance the descriptive ability and robustness. Experimental results indicate that the method proposed in this paper demonstrates good identification performance.

Traditional building identification methods are difficult for extracting the specific information of various buildings. In this paper, A transfer learning method with multi-feature calibration is proposed for building identification. Our model is based on the pre-training and fine-tuning framework of transfer learning. First, a CNN-based feature extractor, pre-trained by ImageNet, is adopted to extract features, then flatten the feature maps and feed it to a fully-connected network for image classification. This basic transfer learning model can correctly identify 81.2% of test samples. Further, a multi-feature calibration method is proposed. By defining the features of multi-functional buildings artificially, the feature vectors via the extractor are more representative and it can be efficiently applied on some small-sample data sets. We use a self-made building data set to test our methods. The experimental results show that the recognition accurate rate of the model with multi-feature calibration attains to 91.9%.

Most existing machine vision‐based location methods mainly focus on the spatial positioning schemes using one or two cameras along with non‐vision sensors. To achieve an accurate location, both schemes require processing a large amount of data. In this study, the authors propose a novel method, which requires much less amount of data to be processed for measuring target distance using monocular vision. Based on the geometric model of camera imaging, the parameters of the camera (such as camera's focal length and equivalent focal length.), as well as the principle of analogue signal being transformed into a digital signal, the authors derive the relationship among the target distance, field of view, equivalent focal length and camera resolution. Experimental results show that the proposed method can effectively and accurately achieve the target distance measurement.

The weighted nuclear norm minimization and truncated nuclear norm minimization are two well-known low-rank constraint for visual applications. In this paper, by integrating their advantages into a unified formulation, we find a better weighting strategy, namely truncated reweighting norm minimization (TRNM), which provides better approximation to the target rank for some specific task. Albeit nonconvex and truncated, we prove that TRNM is equivalent to certain weighted quadratic programming problems, whose global optimum can be accessed by the newly presented reweighting singular value thresholding operator. More importantly, we design a computationally efficient optimization algorithm, namely momentum update and rank propagation (MURP), for the general TRNM regularized problems. The individual advantages of MURP include, first, reducing iterations through nonmonotonic search, and second, mitigating computational cost by reducing the size of target matrix. Furthermore, the descent property and convergence of MURP are proven. Finally, two practical models, i.e., Matrix Completion Problem via TRNM (MCTRNM) and Space Clustering Model via TRNM (SCTRNM), are presented for visual applications. Extensive experimental results show that our methods achieve better performance, both qualitatively and quantitatively, compared with several state-of-the-art algorithms.

Generative Adversarial Network (GAN) has been employed for single image super-resolution (SISR). However, unregularized GAN is difficult for training. This is due gradient descent based GAN optimization is not easy to convergence, thus limiting its performance for image super-resolution. In this paper, a relativistic super-resolution GAN with a simplified gradient penalty (RSRGAN-GP) is proposed for single image super-resolution. In the proposed method, a compact residual network optimized by removing Batch-Normalization layers is employed as the generator to estimate photo-realistic images of 4× upscaling. Further, we introduce a residual network, which also has no Batch-Normalization layers as the conditional discriminator and adopt a simplified gradient regularization to penalize it for stabilizing the super-resolution GAN training, thus guaranteeing high-quality image reconstruction. Additionally, the super-resolution GAN is enhanced with a relativistic discriminator, which produces sharp and rich-detail images at no extra computational cost. The results on benchmark datasets show that our proposed method can effectively improve the visual quality of super-resolved images and achieves competitive performance compared with related works.

With rapid development of the Internet, images are spreading more and more quickly and widely. The phenomenon of image illegal usage emerges frequently, and this has marked impacts on people’s normal life. Therefore, it is of great importance to protect image security and image owner’s rights. At present, most image protection is passive. Most of the time, only when the images had been used illegally and serious adverse consequences had appeared did the image owners discover it. In this paper, a Spark-based real-time proactive image tracking protection model (SRPITP) is proposed to monitor the status of images under protection in real time. Whenever illegal use is found, an alert will be issued to image owners. The model mainly includes image fingerprint extraction module, image crawling module, and image matching module. The experimental results show that in SRPITP, the image matching accuracy rate is above 98.9%, and compared with its stand-alone counterpart, the corresponding time reduction for image extraction and matching are about 58.78% and 61.67%.

Teeth are difficult to be destroyed due to their corrosion resistance, high melting point and hardness. Dental biometrics can therefore provide assistance in human forensic identification, especially to the unknown corpses. One of the key issue in dental based human identification is the segmentation of Dental X‐ray images. In this paper, a novel segmentation algorithm has been proposed for this purpose. The proposed algorithm is based on full threshold segmentation. We first obtain the outline image set Iwhole n and crown image set Icrown m of the complete target tooth. Morphological open operation is then applied to the difference images of Iwhole n and Icrown m . Subsequently, the most complete target tooth image and its corresponding crown image are selected. Getting independent target tooth image I contour and its crown image I crown from these two images. Median filtering is applied to the synthetic image of I contour and I crown , and the resulted image will be used as the Mask for GrabCut to obtain the target tooth image. Experimental results show our proposed algorithm can effectively overcome the problems of uneven grayscale distribution and adhesion of adjacent crowns in dental X‐ray images. It can also achieve a high segmentation accuracy and outperform related methods to be compared.

Automatic data clustering, whose goal is to recover the proper number of clusters as well as appropriate partitioning of data sets, is a fundamental yet challenging problem in unsupervised learning. In this paper, adaptive multisubpopulation competition (AMC) and multiniche crowding are proposed and incorporated into a memetic algorithm to tackle the problem. The AMC mechanism is developed to ensure a diverse search over solution subspaces corresponding to different numbers of clusters while allowing more promising subspaces to be more intensively searched. In this mechanism, the amount of individuals to be migrated between subpopulations is adaptively controlled according to the performance of subpopulations as well as the diversity of cluster numbers in population. Further, the migration is restricted to occur between subpopulations with relatively similar performances. Additionally, subpopulations with different performances are devised to search their corresponding subspaces with different exploration powers. The adaptive multiniche crowding scheme is designed to promote a diverse search of the subspace while allowing an efficient convergence of the corresponding subpopulation. This is achieved by dynamically adjusting parameter values of a multiniche crowding method to form and maintain diverged niches of high fitness within the subpopulation. The performance of proposed algorithm has been demonstrated through a series of experiments on both artificial and real data, and compared with existing methods. The results reveal that our proposed algorithm can achieve superior clustering performance and outperform related methods.

Storing biometric templates and/or encryption keys, as adopted in traditional biometrics-based authentication methods, has raised a matter of serious concern. To address such a concern, biometric key generation, which derives encryption keys directly from statistical features of biometric data, has emerged to be a promising approach. Existing methods of this approach, however, are generally unable to appropriately model user variations, making them difficult to produce consistent and discriminative keys of high entropy for authentication purposes. This paper develops a semisupervised clustering scheme, which is optimized through a niching memetic algorithm, to effectively and simultaneously model both intra- and interuser variations. The developed scheme is employed to model the user variations on both single features and feature subsets with the purpose of recovering a large number of consistent and discriminative feature elements for key generation. Moreover, the scheme is designed to output a large number of clusters, thus further assisting in producing long while consistent and discriminative keys. Based on this scheme, a biometric key generation method is finally proposed. The performance of the proposed method has been evaluated on the biometric modality of handwritten signatures and compared with existing methods. The results show that our method can deliver consistent and discriminative keys of high entropy, outperforming-related methods.

Clustering is deemed one of the most difficult and challenging problems in machine learning. In this paper, we propose a multilocal search and adaptive niching-based genetic algorithm with a consensus criterion for automatic data clustering. The proposed algorithm employs three local searches of different features in a sophisticated manner to efficiently exploit the decision space. Furthermore, we develop an adaptive niching method, which can dynamically adjust its parameter value depending on the problem instance as well as the search progress, and incorporate it into the proposed algorithm. The adaptation strategy is based on a newly devised population diversity index, which can be used to promote both genetic diversity and fitness. Consequently, diverged niches of high fitness can be formed and maintained in the population, making the approach well-suited to effective exploration of the complex decision space of clustering problems. The resulting algorithm has been used to optimize a consensus clustering criterion, which is suggested with the purpose of achieving reliable solutions. To evaluate the proposed algorithm, we have conducted a series of experiments on both synthetic and real data and compared it with other reported methods. The results show that our proposed algorithm can achieve superior performance, outperforming related methods.