• A multi-scale feature fusion feedback module is proposed to refine the local features;.
• The global feature module is developed to obtain a fine global information map;.
• The adaptive feature fusion is proposed to obtain final ...

Surface defect detection (SDD) is the necessary technique to monitor the surface quality of production. However, fine grain defects caused by stress loading, environmental influences, and construction defects is still a challenge to detect. In ...

Online signature parameters, which are based on human characteristics, broaden the applicability of an automatic signature verifier. Although kinematic and dynamic features have previously been suggested, accurately measuring features such as arm ...

Display Omitted

• We explore kinematic and dynamic features for online signature verification.
• A UR5 robotic arm is used to acquire these features from the MCYT330 dataset.
• A neural network estimates the kinematic and dynamic features of a ...

Existing deep learning-based super-resolution generation approaches usually depend on the backbone of convolutional neural networks (CNNs) or Transformers. CNN-based approaches are unable to model long-range dependencies, whereas Transformer-...

• We propose a Mamba-based U-Net network for medical image super-resolution generation.
• We develop the self-prior learning to mine the self-prior information of the image.
• We design improved 2D-Selective-Scan to adaptively fuse multi-...

A component tree is a graph representation that encodes the connected components of the upper or lower level sets of a grayscale image. Consequently, the nodes of a component tree represent binary images of the encoded connected components. There ...

Display Omitted

• Novel incremental contour computation algorithm for component trees.
• Contour computation for component tree time complexity analysis.
• Contour computation for component tree experimental runtime analysis.
• Comparison between ...

Individual differences in organ size and spatial distribution can lead to significant variations in the content of medical images at similar anatomical locations. These case-level differences are distinct from the domain shift between multi-...

• A hybrid attention network is proposed to better model multiscale relationships.
• A meta-learning strategy is designed to achieve better segmentation generalization.
• An individual discriminator is designed to extract individual-...

Neuromorphic sensors, also known as event cameras, are a class of imaging devices mimicking the function of biological visual systems. Unlike traditional frame-based cameras, which capture fixed images at discrete intervals, neuromorphic sensors ...

• Neuromorphic sensors are becoming more common in human-face related vision tasks.
• As a new niche field it lacks overview papers helping researchers orient themselves.
• We compare the relevant literature to classical methods and ...

• Develop a semi-supervised learning framework for breast tumor segmentation, integrating a DIGN network, APMN network, and STA-UNet to leverage labeled and unlabeled data effectively.
• Enhance the STA-UNet encoder with a computationally ...

Accurate segmentation of breast tumors, especially in younger women, remains a significant challenge in cancer research. Ultrasound imaging, a non-invasive screening method, relies on tumor characteristics such as size and texture, which are ...

Underwater images usually show reduced quality due to the underwater environment where light propagation is affected by scattering and absorption, severely limiting the effectiveness of underwater images in practical applications. To effectively ...

• We propose a double mean difference method for color compensation.
• We enhance color distribution by determining the extreme values of color channels.
• Our method can preprocess images with defogging.

• Pioneering cGAN-based technique revolutionizes MRI tumor segmentation accuracy.
• Patch discriminator integration crafts ultra-realistic synthetic MRI datasets.
• Attention-augmented U-Net model dramatically boosts feature-focused ...

Accurate tumor segmentation within MRI images is of great importance for both diagnosis and treatment; however, in many cases, sufficient annotated datasets may not be available. This paper develops a novel approach to the medical image ...

Vision Transformers (ViTs) have demonstrated remarkable performances on various computer vision tasks. Attention scores are often used to explain the decision-making process of ViTs, showing which tokens are more important than others. However, ...

• We propose a novel visual explanation for ViT using a patch-level localization task.
• Our method enhances explainability and localization performance across benchmarks.
• Our method works with pseudo masks from self-supervised ...

Morphological Attribute Profiles serve as powerful tools for extracting meaningful features from remote sensing data. The construction of Morphological Attribute Profiles relies on two primary parameters: the choice of attribute type and the ...

• Adaptive threshold adjustments enhance attribute profile features in remote sensing.
• A semi-automatic method for optimizing attribute profiles in remote sensing data analysis.
• Maximally Stable Extremal Regions theory applied to ...

The domain gap persists as a demanding problem for unsupervised domain adaptive person re-identification (UDA re-ID). In response to this question, we present a novel Sparse self-Attention Augmented Domain Adaptation approach (SAADA Model) to ...

• This method addresses some shortcomings of existing domain adaptation methods.
• This method is a fine-grained solution with better flexibility.
• This approach shows that the sparse self-attention can improve the performance of domain ...

In the near past, a large number of classical intuitively originated dehazing and image enhancing approaches have been worked out, and once played key roles in tremendous practical application scenes. Nevertheless, nowadays, the booming of deep ...

• Universally merging intuitive ideas into deep driven dehazing structure is plausible.
• An adaptive multi-source visual content enhancing framework is designed.
• Multiple structure complexity paths are worked out to fuse various ...

Jigsaw puzzles are a popular and enjoyable pastime that humans can easily solve, even with many pieces. However, solving a jigsaw is a combinatorial problem, and the space of possible solutions is exponential in the number of pieces, intractable ...

• We present new generative modules for estimating the jigsaw solution image.
• We show the effect of estimating the target image for placement of pieces.
• We evaluate on open datasets showing a large margin improvement.

As a fundamental task in computer vision, edge detection is becoming increasingly vital in many fields. Recently, large-parameter pre-training models have been used in edge detection tasks. However, significant computational resources are ...

Display Omitted

• LED-Net improves the edge detection performance while reducing the computational complexity.
• Positional information has been introduced into the edge feature extraction process.
• Feature sample process becomes efficient and ...

Flight maneuver recognition (FMR) refers to automatic recognizing a series of aircraft flight patterns and is a key technology for flight training evaluation. However, the traditional FMR methods generally have higher computational complexity and ...

Display Omitted

• Designed an end-to-end detection framework for flight maneuver recognition (FMR).
• Designed a backbone network tailored for flight data.
• Improved the prediction accuracy of FMR significantly with much lower inference time.

In this work, we propose a novel method for assessing students’ behavioral engagement by representing student’s actions and their frequencies over an arbitrary time interval as a histogram of actions. This histogram and the student’s gaze are ...

• A student dataset is formed with annotated videos for students actions and engagement.
• PoseConv3D model is finetuned to detect student’s actions using upper body joints.
• A novel histogram-based approach is proposed to measure ...

In the rapidly advancing field of industrial automation, the availability of robust and diverse datasets is crucial for the development and evaluation of machine learning models. The data repository consists of four distinct versions of datasets: ...

• MMIFR is a multimodal dataset for industrial equipment related work.
• It includes four components: MMIFR-D, MMIFR-FS, MMIFR-OD, and MMIFR-P.
• Comparative analysis shows MMIFR’s advantages over other industrial datasets.
• Benchmark ...

Detection of depressive symptoms from spoken content has emerged as an efficient Artificial Intelligence (AI) tool for diagnosing this serious mental health condition. Since speech is a highly sensitive form of data, privacy-enhancing measures ...

• First study on how obfuscating speaker attributes impacts depression detection.
• Investigates multimodal depression detection,prior work largely unimodal.
• Results on a clinically validated dataset,unlike prior works using self-...

There are diverse datasets available for training deep learning models utilized in autonomous driving. However, most of these datasets are composed of images obtained in day conditions, leading to a data imbalance issue when dealing with night ...

Display Omitted

• Our novel Y-control loss is proposed to control the brightness degree of the generated night condition images.
• We reduced the artifacts in the generated night condition images by incorporating a self-attention module.
• Addressing ...