Although great progress has been made in Camouflaged Object Detection (COD), it still faces challenges in complex real-world scenes. Existing methods are primarily designed for visible images but face limitations when detecting highly camouflaged or partially occluded objects. Integrating multiple complementary information sources, such as visible images and infrared images, is an effective way to improve the performance of COD. However, research in this field is limited by the lack of comprehensive and high-quality benchmark datasets. To solve this problem, a Visible-Infrared Artificial Camouflage (VIAC) dataset is constructed. Building on this dataset, we propose a novel Visible-Infrared Camouflaged Object Detection (VICOD) framework, termed the Confidence-Guided Fusion and Inpainting Network (CGFINet). The network utilizes a cross-modal collaborative fusion module (CMCF) to achieve adaptive integration of visible and infrared information. Simultaneously, low-confidence regions segmentation boundaries are refined by leveraging high-confidence pixel information within the confidence-driven inpainting module (CDIM). To focus on low-confidence areas, pixel-level uncertainty is incorporated into the loss function as a dynamic weight factor, which prompts the model to focus on high-uncertainty areas. Extensive experiments on VIAC demonstrate that our method achieves state-of-the-art performance, surpassing existing COD and visible-infrared SOD approaches.

There has been an emergence of deep models for multivariate time series forecasting. Transformer-based models and recent linear forecasters are currently battling for the leading position. However, most of them focus on model architectures, while leaving time series data itself underexplored. We argue that not all channels within time series data should share equal importance during the training process since the levels of relevance vary over time. Our goal is to illustrate different levels of contributions made by each channel in time series data via self-influence. To this end, we propose a novel channel reweighting strategy for time series forecasting, IBCR, which employs the ideas of self-influence and clustering to reweigh channels within time series data based on different channel importances. IBCR improves both the explainability of time series data and the predictive performance of baseline models. Extensive experimental results show the reasonability of channel self-influence and the effectiveness of the channel reweighting strategy.

Camouflaged object detection (COD) is a task of identifying and locating target objects that are camouflaged, masked, or confused. Research claims that depth cues can provide effective object location cues. However, depth images often contain noise interference, which may negatively affect object recognition. In addition, depth images also lack edge details, and most of previous works pay more attention to the integrity of the region, rather than the quality of the edge. To solve these two problems, we propose a joint edge and regional depth enhancement network (ERDENet) for Camouflaged Object Detection. The network first introduces the Locate and Generate Depth (LGD) module to locate the target region and generate its depth image. After that, the Feature Interactive Fusion (FIF) module is carried out, complementing the enhanced depth feature with the feature extracted from the original image, and then fuse the edge clues into it. Finally, we design a Muiti-modal Refinement Extraction (MRE) module to refine the feature to improve the detection performance. Extensive experiments show that our method has advantages and effectiveness.

To adapt to the resource-limited environment, this study introduces the lightweight boundary-aware camouflaged object detection(COD) network LMABnet. We enhance the feature representation capability of the lightweight network through a multi-scale feature fusion architecture, while effectively avoids the model inflation and parameter redundancy of traditional COD methods. The LMABnet adopts the streamlined two-branch architecture that incorporates with the lightweight feature extraction module, which provides the multi-scale feature perception capability and reduces the loss of spatial information caused by rapid downsampling. In addition, based on the principle of "easy before difficult", the lightweight multi-scale feature fusion module discovers the key parts of the camouflaged object through the details. Then enhances the recognition of the object edges by using the edge-attention fusion module, so as to improve the accuracy performance of detection. Empirical evaluations conducted on the COD dataset demonstrate that the proposed methodology not only attains state-of-the-art performance but also accomplishes a significant reduction of 40% in parameter count relative to existing approaches.

Non-Intrusive Load Monitoring (NILM) addresses the challenge of disaggregating total energy consumption into individual appliance usage, which is essential for enhancing energy efficiency and managing smart grids. Existing methods often overlook the impact of window sizes on the separation of appliance-level power signals, leading to appliance power aliasing (APA), where a single total power curve corresponds to multiple operating conditions and appliance couplings. A larger window captures global features noise, but it also exacerbates APA, thereby enlarging the solution space. In contrast, a smaller window mitigates APA but it introduces noise and increases complexity. To address these limitations, we propose the Multi-Scale Re-weighted Attention Feature Fusion (MRAFF) model, which employs a multi-scale framework to manage temporal variations and incorporates a re-weighted attention module to enhance multi-scale interactions, thereby improving feature representation. Experimental results demonstrate that our MRAFF model significantly outperforms baseline models on the REDD and UK-DALE datasets, achieving improvements ranging from 2.27% to 10.5% in MAE and from 33.74% to 58.34% in SAE.

Camouflaged Object Detection (COD) is a visual task aimed at identifying objects hidden within their surroundings. Current methods often enhance detection accuracy through boundary structures or uncertainty guidance, but they frequently overlook the identification cues embedded in gradient features. Inspired by the high sensitivity of gradient features to differences between the object and the background, we introduce a novel Gradient-guided Attention Fusion Network (GAFNet) that emphasizes extracting valuable cues by focusing on gradient and high-frequency features of the object. In GAFNet, we propose a Deep Gradient Attention Fusion module (DGAF) to strengthen the response to multi-scale gradient features, utilizing the deep information of gradient features to further refine object localization and identification. Additionally, to globally capture more gradient feature and high-frequency feature cues, we design a High-Frequency Feature Perception module (HFFP) based on a deep residual attention mechanism. Our experimental results on three established COD datasets demonstrate that GAFNet significantly outperforms existing state-of-the-art methods.

Camouflaged Object Detection (COD) has historically been a significant challenge in the field of computer vision. Most existing methods for COD predominantly rely on complex designs to maximize the confidence of foreground regions within spatial features. In contrast, an alternative perspective is that suppressing background distractions to highlight the foreground might be a more effective approach. To address this issue, we propose Distraction Suppression Network, named DSNet. Specifically, Distracion Suppression Module (DSM) is implemented prior to the decoding stage to suppress the distracting information based on the Object-Related Information (ORI) extracted from Object Mining Module (OMM). Then, the Feature Modulation Decoder (FMD) modulates features with varing frequencies and obtains the prediction in a coarse-to-fine way. Experimental results show that our model outperforms existing state-of-the-art models on benchmark datasets by a large margin. Notably, our model maintains its performance even in more complex camouflage scenes.

Scribble-supervised image segmentation holds significant clinical value, notably reducing the labor-intensive annotation process compared to fully supervised alternatives. Presently, existing methodologies in scribble supervision predominantly focus on individual images, neglecting the prevalent clinical practice of referencing multimodal images for a comprehensive assessment of tumors, organs, and related structures. Despite the proven efficacy of utilizing multimodal images in fully supervised medical image segmentation, this advantage remains unexplored in the context of scribble-supervised methodologies, primarily due to the absence of annotated datasets supporting such investigations. In this paper, we address this gap by introducing two scribble-annotated multimodal image datasets, ScribbleBraTS and ScribbleMyoPS, derived from the publicly available BraTS2018 and MyoPS multimodal segmentation datasets, respectively. To further confront this special challenge, we propose a comprehensive framework employing a multi-label training strategy namely SMSeg for scribble-supervised multimodal image segmentation. The framework leverages the segment anything model to generate multiple modality-specific pseudo-labels from diverse modalities and adopt these pseudo-labels as joint-supervision. Extensive experiments validate the effectiveness of our approach, underscoring the potential of scribble-supervised multimodal image segmentation in the medical image segmentation field. The datasets are available at github.

In the biosphere, camouflaged objects take the advantage of visional wholeness by keeping the color and texture of the objects highly consistent with the background, thereby confusing the visual mechanism of other creatures and achieving a concealed effect. This is also the main reason why the task of camouflaged object detection is challenging. In this article, we break the visual wholeness and see through the camouflage from the perspective of matching the appropriate field of view. We propose a matching-recognition-refinement network (MRR-Net), which consists of two key modules, i.e., the visual field matching and recognition module (VFMRM) and the stepwise refinement module (SWRM). In the VFMRM, various feature receptive fields are used to match candidate areas of camouflaged objects of different sizes and shapes and adaptively activate and recognize the approximate area of the real camouflaged object. The SWRM then uses the features extracted by the backbone to gradually refine the camouflaged region obtained by VFMRM, thus yielding the complete camouflaged object. In addition, a more efficient deep supervision method is exploited, making the features from the backbone input into the SWRM more critical and not redundant. Extensive experimental results demonstrate that our MRR-Net runs in real-time (82.6 frames/s) and significantly outperforms 30 state-of-the-art models on three challenging datasets under three standard metrics. Furthermore, MRR-Net is applied to four downstream tasks of camouflaged object segmentation (COS), and the results validate its practical application value. Our code is publicly available at: https://github.com/XinyuYanTJU/MRR-Net.

Few-shot image classification(FSIC) aims to recognize novel classes given few labeled images from base classes. Recent works have achieved promising classification performance, especially for metric-learning methods, where a measure at only image feature level is usually used. In this paper, we argue that measure at such a level may not be effective enough to generalize from base to novel classes when using only a few images. Instead, a multi-level descriptor of an image is taken for consideration in this paper. We propose a multi-level correlation network (MLCN) for FSIC to tackle this problem by effectively capturing local information. Concretely, we present the self-correlation module and cross-correlation module to learn the semantic correspondence relation of local information based on learned representations. Moreover, we propose a pattern-correlation module to capture the pattern of fine-grained images and find relevant structural patterns between base classes and novel classes. Extensive experiments and analysis show the effectiveness of our proposed method on four widely-used FSIC benchmarks.

While saliency detection on static images has been widely studied, the research on video saliency detection is still in an early stage and requires more efforts due to the challenge to bring both local and global consistency of salient objects into full consideration. In this article, we propose a novel dynamic saliency network based on both local consistency and global discriminations, via which semantic features across video frames are simultaneously extracted and a recurrent feature optimization structure is designed to further enhance its performances. To ensure that the generated dynamic salient map is more concentrated, we design a lightweight discriminator with a local consistency loss LC to identify subtle differences between predicted maps and ground truths. As a result, the proposed network can be further stimulated to produce more realistic saliency maps with smoother boundaries and simpler layer transitions. The added LC loss forces the network to pay more attention to the local consistency between continuous saliency maps. Both qualitative and quantitative experiments are carried out on three large datasets, and the results demonstrate that our proposed network not only achieves improved performances but also shows good robustness.

Recent deep learning based salient object detection methods with attention mechanisms have made great success. However, existing attention mechanisms can be generally separated into two categories. One part chooses to calculate weights indiscriminately, which yields computational redundancy. While one part focuses randomly on a small part of the images, such as hard attention, resulting in incorrectness owing to insufficiently targeted selection of a subset of tokens. To alleviate these problems, we design a Curiosity-driven Network (CNet) and a Curiosity-driven Learning Algorithm (CLA) based on fragment attention (FA) mechanism newly defined in this paper. FA imitates the process of cognition perception driven by human curiosity, and divides the degree of curiosity into three levels, i.e. curious, a little curious and not curious. These three levels correspond to five saliency degrees, including salient and non-salient, likewise salient and likewise non-salient, completely uncertain. With more knowledge gained by the network, CLA transforms the curiosity degree of each pixel to yield enhanced detail-enriched saliency maps. In order to extract more context-aware information of potential salient objects and make a better foundation for CLA, a high-level feature extraction module (HFEM) is further proposed. Based on the much better high-level features extracted by HFEM, FA can classify the curiosity degree for each pixel more reasonably and accurately. Extensive experiments on five popular datasets clearly demonstrate that our method outperforms the state-of-the-art approaches without any pre-processing operations or post-processing operations.

Existing saliency detection techniques are sensitive to image quality and perform poorly on degraded images. In this paper, we systematically analyze the current status of the research on detecting salient objects from degraded images and then propose a new multi-type self-attention network, namely MSANet, for degraded saliency detection. The main contributions include: 1) Applying attention transfer learning to promote semantic detail perception and internal feature mining of the target network on degraded images; 2) Developing a multi-type self-attention mechanism to achieve the weight recalculation of multi-scale features. By computing global and local attention scores, we obtain the weighted features of different scales, effectively suppress the interference of noise and redundant information, and achieve a more complete boundary extraction. The proposed MSANet converts low-quality inputs to high-quality saliency maps directly in an end-to-end fashion. Experiments on seven widely-used datasets show that our approach produces good performance on both clear and degraded images.

In recent years, numerous multi-view subspace clustering methods have been proposed to exploit the complementary information from multiple views. Most of them perform data reconstruction within each single view, which makes the subspace representation unpromising and thus can not well identify the underlying relationships among data. In this paper, we propose to conduct subspace clustering based on Flexible Multi-view Representation (FMR) learning, which avoids using partial information for data reconstruction. The latent representation is flexibly constructed by enforcing it to be close to different views, which implicitly makes it more comprehensive and well-adapted to subspace clustering. With the introduction of kernel dependence measure, the latent representation can flexibly encode complementary information from different views and explore nonlinear, high-order correlations among these views. We employ the Alternating Direction Minimization (ADM) method to solve our problem. Empirical studies on real-world datasets show that our method achieves superior clustering performance over other state-of-the-art methods.

Video salient object detection has been attracting more and more research interests recently. However, the definition of salient objects in videos has been controversial all the time, which has become a critical bottleneck in video salient object detection. Specifically, the sequential information contained in videos results in a fact that objects have a relative saliency ranking between each other rather than specific saliency. This implies that simply distinguishing objects into salient or not-salient as usual could not represent the information about saliency comprehensively. To address this issue, 1) in this paper we propose a completely new definition for the salient objects in videos---ranking salient objects, which considers relative saliency ranking assisted with eye fixation points. 2) Based on this definition, a ranking video salient object dataset(RVSOD) is built. 3) Leveraging our RVSOD, a novel neural network called Synthesized Video Saliency Network (SVSNet) is constructed to detect both traditional salient objects and human eye movements in videos. Finally, a ranking saliency module (RSM) takes the results of SVSNet as input to generate the ranking saliency maps. We hope our approach will serve as a baseline and lead to a conceptually new research in the field of video saliency.

Tongue diagnosis is an important concept in Traditional Chinese Medicine (TCM). The tongue colour and coating can aid understanding of the body's physiological mechanisms, as well as the pathology of diseases. Existing research has focused on using digital images and tongue colour classification, without considering the other visible bands of information in the tongue. In this study, a visible hyperspectral image system, with an approximate spectral range of 400–1000 nm, was used to predict the tongue colour values and the coating position in TCM, and a stacked autoencoder (SAE) predict model based on spectral–spatial feature was performed to digital the tongue colour space and the coating. The experimental results show the effectiveness of the spectral–spatial feature with SAE model in predicting the CIELAB values of L , a, and coating position, thus the authors provide a new technique for the objective and digitising development of TCM.

Data-driven saliency detection has attracted strong interest as a result of applying convolutional neural networks to the detection of eye fixations. Although a number of image-based salient object and fixation detection models have been proposed, video fixation detection still requires more exploration. Different from image analysis, motion and temporal information is a crucial factor affecting human attention when viewing video sequences. Although existing models based on local contrast and low-level features have been extensively researched, they failed to simultaneously consider interframe motion and temporal information across neighboring video frames, leading to unsatisfactory performance when handling complex scenes. To this end, we propose a novel and efficient video eye fixation detection model to improve the saliency detection performance. By simulating the memory mechanism and visual attention mechanism of human beings when watching a video, we propose a step-gained fully convolutional network by combining the memory information on the time axis with the motion information on the space axis while storing the saliency information of the current frame. The model is obtained through hierarchical training, which ensures the accuracy of the detection. Extensive experiments in comparison with 11 state-of-the-art methods are carried out, and the results show that our proposed model outperforms all 11 methods across a number of publicly available datasets.

As a crucial challenge for video understanding, exploiting the spatial-temporal structure of video has attracted much attention recently, especially on video captioning. Inspired by the insight that people always focus on certain interested regions of video content, we propose a novel approach which will automatically focus on regions-of-interest and catch their temporal structures. In our approach, we utilize a specific attention model to adaptively select regions-of-interest for each video frame. Then a Dual Memory Recurrent Model (DMRM) is introduced to incorporate temporal structure of global features and regions-of-interest features in parallel, which will obtain rough understanding of video content and particular information of regions-of-interest. Since the attention model could not always catch the right interests, we additionally adopt semantic supervision to attend to interested regions more correctly. We evaluate our method for video captioning on two public benchmarks: the Microsoft Video Description Corpus (MSVD) and the Montreal Video Annotation Dataset (M-VAD). The experiments demonstrate that catching temporal regions-of-interest information really enhances the representation of input videos and our approach obtains the state-of-the-art results on popular evaluation metrics like BLEU-4, CIDEr, and METEOR.

Hyperspectral imaging (HSI) classification has become a popular research topic in recent years, and effective feature extraction is an important step before the classification task. Traditionally, spectral feature extraction techniques are applied to the HSI data cube directly. This paper presents a novel algorithm for HSI feature extraction by exploiting the curvelet-transformed domain via a relatively new spectral feature processing technique—singular spectrum analysis (SSA). Although the wavelet transform has been widely applied for HSI data analysis, the curvelet transform is employed in this paper since it is able to separate image geometric details and background noise effectively. Using the support vector machine classifier, experimental results have shown that features extracted by SSA on curvelet coefficients have better performance in terms of classification accuracy over features extracted on wavelet coefficients. Since the proposed approach mainly relies on SSA for feature extraction on the spectral dimension, it actually belongs to the spectral feature extraction category. Therefore, the proposed method has also been compared with some state-of-the-art spectral feature extraction techniques to show its efficacy. In addition, it has been proven that the proposed method is able to remove the undesirable artifacts introduced during the data acquisition process. By adding an extra spatial postprocessing step to the classified map achieved using the proposed approach, we have shown that the classification performance is comparable with several recent spectral–spatial classification methods.

A novel stroke based sparse hybrid convolutional neural networks (CNNs) method is proposed for author classification of Chinese ink-wash paintings (IWPs). As Chinese IWPs usually have many authors in several art styles, this differs from real images or western paintings and has led to a big challenge. In our work, we classify Chinese IWPs of different artists by analyzing a set of automatically extracted brushstrokes. A sparse hybrid CNNs in a deep-learning framework is then proposed to extract brushstroke features to replace the commonly used handcrafted ones such as edge, color, intensity and texture. Using 120 IWPs from six famous artists, promising results have been shown in successfully classifying authors in comparison to two other state-of-the-art approaches.

As a very recent technique for time-series analysis, singular spectrum analysis (SSA) has been applied in many diverse areas, where an original 1-D signal can be decomposed into a sum of components, including varying trends, oscillations, and noise. Considering pixel-based spectral profiles as 1-D signals, in this letter, SSA has been applied in hyperspectral imaging for effective feature extraction. By removing noisy components in extracting the features, the discriminating ability of the features has been much improved. Experiments show that this SSA approach supersedes the empirical mode decomposition technique from which our work was originally inspired, where improved results in effective data classification using support vector machine are also reported.

Classification of micro calcification clusters is very essential for early detection of breast cancer from mammograms. In this paper, an improved support vector machine (SVM) scheme is proposed, where optimized decision making is introduced for effective and more accurate data classification. Experimental results on the well-known DDSM database have shown that the proposed method can significantly increase the performance in terms of F1 and Az measurements for the successful classification of clustered micro calcifications.