Salient Target Research Articles

Top-down and bottom-up sources of eye-movement guidance during realistic scene search in Alzheimer's disease.

Visual search is a crucial task in daily life, but in Alzheimer's disease (AD) it has usually been investigated using simple arrays. Here, we used scenes depicting real environments and studied the time course of attentional guidance. We analyzed eye-movement differences between mild AD patients and age-matched healthy controls during search. We examined top-down guidance, manipulating the target template (precise picture vs. word cue) and the target-scene semantic consistency (consistent vs. inconsistent), and bottom-up guidance, manipulating the perceptual salience (high vs. low) of targets and distractors. During scene scanning, AD patients had longer search times, made more fixations before the first target fixation, and showed a greater probability of distractor selection, with longer distractor fixation. AD also led to longer target fixation. In patients and controls, picture cues and highly salient targets improved all search phases, whereas consistent targets only improved search initiation (first saccade). Moreover, top-down and bottom-up guidance interacted in initiation and scanning, and this did not differ between the two groups of participants. However, AD led to a smaller picture cue benefit in shortening distractor fixation and greater bottom-up search facilitation during scanning, where a high-salience target reduced the performance gap between patients and controls. Our study shows the importance of top-down and bottom-up guidance, and their integration, in improving search in AD patients. It suggests that precise target cues and, even more, highly salient targets may act as environmental supports that enhance attentional processing and search performance. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Searching for Visual Singletons Without A Feature to Guide Attention.

RT studies have provided evidence for a singleton-detection strategy that is used to search for salient targets when there is no additional featural knowledge that would help guide attention. Despite this behavioral evidence, there have been few ERP studies of singleton detection mode because it was reported early on that the ERP signature of attentional selection (the N2pc) is absent without feature guidance. Recently, however, it was discovered that a small and relatively late N2pc occurs in singleton detection mode along with a previously unreported component called the singleton detection positivity (SDP). Here, we show that both components are influenced by the number of items in the display, as one might expect in a salience-based search mode. Specifically, the N2pc and SDP were larger when the set size was increased to make the singleton "pop out" more easily, when participants responded more quickly regardless of set size, and when RT search slopes were negative (Experiment 1). The latency of the SDP also depended on set size. In Experiment 2, EEG was recorded with a higher density electrode array to better characterize the scalp topography of the components and to estimate their neural sources. Regional sources near the ventral surface of extrastriate cortex in the occipital lobe explained over 96% of N2pc and SDP activities. These results indicate that searching in singleton detection mode selectively modulates processing within perceptual regions of visual cortex.

Target Detection and Segmentation in Circular-Scan Synthetic Aperture Sonar Images Using Semisupervised Convolutional Encoder–Decoders

We propose a framework for saliency-based, multi-target detection and segmentation of circular-scan, synthetic-aperture-sonar (CSAS) imagery. Our framework relies on a multi-branch, convolutional encoder-decoder network (MB-CEDN). The encoder portion of the MB-CEDN extracts visual contrast features from CSAS images. These features are fed into dual decoders that perform pixel-level segmentation to mask targets. Each decoder provides different perspectives as to what constitutes a salient target. These opinions are aggregated and cascaded into a deep-parsing network to refine the segmentation. We evaluate our framework using real-world CSAS imagery consisting of five broad target classes. We compare against existing approaches from the computer-vision literature. We show that our framework outperforms supervised, deep-saliency networks designed for natural imagery. It greatly outperforms unsupervised saliency approaches developed for natural imagery. This illustrates that natural-image-based models may need to be altered to be effective for this imaging-sonar modality.

Saliency Detection of Light Field Images by Fusing Focus Degree and GrabCut

In the light field image saliency detection task, redundant cues are introduced due to computational methods. Inevitably, it leads to the inaccurate boundary segmentation of detection results and the problem of the chain block effect. To tackle this issue, we propose a method for salient object detection (SOD) in light field images that fuses focus and GrabCut. The method improves the light field focus calculation based on the spatial domain by performing secondary blurring processing on the focus image and effectively suppresses the focus information of out-of-focus areas in different focus images. Aiming at the redundancy of focus cues generated by multiple foreground images, we use the optimal single foreground image to generate focus cues. In addition, aiming at the fusion of various cues in the light field in complex scenes, the GrabCut algorithm is combined with the focus cue to guide the generation of color cues, which realizes the automatic saliency target segmentation of the image foreground. Extensive experiments are conducted on the light field dataset to demonstrate that our algorithm can effectively segment the salient target area and background area under the light field image, and the outline of the salient object is clear. Compared with the traditional GrabCut algorithm, the focus degree is used instead of artificial Interactively initialize GrabCut to achieve automatic saliency segmentation.

A Novel RDA-Based Network to Conceal Image Data and Prevent Information Leakage

Image data play an important role in our daily lives, and scholars have recently leveraged deep learning to design steganography networks to conceal and protect image data. However, the complexity of computation and the running speed have been neglected in their model designs, and steganography security still has much room for improvement. For this purpose, this paper proposes an RDA-based network, which can achieve higher security with lower computation complexity and faster running speed. To improve the hidden image’s quality and ensure that the hidden image and cover image are as similar as possible, a residual dense attention (RDA) module was designed to extract significant information from the cover image, thus assisting in reconstructing the salient target of the hidden image. In addition, we propose an activation removal strategy (ARS) to avoid undermining the fidelity of low-level features and to preserve more of the raw information from the input cover image and the secret image, which significantly boosts the concealing and revealing performance. Furthermore, to enable comprehensive supervision for the concealing and revealing processes, a mixed loss function was designed, which effectively improved the hidden image’s visual quality and enhanced the imperceptibility of secret content. Extensive experiments were conducted to verify the effectiveness and superiority of the proposed approach.

Infrared-Visible Image Fusion Based on Semantic Guidance and Visual Perception

Infrared-visible fusion has great potential in night-vision enhancement for intelligent vehicles. The fusion performance depends on fusion rules that balance target saliency and visual perception. However, most existing methods do not have explicit and effective rules, which leads to the poor contrast and saliency of the target. In this paper, we propose the SGVPGAN, an adversarial framework for high-quality infrared-visible image fusion, which consists of an infrared-visible image fusion network based on Adversarial Semantic Guidance (ASG) and Adversarial Visual Perception (AVP) modules. Specifically, the ASG module transfers the semantics of the target and background to the fusion process for target highlighting. The AVP module analyzes the visual features from the global structure and local details of the visible and fusion images and then guides the fusion network to adaptively generate a weight map of signal completion so that the resulting fusion images possess a natural and visible appearance. We construct a joint distribution function between the fusion images and the corresponding semantics and use the discriminator to improve the fusion performance in terms of natural appearance and target saliency. Experimental results demonstrate that our proposed ASG and AVP modules can effectively guide the image-fusion process by selectively preserving the details in visible images and the salient information of targets in infrared images. The SGVPGAN exhibits significant improvements over other fusion methods.

Exploration and Application of Graphic Design Language Based on Artificial Intelligence Visual Communication

Graphic design is one of the design disciplines with the longest history in the history of human design. As a marginal discipline, it integrates science and art organically. Graphic design has three basic characteristics: information, art, and economy. Information refers to the fact that graphic design is a carrier of information communication, and graphic design works have the practical function of specific information transmission. Among them, graphic design language is the direct form of information communication, but there is a relative lack of research on the intelligent recognition of graphic design language. To address this problem, this paper focuses on the analysis method of graphic design language based on artificial intelligence visual communication. First, in order to segment different parts of the image more accurately, this paper improves a deep learning-based image segmentation method. The method uses a three-branch network structure to learn semantic information, detail information, and fusion information, respectively. The coding network uses a lightweight convolutional neural network and adds an attention mechanism in the branches to weight the importance of image feature channels, and the features extracted from different perceptual fields of the image are multiscale fused to fuse the features extracted from different stages of the coding network. Then, the salient target regions are detected on the basis of segmented images, the salient target emotions are analyzed by using feature pyramids to improve the convolutional neural network, the emotions expressed by graphic design language are analyzed by constructing a weighted loss convolutional neural network on a multilayer supervised module, and the salient target emotions are fused to obtain the final emotion classification results. The experimental results show that our proposed method outperforms traditional segmentation methods in the dataset, and the sentiment analysis based on segmented images can obtain higher sentiment classification accuracy than the sentiment analysis method that directly identifies the whole image, which is beneficial to the research and application of graphic design language.

Infrared and low-light visible image fusion based on hybrid multiscale decomposition and adaptive light adjustment

Most traditional infrared and visible image fusion methods often ignore weak texture details, especially for the low-light visible images in which the weak details are easily drowned due to noise or ill-illumination. To address this problem, we propose a novel infrared and low-light visible image fusion method from the perspective of low-light visible image enhancement, weak feature extraction strategy and detail preserved fusion rules. By combining both local and global contrast enhancements, an adaptive light adjustment algorithm is proposed to improve the brightness and texture details of low-light visible images. In addition, we design a hybrid multiscale decomposition model based on guided filters (GFs) and side window guided filters (SWGFs) to decompose the source images into the base layer, large-scale detail layers and small-scale detail layers. The three layers reflects the background, large edge structures and weak texture details of source images respectively. Subsequently, the visual saliency retention, normalized arctan function, and edge preservation-based consistency verification are applied to highlight salient targets and retain weak details for three layers fusion. Qualitative and quantitative experimental results on publicly available datasets prove the superiority of our method over state-of-the-art methods in terms of highlight salient targets, avoiding edge blurring, and retaining weak details.

An Enhanced Steganography Network for Concealing and Protecting Secret Image Data.

The development of Internet technology has provided great convenience for data transmission and sharing, but it also brings serious security problems that are related to data protection. As is detailed in this paper, an enhanced steganography network was designed to protect secret image data that contains private or confidential information; this network consists of a concealing network and a revealing network in order to achieve image embedding and recovery separately. To reduce the system’s computation complexity, we constructed the network’s framework using a down–up structure in order to compress the intermediate feature maps. In order to mitigate the input’s information loss caused by a sequence of convolution blocks, the long skip concatenation method was designed to pass the raw information to the top layer, thus synthesizing high-quality hidden images with fine texture details. In addition, we propose a novel strategy called non-activated feature fusion (NAFF), which is designed to provide stronger supervision for synthetizing higher-quality hidden images and recovered images. In order to further boost the hidden image’s visual quality and enhance its imperceptibility, an attention mechanism-based enhanced module was designed to reconstruct and enhance the salient target, thus covering up and obscuring the embedded secret content. Furthermore, a hybrid loss function that is composed of pixel domain loss and structure domain loss was designed to boost the hidden image’s structural quality and visual security. Our experimental results demonstrate that, due to the elaborate design of the network structure and loss function, our proposed method achieves high levels of imperceptibility and security.

Testing the effect of display organization in the collinear search impairment.

Previous studies established that a salient collinear structure impairs local visual search. A display organization hypothesis states that the vertical grouping of elemental bars in the search display may selectively increase the salience of the local target in the background than that in the collinear distractor, leading to the collinear search impairment. Three displays were designed to test this hypothesis. A classical search display was adopted as a baseline. A diagonal search display was created with tilted bars, making perceptual organization diagonal and should reduce collinear search impairment. An illusory search display was designed by using abutting line illusion to emphasize the vertical grouping direction, which should increase collinear search impairment. A manipulation check was conducted with an online survey to understand the perceptual organization of the three displays. Results showed that the probability to perceive the stimuli grouping in the vertical direction was strongest in the illusory display and the least in the diagonal display. Nevertheless, the collinear search impairment did not vary with these manipulations, argue against the display organization hypothesis. We speculate that the search impairment might associate with the perceptual organization of the collinear distractor per se, rather than the perceptual organization of the background.

TIPFNet: a transformer-based infrared polarization image fusion network

The fusion of infrared intensity and polarization images can generate a single image with better visible perception and more vital information. Existing fusion methods based on a convolutional neural network (CNN), with local feature extraction, have the limitation of fully exploiting salient target features of polarization. In this Letter, we propose a transformer-based deep network to improve the performance of infrared polarization image fusion. Compared with existing CNN-based methods, our model can encode long-range features of infrared polarization images to obtain global contextual information using the self-attention mechanism. We also design a loss function with the self-supervised constraint to boost the performance of fusion. Experiments on the public infrared polarization dataset validate the effectiveness of the proposed method. Our approach achieves better fusion performance than the state-of-the-art.

Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes.

Thermal imaging is an important technology in low-visibility environments, and due to the blurred edges and low contrast of infrared images, enhancement processing is of vital importance. However, to some extent, the existing enhancement algorithms based on pixel-level information ignore the salient feature of targets, the temperature which effectively separates the targets by their color. Therefore, based on the temperature and pixel features of infrared images, first, a threshold denoising model based on wavelet transformation with bilateral filtering (WTBF) was proposed. Second, our group proposed a salient components enhancement method based on a multi-scale retinex algorithm combined with frequency-tuned salient region extraction (MSRFT). Third, the image contrast and noise distribution were improved by using salient features of orientation, color, and illuminance of night or snow targets. Finally, the accuracy of the bounding box of enhanced images was tested by the pre-trained and improved object detector. The results show that the improved method can reach an accuracy of 90% of snow targets, and the average precision of car and people categories improved in four low-visibility scenes, which demonstrates the high accuracy and adaptability of the proposed methods of great significance for target detection, trajectory tracking, and danger warning of automobile driving.

Concealed multiscale feature extraction network for automatic four-bar target detection in infrared imaging

The measurement of the minimum temperature difference (MTD) at which a four-bar target can be resolved is an important task for assessing the performance of infrared imaging equipment. Recently, there have been efforts to use an automatic objective approach based on machine learning to replace the classical manual subjective MTD measurement approach, which is heavily influenced by the psychological subjective factors of the operator and is limited in accuracy and processing speed. However, the scale variability of the four-bar targets and the high intrinsic target-background similarity in infrared images have been observed to present a challenging problem for automatic MTD measurement. We present a concealed multiscale feature extraction network (CMF-Net), a backbone for automatic multiscale four-bar target detections, in an attempt to address the aforementioned challenges. We first propose a multilevel feature pyramid module to construct a robust representation of multiscale four-bar targets. Next, to distinguish between the four-bar targets from the background, a target saliency enhancement module (TSE) is introduced to capture discriminative features about the target by encoding local and global contextual information. Experiments show that the proposed method is effective and achieves state-of-the-art four-bar target detection results on infrared-image dataset compared with existing methods.

Effect of the COVID-19 Pandemic on Stimulant Use and Antiretroviral Therapy Adherence Among Men Who Have Sex With Men Living With HIV: Qualitative Focus Group Study.

BackgroundEvidence suggests that economic, social, and psychological circumstances brought about by the COVID-19 pandemic may have a serious impact on behavioral health. Men who have sex with men (MSM) are disproportionally impacted by HIV and stimulant use, the co-occurrence of which heightens HIV transmission risk and undermines nationwide treatment strategies as prevention efforts for ending the HIV epidemic. There is a paucity of information regarding the potential impact of the COVID-19 pandemic on the substance use and HIV medication adherence in this key vulnerable population—MSM who use stimulants and are living with HIV.ObjectiveThe aim of this qualitative study was to identify ways in which the COVID-19 pandemic has affected stimulant use and antiretroviral therapy (ART) adherence among a sample of MSM living with HIV.MethodsTwo focus groups were conducted in August 2020 via videoconferencing technology compliant with the Health Insurance Portability and Accountability Act. Potential participants from an established research participant registry at State University of New York Downstate Health Sciences University were invited and screened for study participation on the basis of inclusion criteria. A semistructured interview guide was followed. A general inductive approach was used to analyze the data. Findings in two general areas of interest, the impact of the COVID-19 pandemic on stimulant use and ART adherence, emerged directly from the raw data.ResultsA total of 12 ethnically diverse participants over the age of 25 years took part in the study. Results were heterogeneous in terms of the effects of the pandemic on both stimulant use and ART adherence among MSM living with HIV. Some men indicated increased or sustained stimulant use and ART adherence, and others reported decreased stimulant use and ART adherence. Reasons for these behavioral changes ranged from concerns about their own health and that of their loved ones to challenges brought about by the lack of daily structure during the lockdown phase of the pandemic and emotion regulation difficulties.ConclusionsThe COVID-19 pandemic has had a differential impact on stimulant use and ART medication adherence among MSM living with HIV. The reasons for behavioral change identified in this study may be salient intervention targets to support ART medication adherence and lower stimulant use among MSM in the aftermath of the of the COVID-19 pandemic, as well as beyond.

A Multi-Stage Visible and Infrared Image Fusion Network Based on Attention Mechanism.

Pixel-level image fusion is an effective way to fully exploit the rich texture information of visible images and the salient target characteristics of infrared images. With the development of deep learning technology in recent years, the image fusion algorithm based on this method has also achieved great success. However, owing to the lack of sufficient and reliable paired data and a nonexistent ideal fusion result as supervision, it is difficult to design a precise network training mode. Moreover, the manual fusion strategy has difficulty ensuring the full use of information, which easily causes redundancy and omittance. To solve the above problems, this paper proposes a multi-stage visible and infrared image fusion network based on an attention mechanism (MSFAM). Our method stabilizes the training process through multi-stage training and enhances features by the learning attention fusion block. To improve the network effect, we further design a Semantic Constraint module and Push–Pull loss function for the fusion task. Compared with several recently used methods, the qualitative comparison intuitively shows more beautiful and natural fusion results by our model with a stronger applicability. For quantitative experiments, MSFAM achieves the best results in three of the six frequently used metrics in fusion tasks, while other methods only obtain good scores on a single metric or a few metrics. Besides, a commonly used high-level semantic task, i.e., object detection, is used to prove its greater benefits for downstream tasks compared with single-light images and fusion results by existing methods. All these experiments prove the superiority and effectiveness of our algorithm.

Salient object detection with image-level binary supervision

Recent deep learning based salient object detection (SOD) methods have achieved impressive performance. However, while fully-supervised methods require a large amount of labeled data, weakly-supervised methods still require a considerable human effort. To address this problem, we propose a novel weakly-supervised method for salient object detection based on only binary image tags, which are much cheaper to collect. Our basic idea is to construct a dataset of images that are labeled as either salient (with salient objects) or non-salient (without salient objects), and leverage such binary labels as supervision to learn a salient object detector based on existing unsupervised methods. In particular, we propose a target saliency map hallucinator, which can synthesize pseudo ground truth saliency maps for the salient images in the training data solely from binary labels. We can then use the pseudo ground truth labels to train a salient object detector. Experimental results show that our method performs comparably to the state-of-the-art weakly-supervised methods, but requires considerably less human supervision.

Real-Time Event-Based Unsupervised Feature Consolidation and Tracking for Space Situational Awareness.

Earth orbit is a limited natural resource that hosts a vast range of vital space-based systems that support the international community's national, commercial and defence interests. This resource is rapidly becoming depleted with over-crowding in high demand orbital slots and a growing presence of space debris. We propose the Fast Iterative Extraction of Salient targets for Tracking Asynchronously (FIESTA) algorithm as a robust, real-time and reactive approach to optical Space Situational Awareness (SSA) using Event-Based Cameras (EBCs) to detect, localize, and track Resident Space Objects (RSOs) accurately and timely. We address the challenges of the asynchronous nature and high temporal resolution output of the EBC accurately, unsupervised and with few tune-able parameters using concepts established in the neuromorphic and conventional tracking literature. We show this algorithm is capable of highly accurate in-frame RSO velocity estimation and average sub-pixel localization in a simulated test environment to distinguish the capabilities of the EBC and optical setup from the proposed tracking system. This work is a fundamental step toward accurate end-to-end real-time optical event-based SSA, and developing the foundation for robust closed-form tracking evaluated using standardized tracking metrics.

Microglial GPR56 is the molecular target of maternal immune activation-induced parvalbumin-positive interneuron deficits.

Parvalbumin-positive (PV+) interneurons play a critical role in maintaining circuit rhythm in the brain, and their reduction is implicated in autism spectrum disorders. Animal studies demonstrate that maternal immune activation (MIA) leads to reduced PV+ interneurons in the somatosensory cortex and autism-like behaviors. However, the underlying molecular mechanisms remain largely unknown. Here, we show that MIA down-regulates microglial Gpr56 expression in fetal brains in an interleukin-17a–dependent manner and that conditional deletion of microglial Gpr56 [Gpr56 conditional knockout (cKO)] mimics MIA-induced PV+ interneuron defects and autism-like behaviors in offspring. We further demonstrate that elevated microglial tumor necrosis factor–α expression is the underlying mechanism by which MIA and Gpr56 cKO impair interneuron generation. Genetically restoring Gpr56 expression in microglia ameliorates PV+ interneuron deficits and autism-like behaviors in MIA offspring. Together, our study demonstrates that microglial GPR56 plays an important role in PV+ interneuron development and serves as a salient target of MIA-induced neurodevelopmental disorders.

PoVRPoint: Authoring Presentations in Mobile Virtual Reality.

Virtual Reality (VR) has the potential to support mobile knowledge workers by complementing traditional input devices with a large three-dimensional output space and spatial input. Previous research on supporting VR knowledge work explored domains such as text entry using physical keyboards and spreadsheet interaction using combined pen and touch input. Inspired by such work, this paper probes the VR design space for authoring presentations in mobile settings. We propose PoVRPoint-a set of tools coupling pen- and touch-based editing of presentations on mobile devices, such as tablets, with the interaction capabilities afforded by VR. We study the utility of extended display space to, for example, assist users in identifying target slides, supporting spatial manipulation of objects on a slide, creating animations, and facilitating arrangements of multiple, possibly occluded shapes or objects. Among other things, our results indicate that 1) the wide field of view afforded by VR results in significantly faster target slide identification times compared to a tablet-only interface for visually salient targets; and 2) the three-dimensional view in VR enables significantly faster object reordering in the presence of occlusion compared to two baseline interfaces. A user study further confirmed that the interaction techniques were found to be usable and enjoyable.

Dynamic causal interactions between occipital and parietal cortex explain how endogenous spatial attention and stimulus-driven salience jointly shape the distribution of processing priorities in 2D visual space

Visuo-spatial attention prioritizes the processing of relevant inputs via different types of signals, including current goals and stimulus salience. Complex mixtures of these signals engage in everyday life situations, but little is known about how these signals jointly modulate distributed patterns of activity across the occipital regions that represent visual space. Here, we measured spatio-topic, quadrant-specific occipital activity during the processing of visual displays containing both task-relevant targets and salient color-singletons. We computed spatial bias vectors indexing the effect of attention in 2D space, as coded by distributed activity in the occipital cortex. We found that goal-directed spatial attention biased activity towards the target and that salience further modulated this endogenous effect: salient distractors decreased the spatial bias, while salient targets increased it. Analyses of effective connectivity revealed that the processing of salient distractors relied on the modulation of the bidirectional connectivity between the occipital and the posterior parietal cortex, as well as the modulation of the lateral interactions within the occipital cortex. These findings demonstrate that goal-directed attention and salience jointly contribute to shaping processing priorities in the occipital cortex and highlight that multiple functional paths determine how spatial information about these signals is distributed across occipital regions.