Discriminant Saliency Research Articles

All Stressors Are Not Equal: The Salience of Racial Discrimination and Appraisal for Blood Pressure in African American Women.

Psychosocial stress is a major predictor of chronic disease among African American (AA) women. Stress is a process involving exposure, appraisal of threat, coping, and psychobiologic adaptation. However, many studies focus on the frequency of stress events and/or coping; few explicitly study stress events and their appraisals; and AA women experience high levels of racial discrimination, a well-known form of social identity threat (i.e., negative experiences due to judgment based on identity). Stressors related to social identity threat may be differentially appraised and associated with divergent physiologic outcomes. This study examined the differences in the frequency and stressfulness associated with general stressors and racial discrimination in relation to blood pressure (BP) among AA women. Multivariable regression was used on cross-sectional data from 208 middle-aged AA women residing in the San Francisco Bay Area. AA women reported less frequency of racial discrimination compared with general stressors, but were more likely to appraise racial discrimination events as stressful. Racial discrimination stressfulness was more strongly associated with systolic BP (SBP) than the number of racial discrimination events. There was a U-shaped association between racial discrimination stress and SBP, with those reporting "none" and "high/very high" distress having the highest SBP ( b = 12.2 [2.7 to 21.8] and b = 15.7 [1.5-29.8], respectively, versus moderate stress). Conversely, those reporting "very low" general stressfulness had the lowest SBP ( b = -7.9 [-15.8 to -0.1], versus moderate stress). Diastolic BP followed a similar pattern, although results were nonsignificant. This study highlights the importance of stress appraisal measures and adds to the body of evidence documenting racial discrimination as a salient psychosocial stressor for AA women.

(Not) Discussing Race, via Books, in Mainly White Preschools

ABSTRACT This mixed-methods study investigated how two White preschool teachers, who were familiar with anti-bias pedagogy but had low training on anti-racist teaching strategies, discussed race and racism, using books, in two predominantly White classrooms. Teachers were observed in two classrooms, during book discussions with children, and teachers’ racial attitudes were assessed via two survey measures. The book discussions were audio-recorded and transcribed. Teachers discussed skin, hair, and eye color, and avoided naming “race” or “racism.” Teachers placed racial discrimination on the same footing as other physical differences, decreasing the significance of racism and racial discrimination. There was silence surrounding race, both from the White teachers and primarily White children. The teachers focused on encouraging children to accept all differences and minimized the salience of race, racism, and racial discrimination. Despite reporting race-conscious attitudes on the survey measures, the teachers struggled to discuss race and racism with young children in the actual classrooms. Implications are discussed for teacher professional development.

Hate as a system: Examining hate crimes and hate groups as state level moderators on the impact of online and offline racism on mental health

The rise in race-based hate crimes and groups should not only be examined as an individual- or group-level issue but as indicators that reflect state-level norms of hate and degradation toward racial minority groups. Specifically, for racial minority individuals residing in states that yield higher rates of hate crimes and groups, this may reflect a greater hate culture, and the distress associated with racism may be exacerbated, compared to those residing in states with less of a hate culture (e.g., lower numbers of hate crimes and groups). Thus, to test these assertions, we examined whether state-level indicators of race-based hate crimes and groups would moderate the relationship between perceived racism (offline and online) and stress among racial minority individuals. Using data from 935 racial minority adults across 43 states, a multilevel analysis was conducted with online and offline racism predicting distress at level 1, and the total number of hate crimes and groups moderating this relationship at level 2 (state-level). Between hate crimes and groups, only hate groups was a significant indicator moderating this link. In states with a low number of hate groups, the link between offline racism and stress was not significant while this link was significant in states with a high number of hate groups. Online racism was significantly associated with stress, but this link was not moderated by any of the hate indicators. The findings suggest that the presence and activity of hate groups may be a significant contextual factor in understanding the salience of racial discrimination. Implications for research are discussed.

Sexual Orientation Discrimination and Exclusive, Dual, and Polytobacco Use among Sexual Minority Adults in the United States.

Research on whether sexual orientation discrimination is associated with multiple tobacco product use among sexual minority (SM) adults is limited. Thus, we explored the associations between sexual orientation discrimination and exclusive, dual, and polyuse among a subset of SM adults (18+) (n = 3453) using the 2012–2013 National Epidemiologic Survey on Alcohol and Related Conditions-III. We evaluated six indicators of prior-to-past-year sexual orientation discrimination separately and as a summary scale and defined past-year exclusive, dual, and polyuse based on cigarette, electronic nicotine delivery systems, other combustible (cigars and traditional pipe), and smokeless tobacco products. Using multinomial logistic regression, we estimated adjusted associations between sexual orientation discrimination and exclusive, dual, and polyuse. Experiencing discrimination in public places, being called names, and being bullied, assaulted, or threatened were associated with dual use, while experiencing discrimination when obtaining health care or insurance and when receiving health care were associated with polyuse. Each one-unit increase in the sexual orientation discrimination summary scale was associated with 5% and 10% higher odds of dual (95% CI: 1.01–1.10) and polyuse (95% CI: 1.02–1.18), respectively. To conclude, we advise health professionals to consider the salience of discrimination against SM adults and how these experiences lead to dual/polyuse.

Handwritten Annotation Spotting in Printed Documents Using Top-Down Visual Saliency Models

In this article, we address the problem of localizing text and symbolic annotations on the scanned image of a printed document. Previous approaches have considered the task of annotation extraction as binary classification into printed and handwritten text. In this work, we further subcategorize the annotations as underlines, encirclements, inline text, and marginal text. We have collected a new dataset of 300 documents constituting all classes of annotations marked around or in-between printed text. Using the dataset as a benchmark, we report the results of two saliency formulations—CRF Saliency and Discriminant Saliency, for predicting salient patches, which can correspond to different types of annotations. We also compare our work with recent semantic segmentation techniques using deep models. Our analysis shows that Discriminant Saliency can be considered as the preferred approach for fast localization of patches containing different types of annotations. The saliency models were learned on a small dataset, but still, give comparable performance to the deep networks for pixel-level semantic segmentation. We show that saliency-based methods give better outcomes with limited annotated data compared to more sophisticated segmentation techniques that require a large training set to learn the model.

Implication of stigmatization on investors financial risk tolerance: The case of gay men

This study evaluates whether the salience of discrimination and perceived stigmatization influence gay men’s financial risk tolerance (FRT). This evaluation is conducted using the FRT measure of Grable and Lytton (1999), a “two-study ruse” approach and a hierarchical linear regression model. The findings show that individuals with anticipated stigmatization, after being exposed to information about bias against their community, exhibited greater FRT. These results support the hypothesis that risk-taking behavior by members of stigmatized populations increases when they experience discrimination.

Geometry Auxiliary Salient Object Detection for Light Fields via Graph Neural Networks.

Light field imaging, originated from the availability of light field capture technology, offers a wide range of applications in the field of computational vision. The capability of predicting salient objects of light fields remains technologically challenging due to its complicated geometry structure. In this paper, we propose a light field salient object detection approach that formulates the geometric coherence among multiple views of light fields as graphs, where the angular/central views represent the nodes and their relations compose the edges. The spatial and disparity correlations between multiple views are effectively explored through multi-scale graph neural networks, enabling the more comprehensive understanding of light field content and more representative and discriminative saliency features generation. Moreover, a multi-scale saliency feature consistency learning module is embedded to enhance the saliency features. Finally, an accurate salient object map is produced for the light field based upon the extracted features. In addition, we establish a new light field salient object detection dataset (CITYU-Lytro) that contains 817 light fields with diverse contents and their corresponding annotations, aiming to further promote the research on light field salient object detection. Quantitative and qualitative experiments demonstrate that the proposed method performs favorably compared with the state-of-the-art methods on the benchmark datasets.

New Contour Cue-Based Hybrid Sparse Learning for Salient Object Detection.

Saliency detection is a hot topic in recent years and much efforts have been made to address it from different perspectives. However, current saliency models cannot meet the needs for diversified scenes due to their limited generalization capability. To tackle this problem, in this paper, we propose a hybrid saliency model, which can fuse heterogeneous visual cues for robust salient object detection. A new contour cue is first introduced to provide discriminative saliency information for scene description. Its realization is based on a discrete optimization objective and can be solved efficiently with an iterative algorithm. Followed by this, the contour cue is taken as a part of a hybrid sparse learning model, in which cues from different domains can interact and complement with each other for joint saliency fusion. This saliency fusion model is parameter-free and its numerical solution can be obtained using gradient descent methods. Finally, we advance an object proposal-based collaborative filtering strategy to generate high quality saliency maps from the above fusion results. Compared with traditional methods, the proposed saliency model can fuse heterogeneous cues in a unified optimization framework rather than combine them separately. Therefore, it has favorable modeling capability under diversified scenes where the saliency patterns appear quite differently. To verify the effectiveness of the proposed method, we take experiments on four large saliency benchmark datasets and compare it with other 26 state-of-the-art saliency models. Both qualitative and quantitative evaluation results indicate the superiority of our method, especially in challenging situations. Besides, we apply our saliency model to ship detection of radar platforms and promising results are obtained over traditional detectors.

Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps

In this paper, we propose a novel effective non-rigid object tracking framework based on the spatial-temporal consistent saliency detection. In contrast to most existing trackers that utilize a bounding box to specify the tracked target, the proposed framework can extract accurate regions of the target as tracking outputs. It achieves a better description of the non-rigid objects and reduces the background pollution for the tracking model. Furthermore, our model has several unique characteristics. First, a tailored fully convolutional neural network (TFCN) is developed to model the local saliency prior for a given image region, which not only provides the pixel-wise outputs but also integrates the semantic information. Second, a novel multi-scale multi-region mechanism is proposed to generate local saliency maps that effectively consider visual perceptions with different spatial layouts and scale variations. Subsequently, the local saliency maps are fused via a weighted entropy method, resulting in a discriminative saliency map. Finally, we present a non-rigid object tracking algorithm based on the predicted saliency maps. By utilizing a spatial-temporal consistent saliency map (STCSM), we conduct the target-background classification and use an online fine-tuning scheme for model updating. Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets. Source codes and compared results are released at https://github.com/Pchank/TFCNTracker.

Exploiting background divergence and foreground compactness for salient object detection

In this paper, we propose an efficient and discriminative saliency method that takes advantage of background divergence and foreground compactness. Concretely, a graph is first constructed by introducing the concept of virtual node to effectively enhance the distinction between nodes along object boundaries and the similarity among object regions. A reasonable edge weight is defined by incorporating low-level features as well as deep features extracted from deep networks to measure the relationship between different regions. To remove incorrect outputs, two computational mechanisms are then developed to extract reliable background seeds and compact foreground regions, respectively. The saliency value of a node is calculated by fully considering the relationship between the corresponding node and the virtual background (foreground) node. As a result, two types of saliency maps are obtained and integrated into a uniform map. In order to achieve significant performance improvement consistently, we propose a robust saliency optimization mechanism, which subtly combine suppressed/active (SA) nodes and mid-level structure information based on manifold ranking. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-art saliency detection methods in terms of different evaluation metrics on several benchmark datasets.

Multi-scale deep encoder-decoder network for salient object detection

Abstract Deep convolutional neural networks (CNNs) have recently made revolutionary improvements in salient object detection. However, most existing CNN-based models fail to precisely separate the whole salient object(s) from a cluttered background due to the downsampling effects or the patch-level operation. In this paper, we propose a multi-scale deep encoder-decoder network which learns discriminative saliency cues and computes confidence scores in an end-to-end fashion. The encoder network extracts meaningful and informative features in a global view, and the decoder network recovers lost detailed object structure in a local perspective. By taking multiple resized images as the inputs, the proposed model incorporates multi-scale features from a shared network and predicts a fine-grained saliency map at the pixel level. To easily and efficiently train the whole network, the light-weighted decoder breaks through the limit of conventional symmetric structure. In addition, a two-stage training strategy is designed to encourage the robustness and accuracy of the network. Without any post-processing steps, our method is capable of significantly reducing the computation complexity while densely segmenting foreground objects from an image. Extensive experiments on six challenging datasets demonstrate that the proposed model outperforms other state-of-the-art approaches in terms of various evaluation metrics.

Video Saliency Detection Using Object Proposals.

In this paper, we introduce a novel approach to identify salient object regions in videos via object proposals. The core idea is to solve the saliency detection problem by ranking and selecting the salient proposals based on object-level saliency cues. Object proposals offer a more complete and high-level representation, which naturally caters to the needs of salient object detection. As well as introducing this novel solution for video salient object detection, we reorganize various discriminative saliency cues and traditional saliency assumptions on object proposals. With object candidates, a proposal ranking and voting scheme, based on various object-level saliency cues, is designed to screen out nonsalient parts, select salient object regions, and to infer an initial saliency estimate. Then a saliency optimization process that considers temporal consistency and appearance differences between salient and nonsalient regions is used to refine the initial saliency estimates. Our experiments on public datasets (SegTrackV2, Freiburg-Berkeley Motion Segmentation Dataset, and Densely Annotated Video Segmentation) validate the effectiveness, and the proposed method produces significant improvements over state-of-the-art algorithms.

Racial inequality and the recognition of racial discrimination in Jamaica

ABSTRACTA growing body of literature posits that a population’s denial of the salience of racial discrimination acts as a mechanism of its perpetuation. Moreover, scholars locate a population’s propensity to deny racial discrimination in contemporary ideologies of racial mixing or ethnic fusion. Most quantitative studies of public opinion on these issues are limited to Latin America and the Spanish-speaking Caribbean. This study examines the case of Jamaica. We first (1) examine the extent of Jamaica’s contemporary racial inequality using national census data. We then (2) use nationally representative data from the AmericasBarometer social survey to determine the extent to which a recognition of racial discrimination characterizes Jamaican public opinion. Finally, we (3) explore the salience of an ideology of racial mixing in Jamaica and (4) test whether that ideology affects the likelihood that Jamaicans acknowledge contemporary racial discrimination. Our findings document dramatic social inequality by skin colour in Jamaica and suggest that a majority embrace an ideology that racial mixing is negatively associated with Jamaicans’ recognition of racial discrimination. We discuss our findings and their implications for understanding ideologies of racial mixing and racial inequality in the Americas.

Depth-Aware Salient Object Detection and Segmentation via Multiscale Discriminative Saliency Fusion and Bootstrap Learning.

This paper proposes a novel depth-aware salient object detection and segmentation framework via multiscale discriminative saliency fusion (MDSF) and bootstrap learning for RGBD images (RGB color images with corresponding Depth maps) and stereoscopic images. By exploiting low-level feature contrasts, mid-level feature weighted factors and high-level location priors, various saliency measures on four classes of features are calculated based on multiscale region segmentation. A random forest regressor is learned to perform the discriminative saliency fusion (DSF) and generate the DSF saliency map at each scale, and DSF saliency maps across multiple scales are combined to produce the MDSF saliency map. Furthermore, we propose an effective bootstrap learning-based salient object segmentation method, which is bootstrapped with samples based on the MDSF saliency map and learns multiple kernel support vector machines. Experimental results on two large datasets show how various categories of features contribute to the saliency detection performance and demonstrate that the proposed framework achieves the better performance on both saliency detection and salient object segmentation.

Weight stigma predicts inhibitory control and food selection in response to the salience of weight discrimination

ObjectiveFear and stigmatization are often used to motivate individuals with higher body weight to engage in healthy behaviors, but these strategies are sometimes counterproductive, leading to undesirable outcomes. In the present study, the impact of weight-based stigma on cognition (i.e., inhibitory control) and food selection (i.e., calories selected) was examined among individuals who consider themselves to be overweight. It was predicted that participants higher in perceived weight stigma would perform more poorly on an inhibitory control task and order more calories on a food selection task when they read about discrimination against individuals with higher weight versus discrimination against an out-group. MethodsParticipants completed online prescreen measures assessing whether they considered themselves to be overweight and their perceptions of weight stigma. Individuals who considered themselves to be overweight were invited into the laboratory to complete tasks that manipulated weight-based discrimination, then inhibitory control and food selection were measured. ResultsThe higher participants were in perceived weight stigma, the more poorly they performed on the inhibitory control task and the more calories they ordered when they read about discrimination against individuals with higher body weight. These relationships were not observed when participants read about discrimination against an out-group. ConclusionsThe present findings provide evidence that perceptions of weight stigma are critical in understanding the impact of weight-based discrimination. Additionally, these results have theoretical and practical implications for both understanding and addressing the psychological and physical consequences of weight-based stigma.

Ethnic discrimination during résumé screening: Interactive effects of applicants’ ethnic salience with job context

Systematic research considering job context as affecting ethnic discrimination in hiring is limited. Building on contemporary literature on social categorization and cognitive matching, the interactive effect of context characteristics (client contact; industry status) and person characteristics (i.e. ethnic cues: Maghreb/Arab vs Flemish-sounding name; dark vs light skin tone) were investigated using an experimental field study among 424 white majority HR professionals. Findings showed that equally qualified applicants with a dark skin tone received lower job suitability ratings than applicants with a light skin tone, particularly when they were screened for high client contact/low industry status positions and low client contact/high industry status positions. It is concluded that some ethnic cues (such as skin tone) may be more salient compared with other cues and that job context may influence the salience of ethnic cues and steer hiring discrimination in subtle ways. Implications of these findings for hiring discrimination research and organizations are discussed.

Discriminative saliency propagation with sink points

Salient object detection is still very challenging especially in images with complex or cluttered background. In this paper, we present an efficient and discriminative framework to address it. In specially, a discriminative similarity metric is first proposed by measuring the chi-square distance in a new constructed feature space. Then, we apply it to calculate a background based coarse saliency map by introducing distribution prior to remove foreground noises in the image boundaries. Based on manifold ranking, a robust saliency propagation mechanism is further developed to highlight salient object and simultaneously suppress background region by setting appropriate sink points. Finally, several simple refinement techniques are utilized to generate pixel-wise and smooth saliency maps. Extensive experimental results show the superior performance of the proposed method in terms of different evaluation metrics. In addition, the proposed framework can be also applied to the existing saliency propagation methods for significant performance boosting. We also believe that it is a good choice for subsequent applications based on the achieved high performance and acceptable computational overhead.

Saliency detection via a unified generative and discriminative model

In this paper, we propose a visual saliency detection algorithm which incorporates both generative and discriminative saliency models into a unified framework. First, we develop a generative model by defining image saliency as the sparse coding residual based on a learned background dictionary. Second, we introduce a discriminative model by solving an optimization problem that exploits the intrinsic relevance of similar regions for regressing region-based saliency to the smooth state. Third, a weighted sum of multi-scale region-level saliency is computed as the pixel-level saliency, which generates a more continuous and smooth result. Furthermore, object location is also utilized to suppress background noise, which acts as a vital prior for saliency detection. Experimental results show that the proposed algorithm generates more accurate saliency maps and performs favorably against the state-of-the-art saliency detection methods on three publicly available datasets.

Racial microstressors, racial self-concept, and depressive symptoms among male African Americans during the transition to adulthood.

Racial discrimination is a pervasive stressor that can undermine mental health among African American youth and young adults. Several studies identify links between racial discrimination and depressive symptoms; however, this research base does not focus on male African American youth who experience significant racism-related stress during the transition to young adulthood. Moreover, few prospective studies consider significant confounding variables that affect exposure to and perception of discriminatory treatment. In response to this need, we examined the effect of exposure to racial discrimination from ages 16 to 18 on depressive symptoms among male African Americans at age 20. Racial self-concept, one's sense of positivity about one's race, was examined as a mediator and self-control as a moderator. Hypotheses were tested with 222 participants, age 16 at baseline and age 20 at the endpoint. Participants provided self-report data at five time points. Exposure to racial discrimination from ages 16 to 18 predicted depressive symptoms at age 20, net of confounding influences. Racial self-concept mediated this effect. Self-control moderated the influence of discrimination on racial self-concept. This study underscores the salience of racial discrimination in the development of depressive symptoms among African American male youth and the clinical utility of interventions targeting racial pride and self-control.

Object recognition with hierarchical discriminant saliency networks.

The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as a pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognition model, the hierarchical discriminant saliency network (HDSN), whose layers are top-down saliency detectors, tuned for a visual class according to the principles of discriminant saliency. As a model of neural computation, the HDSN has two possible implementations. In a biologically plausible implementation, all layers comply with the standard neurophysiological model of visual cortex, with sub-layers of simple and complex units that implement a combination of filtering, divisive normalization, pooling, and non-linearities. In a convolutional neural network implementation, all layers are convolutional and implement a combination of filtering, rectification, and pooling. The rectification is performed with a parametric extension of the now popular rectified linear units (ReLUs), whose parameters can be tuned for the detection of target object classes. This enables a number of functional enhancements over neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation of saliency responses by the discriminant power of the underlying features, and the ability to detect both feature presence and absence. In either implementation, each layer has a precise statistical interpretation, and all parameters are tuned by statistical learning. Each saliency detection layer learns more discriminant saliency templates than its predecessors and higher layers have larger pooling fields. This enables the HDSN to simultaneously achieve high selectivity to target object classes and invariance. The performance of the network in saliency and object recognition tasks is compared to those of models from the biological and computer vision literatures. This demonstrates benefits for all the functional enhancements of the HDSN, the class tuning inherent to discriminant saliency, and saliency layers based on templates of increasing target selectivity and invariance. Altogether, these experiments suggest that there are non-trivial benefits in integrating attention and recognition.