Visual tracking based on transfer learning of deep salience information

In this paper,we propose a new visual tracking method in light of salience information and deep learning.Salience detection is used to exploit features with salient information of the image.Complicated representations of image features can be gained by the function of every layer in convolution neural network(CNN).The characteristic of biology vision in attention-based salience is similar to the neuroscience features of convolution neural network.This motivates us to improve the representation ability of CNN with functions of salience detection.We adopt the fully-convolution networks(FCNs)to perform salience detection.We take parts of the network structure to perform salience extraction,which promotes the classification ability of the model.The network we propose shows great performance in tracking with the salient information.Compared with other excellent algorithms,our algorithm can track the target better in the open tracking datasets.We realize the 0.5592 accuracy on visual object tracking 2015(VOT15)dataset.For unmanned aerial vehicle 123(UAV123)dataset,the precision and success rate of our tracker is 0.710 and 0.429.

Salience adaptive morphological structuring element construction method based on minimum spanning tree

Classical mathematical morphology operations use a fixed size and shape structuring element to process the whole image.Due to the diversity of image content and the complexity of target structure,for processed image,its shape may be changed and part of the information may be lost.Therefore,we propose a method for constructing salience adaptive morphological structuring elements based on minimum spanning tree(MST).First,the gradient image of the input image is calculated,the edge image is obtained by non-maximum suppression(NMS)of the gradient image,and then chamfer distance transformation is performed on the edge image to obtain a salience map(SM).Second,the radius of structuring element is determined by calculating the maximum and minimum values of SM and then the minimum spanning tree is calculated on the SM.Finally,the radius is used to construct a structuring element whose shape and size adaptively change with the local features of the input image.In addition,the basic morphological operators such as erosion,dilation,opening and closing are redefined using the adaptive structuring elements and then compared with the classical morphological operators.The simulation results show that the proposed method can make full use of the local features of the image and has better processing results in image structure preservation and image filtering.

The“Psychology”of Polygraph’:Engendering Differential Salience-Concerns and Caveats

The“success”of a polygraph examination is predicated on the establishment of differential or emotional salience(a“psychological set”)with an examinee.This,according to polygraph proponents,guarantees that an examinee will respond appropriately during the administration of the in-test(questioning)phase of the polygraph examination.However,polygraph procedure,as prescribed by its governing body,the American Polygraph Association(APA),is a static clinical Westernised process that does not make any provision for human multiplicity(culture/ethnicity,idiosyncrasies,level of education,language proficiency,ideologies,and so forth).Identical(one size fits all)test procedures are applied across the board–a highly controversial methodology.This article,instead of rigidly focusing on validity and reliability issues per se,explores the degree to which certain intentional and unintentional human behaviour modification strategies have the potential to counterbalance claimed polygraph rectitude from a metaphysical and discursive standpoint.The article exposes concerns(potential flaws)relating to polygraph theory in the context of the“psychological set”and is intended to serve as a caveat regarding the unmitigated use thereof.

AB064. Product knowledge predicts greater willingness to buy and gaze-related attention, salience does not

Background:Visual salience computed using algorithmic procedures have been shown to predict eye-movements in a number of contexts.However,despite calls to incorporate computationally-defined visual salience metrics as a means of assessing the effectiveness of advertisements,few studies have incorporated these techniques in a marketing context.The present study sought to determine the impact of visual salience and knowledge of a brand on eye-movement patterns and buying preferences.Methods:Participants(N=38)were presented with 54 pairs of products presented on the left and right sides of a blank white screen.For each pair,one product was a known North American product,such as Fresca®,and one was an unknown British product of the same category,such as Irn Bru®.Participants were asked to select which product they would prefer to buy while their eye movements were recorded.Salience was computed using Itti&Koch’s[2001]computational model of bottom-up salience.Products were defined as highly salient if the majority of the first five predicted fixations were in the region of the product.Results:Results showed that participants were much more likely to prefer to buy known products,and tentative evidence suggests that participants had longer total dwell times when looking at unknown products.Salience appears to have had little or no effect on preference for a product,nor did it predict total dwell time or time to first fixation.There also appears to be no interaction between knowledge of a product and visual salience on any of the measures analyzed.Conclusions:The results indicate that product salience may not be a useful predictor of attention under the constraints of the present experiment.Future studies could use a different operational definition of visual salience which might be more predictive of visual attention.Furthermore,a more fine-grained analysis of product familiarity based on survey data may reveal patterns obscured by the definitional constraints of the present study.

A Multi-Channel Salience Based Detail Exaggeration Technique for 3D Relief Surfaces

Visual saliency can always persuade the viewer＇s visual attention to fine-scale mesostructure of 3D complex shapes. Owing to the multi-channel salience measure and salience-domain shape modeling technique, a novel visual saliency based shape depiction scheme is presented to exaggerate salient geometric details of the underlying relief surface. Our multi-channel salience measure is calculated by combining three feature maps, i.e., the 0-order feature map of local height distribution, the l-order feature map of normal difference, and the 2-order feature map of mean curvature variation. The original relief surface is firstly manipulated by a salience-domain enhancement function, and the detail exaggeration surface can then be obtained by adjusting the surface normals of the original surface as the corresponding final normals of the manipulated surface. The advantage of our detail exaggeration technique is that it can adaptively alter the shading of the original shape to reveal visually salient features whilst keeping the desired appearance unimpaired. The experimental results demonstrate that our non-photorealistic shading scheme can enhance the surface mesostructure effectively and thus improving the shape depiction of the relief surfaces.

Application of virtual reality technology improves the functionality of brain networks in individuals experiencing pain

Medical procedures are inherently invasive and carry the risk of inducing pain to the mind and body.Recently,efforts have been made to alleviate the discomfort associated with invasive medical procedures through the use of virtual reality(VR)technology.VR has been demonstrated to be an effective treatment for pain associated with medical procedures,as well as for chronic pain conditions for which no effective treatment has been established.The precise mechanism by which the diversion from reality facilitated by VR contributes to the diminution of pain and anxiety has yet to be elucidated.However,the provision of positive images through VR-based visual stimulation may enhance the functionality of brain networks.The salience network is diminished,while the default mode network is enhanced.Additionally,the medial prefrontal cortex may establish a stronger connection with the default mode network,which could result in a reduction of pain and anxiety.Further research into the potential of VR technology to alleviate pain could lead to a reduction in the number of individuals who overdose on painkillers and contribute to positive change in the medical field.

Idiom Comprehension of Chinese Patients With Aphasia: A Case Study

Previous studies on idiom comprehension of patients with aphasia(PWAs)mainly focused on Indo-European speakers,examining whether PWAs could correctly extract the target meaning of idioms,while among Chinese PWAs,idiom familiarity,context and other variables affecting idiom comprehension were rarely studied.Hence,this study aims to explore whether Chinese PWAs can correctly comprehend the target meaning of idioms,and further investigate the role of familiarity and context.For three Chinese PWAs,this study adopted the string-to-word matching task,taking Chinese four-character idioms as the experimental stimuli,and provided decoy words containing target meaning,literal meaning,unrelated abstract meaning and unrelated concrete meaning as the matching words of idiom items by manipulating the familiarity and contextual presence of idiom items.The results suggested that the PWAs could not correctly extract the target meaning of idioms and presented both the literal meaning tendency and the weak abstract meaning tendency,and the influence of familiarity on the comprehension of idioms was stronger than that of context.These results support the Graded Salience Hypothesis.

Data-driven approach to learning salience models of indoor landmarks by using genetic programming

In landmark-based way-finding,determining the most salient landmark from several candidates at decision points is challenging.To overcome this problem,current approaches usually rely on a linear model to measure the salience of landmarks.However,linear models are not always able to establish an accurate quantitative relationship between the attributes of a landmark and its perceived salience.Furthermore,the numbers of evaluated scenes and of volunteers participating in the testing of these models are often limited.With the aim of overcoming these gaps,we propose learning a non-linear salience model by means of genetic programming.We compared our proposed approach with conventional algorithms by using photographs of two hundred test scenes collected from two shopping malls.Two hundred volunteers who were not in these environments were asked to answer questionnaires about the collected photographs.The results from this experiment showed that in 76%of the cases,the most salient landmark(according to the volunteers’perception)was correctly predicted by our proposed approach.This accuracy rate is considerably higher than the ones achieved by conventional linear models.

Giora的Graded Salience Hypothesis译名探讨

Giora的Graded Salience Hypothesis是语言学研究领域中的重要理论,其中文译名五花八门,不统一。译名的混乱不利于学术交流与研究,因此规范Graded Salience Hypothesis的中文译名非常有必要且迫切。Graded Salience Hypothesis认为,对比喻义和字面义的理解由一种普遍的Salience原则支配,即首先要处理salient意义。根据Giora的理论,结合相关的翻译标准,在分析Graded Salience Hypothesis词义构成的基础上,本文讨论其多种译名,发现"等级突显假说"为最佳翻译。"等级突显假说"是一个新的解释话语理解中词义激活与处理过程的理论,它的运用范围非常广泛,常用于心理学、神经学、医学诊断、语言理解、语言习得、翻译等研究中。在语言学领域,特别是在反语、惯用语、跨文化语用研究中,该理论越来越受重视。

Salience processing by glutamatergic neurons in the ventral pallidum

Organisms must make sense of a constant stream of sensory inputs from both internal and external sources which compete for attention by determining which ones are salient.The ability to detect and respond appropriately to potentially salient stimuli in the environment is critical to all organisms.However,the neural circuits that process salience are not fully understood.Here,we identify a population of glutamatergic neurons in the ventral pallidum(VP)that play a unique role in salience processing.Using cell-type-specific fiber photometry,we find that VP glutamatergic neurons are robustly activated by a variety of aversion-and reward-related stimuli,as well as novel social and non-social stimuli.Inhibition of the VP glutamatergic neurons reduces the ability to detect salient stimuli in the environment,such as aversive cue,novel conspecific and novel object.Besides,VP glutamatergic neurons project to both the lateral habenula(LHb)and the ventral tegmental area(VTA).Together,our findings demonstrate that the VP glutamatergic neurons participate in salience processing and therefore provide a new perspective on treating several neuropsychiatric disorders,including dementia and psychosis.

Enhanced Object Detection and Classification via Multi-Method Fusion

Advances in machine vision systems have revolutionized applications such as autonomous driving,robotic navigation,and augmented reality.Despite substantial progress,challenges persist,including dynamic backgrounds,occlusion,and limited labeled data.To address these challenges,we introduce a comprehensive methodology toenhance image classification and object detection accuracy.The proposed approach involves the integration ofmultiple methods in a complementary way.The process commences with the application of Gaussian filters tomitigate the impact of noise interference.These images are then processed for segmentation using Fuzzy C-Meanssegmentation in parallel with saliency mapping techniques to find the most prominent regions.The Binary RobustIndependent Elementary Features(BRIEF)characteristics are then extracted fromdata derived fromsaliency mapsand segmented images.For precise object separation,Oriented FAST and Rotated BRIEF(ORB)algorithms areemployed.Genetic Algorithms(GAs)are used to optimize Random Forest classifier parameters which lead toimproved performance.Our method stands out due to its comprehensive approach,adeptly addressing challengessuch as changing backdrops,occlusion,and limited labeled data concurrently.A significant enhancement hasbeen achieved by integrating Genetic Algorithms(GAs)to precisely optimize parameters.This minor adjustmentnot only boosts the uniqueness of our system but also amplifies its overall efficacy.The proposed methodologyhas demonstrated notable classification accuracies of 90.9%and 89.0%on the challenging Corel-1k and MSRCdatasets,respectively.Furthermore,detection accuracies of 87.2%and 86.6%have been attained.Although ourmethod performed well in both datasets it may face difficulties in real-world data especially where datasets havehighly complex backgrounds.Despite these limitations,GAintegration for parameter optimization shows a notablestrength in enhancing the overall adaptability and performance of our system.

Unsupervised Color Segmentation with Reconstructed Spatial Weighted Gaussian Mixture Model and Random Color Histogram

Image classification and unsupervised image segmentation can be achieved using the Gaussian mixture model.Although the Gaussian mixture model enhances the flexibility of image segmentation,it does not reflect spatial information and is sensitive to the segmentation parameter.In this study,we first present an efficient algorithm that incorporates spatial information into the Gaussian mixture model(GMM)without parameter estimation.The proposed model highlights the residual region with considerable information and constructs color saliency.Second,we incorporate the content-based color saliency as spatial information in the Gaussian mixture model.The segmentation is performed by clustering each pixel into an appropriate component according to the expectation maximization and maximum criteria.Finally,the random color histogram assigns a unique color to each cluster and creates an attractive color by default for segmentation.A random color histogram serves as an effective tool for data visualization and is instrumental in the creation of generative art,facilitating both analytical and aesthetic objectives.For experiments,we have used the Berkeley segmentation dataset BSDS-500 and Microsoft Research in Cambridge dataset.In the study,the proposed model showcases notable advancements in unsupervised image segmentation,with probabilistic rand index(PRI)values reaching 0.80,BDE scores as low as 12.25 and 12.02,compactness variations at 0.59 and 0.7,and variation of information(VI)reduced to 2.0 and 1.49 for the BSDS-500 and MSRC datasets,respectively,outperforming current leading-edge methods and yielding more precise segmentations.

Guided-YNet: Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network

Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion.Such as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and PET-CT.How to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key questions.To solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this paper.Firstly,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate lesions.Secondly,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after downsampling.Thirdly,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic information.Finally,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local attention.The proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,respectively.It is of great significance for computer-aided diagnosis.

Co-salient object detection with iterative purification and predictive optimization

Background Co-salient object detection(Co-SOD)aims to identify and segment commonly salient objects in a set of related images.However,most current Co-SOD methods encounter issues with the inclusion of irrelevant information in the co-representation.These issues hamper their ability to locate co-salient objects and significantly restrict the accuracy of detection.Methods To address this issue,this study introduces a novel Co-SOD method with iterative purification and predictive optimization(IPPO)comprising a common salient purification module(CSPM),predictive optimizing module(POM),and diminishing mixed enhancement block(DMEB).Results These components are designed to explore noise-free joint representations,assist the model in enhancing the quality of the final prediction results,and significantly improve the performance of the Co-SOD algorithm.Furthermore,through a comprehensive evaluation of IPPO and state-of-the-art algorithms focusing on the roles of CSPM,POM,and DMEB,our experiments confirmed that these components are pivotal in enhancing the performance of the model,substantiating the significant advancements of our method over existing benchmarks.Experiments on several challenging benchmark co-saliency datasets demonstrate that the proposed IPPO achieves state-of-the-art performance.

Visual salience guided feature-aware shape simplification

In the area of 3D digital engineering and 3D digital geometry processing, shape simplification is an important task to reduce their requirement of large memory and high time complexity. By incorporating the content-aware visual salience measure of a polygonal mesh into simplification operation, a novel feature-aware shape simplification approach is presented in this paper. Owing to the robust extraction of relief heights on 3D highly detailed meshes, our visual salience measure is defined by a center-surround operator on Gaussian-weighted relief heights in a scale-dependent manner. Guided by our visual salience map, the feature-aware shape simplification algorithm can be performed by weighting the high-dimensional feature space quadric error metric of vertex pair contractions with the weight map derived from our visual salience map. The weighted quadric error metric is calculated in a six-dimensional feature space by combining the position and normal information of mesh vertices. Experimental results demonstrate that our visual salience guided shape simplification scheme can adaptively and effectively re-sample the underlying models in a feature-aware manner, which can account for the visually salient features of the complex shapes and thus yield better visual fidelity.

Stasis Salience and the Enthymemic Thesis

The argumentative stasis theory and enthymeme principles richly complement each other but they have rarely been investigated jointly. We correct this oversight first with a principled re-analysis of the stasis tradition, resulting in a double-layer stasis system: Cicero's later system(in De Oratore and Topica) with "action" stasis' subclassification, modified by Kenneth Burke's dramatic pentad of act, scene, agent, agency, purpose(in A Grammar of Motives). Then inspired by Ronald Langacker's salience theory in cognitive linguistics, we secure two stasis deployment strategies: selection(profile against base) and prominence(trajector against landmark). Stasis theory thus solidified, we examine how it interacts with the two central aspects of the enthymemic thesis: incompleteness and probability and how the enthymemic thesis helps explain the force of stasis theory. This inquiry contributes to rhetorical theory and criticism; argumentation studies; and linguistics, by showing the reach of salience theory.

Refined Sparse Representation Based Similar Category Image Retrieval

Given one specific image,it would be quite significant if humanity could simply retrieve all those pictures that fall into a similar category of images.However,traditional methods are inclined to achieve high-quality retrieval by utilizing adequate learning instances,ignoring the extraction of the image’s essential information which leads to difficulty in the retrieval of similar category images just using one reference image.Aiming to solve this problem above,we proposed in this paper one refined sparse representation based similar category image retrieval model.On the one hand,saliency detection and multi-level decomposition could contribute to taking salient and spatial information into consideration more fully in the future.On the other hand,the cross mutual sparse coding model aims to extract the image’s essential feature to the maximumextent possible.At last,we set up a database concluding a large number of multi-source images.Adequate groups of comparative experiments show that our method could contribute to retrieving similar category images effectively.Moreover,adequate groups of ablation experiments show that nearly all procedures play their roles,respectively.

Interpreting Randomly Wired Graph Models for Chinese NER

Interpreting deep neural networks is of great importance to understand and verify deep models for natural language processing(NLP)tasks.However,most existing approaches only focus on improving the performance of models but ignore their interpretability.In this work,we propose a Randomly Wired Graph Neural Network(RWGNN)by using graph to model the structure of Neural Network,which could solve two major problems(word-boundary ambiguity and polysemy)of ChineseNER.Besides,we develop a pipeline to explain the RWGNNby using Saliency Map and Adversarial Attacks.Experimental results demonstrate that our approach can identify meaningful and reasonable interpretations for hidden states of RWGNN.

A Detection Method of Bolts on Axlebox Cover Based on Cascade Deep Convolutional Neural Network

This paper proposes a cascade deep convolutional neural network to address the loosening detection problem of bolts on axlebox covers.Firstly,an SSD network based on ResNet50 and CBAM module by improving bolt image features is proposed for locating bolts on axlebox covers.And then,theA2-PFN is proposed according to the slender features of the marker lines for extracting more accurate marker lines regions of the bolts.Finally,a rectangular approximationmethod is proposed to regularize themarker line regions asaway tocalculate the angle of themarker line and plot all the angle values into an angle table,according to which the criteria of the angle table can determine whether the bolt with the marker line is in danger of loosening.Meanwhile,our improved algorithm is compared with the pre-improved algorithmin the object localization stage.The results show that our proposed method has a significant improvement in both detection accuracy and detection speed,where ourmAP(IoU=0.75)reaches 0.77 and fps reaches 16.6.And in the saliency detection stage,after qualitative comparison and quantitative comparison,our method significantly outperforms other state-of-the-art methods,where our MAE reaches 0.092,F-measure reaches 0.948 and AUC reaches 0.943.Ultimately,according to the angle table,out of 676 bolt samples,a total of 60 bolts are loose,69 bolts are at risk of loosening,and 547 bolts are tightened.

A weighted block cooperative sparse representation algorithm based on visual saliency dictionary

Unconstrained face images are interfered by many factors such as illumination,posture,expression,occlusion,age,accessories and so on,resulting in the randomness of the noise pollution implied in the original samples.In order to improve the sample quality,a weighted block cooperative sparse representation algorithm is proposed based on visual saliency dictionary.First,the algorithm uses the biological visual attention mechanism to quickly and accurately obtain the face salient target and constructs the visual salient dictionary.Then,a block cooperation framework is presented to perform sparse coding for different local structures of human face,and the weighted regular term is introduced in the sparse representation process to enhance the identification of information hidden in the coding coefficients.Finally,by synthesising the sparse representation results of all visual salient block dictionaries,the global coding residual is obtained and the class label is given.The experimental results on four databases,that is,AR,extended Yale B,LFW and PubFig,indicate that the combination of visual saliency dictionary,block cooperative sparse representation and weighted constraint coding can effectively enhance the accuracy of sparse representation of the samples to be tested and improve the performance of unconstrained face recognition.