Specific Object Features Research Articles

Weighted parallel decoupled feature pyramid network for object detection

As one of the most representative detectors, feature pyramid network (FPN) has achieved remarkable improvement in object detection. Thanks to its distinctive top-down feature fusion path and multi-scale detection paradigm, FPN has become an essential component in modern detectors and has attracted increasing attention. Nevertheless, since the information of each level feature is not object-specific and the heterogeneity of classification and localization tasks in detection, FPN and its numerous variants endure information redundancy and task conflict. To address these two deficiencies that greatly limit the detection performance, this paper proposes weighted parallel decoupled FPN (WPDFPN). Specifically, selective fusion and elimination (SFE) focusing on internal construction of pyramid is first proposed. Compared to existing feature fusion methods, SFE effectively fuses complementary information between different level features and eliminates redundant information to produce object-specific feature at each pyramid level. Then, a novel weighted parallel FPN (WPFPN) is constructed by investigating the combination manners of feature fusion paths. Different from the sequential bidirectional pyramids, WPFPN performs the top-down and bottom-up paths in parallel and aggregates them using a weighted strategy, adaptively integrating object semantics and details. On this basis, feature decoupling mechanism and decoupled head are both developed to learn task-specific features for classification and localization, thus effectively mitigating the task conflict. Without bells and whistles, WPDFPN achieves 43.6 AP on the MS COCO dataset with ResNet-101 as backbone in Faster R-CNN framework. This achievement suppresses the baseline FPN by 3.1 points and demonstrates competitive performance in comparison with some state-of-the-art detectors. Code is available at https://github.com/HB-X/WPDFPN.

Characteristics of optoelectronic discrete displacement converters with hollow and fiber light guides

This article discusses the issues of optoelectronic discrete converters of any type - longitudinal or transverse movement of the external modulating body. In connection with the development of such important sectors of the economy as mechanical engineering, metallurgy, oil and gas, chemical, industrial, construction, food industry and others, it is important to provide them with modern discrete displacement transducers, which allow monitoring and managing such important quantities as liquid level, speed and flow flows of gases and liquids, as well as automative the processes of automatic accounting of piece goods, products, goods, blanks and semifinished products, which allows you to objectively analyze the economic activities of enterprises and plan their further development. The variety of specific features of monitoring and control objects put forward a set of requirements for discrete converters of object parameters: high sensitivity, accuracy, reliability, sufficient noise immunity, manufacturability. An analysis of existing discrete optoelectronic displacement transducers shows that to solve the above problems for monitoring and control, optoelectronic discrete displacement transducers based on hollow and fiber light guides are the most acceptable. In this regard, the improvement and development of optoelectronic discrete displacement transducers based on hollow and fiber light guides is an urgent task.

Identifying and modelling polysemous senses of spatial prepositions in referring expressions

In this paper we analyse the issue of reference using spatial language and examine how the polysemy exhibited by spatial prepositions can be incorporated into semantic models for situated dialogue. After providing a brief overview of polysemy in spatial language and a review of related work, we describe an experimental study we used to collect data on a set of relevant spatial prepositions. We then establish a semantic model in which to integrate polysemy (the Baseline Prototype Model), which we test against a Simple Relation Model and a Perceptron Model. To incorporate polysemy into the baseline model we introduce two methods of identifying polysemes in grounded settings. The first is based on ‘ideal meanings’ and a modification of the ‘principled polysemy’ framework and the second is based on ‘object-specific features’. In order to compare polysemes and aid typicality judgements we then introduce a notion of ‘polyseme hierarchy’. Finally, we test the performance of the polysemy models against the Baseline Prototype Model and Perceptron Model and discuss the improvements shown by the polysemy models.

The Missing Voices of Disabled People.

This paper presents the development process of a graph database that connects statements posted by disabled people on various web-based platforms with accessibility requirements in the Danish Building Regulations (BR18). The aim is to bring the lived experience of disabled people into a vocabulary of space-making for architects. By elevating the missing voices of disabled people - describing what matters, how and why - the project supports the decision-making processes of architects to make the built environment more inclusive. The developed database relates statements posted by disabled people with sentences from paragraphs of BR18 through specific architectural features of room, element, and object. Using the architectural features as point of reference, the database not only highlights some of the most common building situations encountered by disabled people, but also allows anyone interested to explore their relationship to the real lives of disabled users and the statutory requirements.

Объекты поклонения орочонов Китая

The paper aims to identify meaningful characteristics and specific features of cult objects of Oroqen people in Northeast China. The authors consider a poorly investigated problem, analyze worldview conceptions and religious cults of China’s Oroqen people, and herein lies scientific originality of the study. The findings are as follows: Oroqen people of trans-border northern Manchuria region worshipped numerous deities; naturalistic and animal cults influenced considerably the formation of Oroqen religious and mythological worldview. The conclusion is made that Oroqen people’s cults represent the conceptions of Tungusic peoples on interrelation between humans and spirits of the elements.

An End-to-End Bidirectional Authentication System for Pallet Pooling Management Through Blockchain Internet of Things (BIoT)

Pallet pooling is regarded as a sustainable and cost-effective measure for the industry, but challenging to advocate due to weak data and pallet authentication.In order to establish trust between end-users and pallet pooling services, we propose an end-to-end, bidirectional authentication system for transmitted data and pallets based on blockchain and Internet-of-things (IoT) technologies. In addition, secure data authentication fosters the pallet authenticity in the whole supply chain network, which is achieved by considering the tag, location, and object-specific features. To evaluate the object-specific features, the scale invariant feature transform (SIFT) approach is adopted to match key-points and descriptors between two pallet images. According to the case study, it is found that the proposed system provides a low bandwidth blocking rate and a high probability of restoring complete data payloads. Consequently, positive influences on end-user satisfaction, quality of service, operational errors, and pallet traceability are achieved through the deployment of the proposed system.

Precise functional connections from the dorsal anterior cingulate cortex to the intuitive physics network in the human brain

Recent work has identified a set of brain regions that are recruited when people predict how the physical behavior of the world will unfold (here termed the intuitive physics network; IPN). Mounting evidence supports the characterization of this network as a physics simulation engine in the brain, but many fundamental questions about the architecture of the IPN remain unanswered. One such question is what regions provide the key inputs to the network, supplying the necessary information for physical prediction and regulating when and how the IPN is engaged in service of our goals. Here, we investigated the dorsal anterior cingulate cortex (dACC) as a candidate for regulating IPN function. The dACC has long been implicated in "attention for action", driving the focus of processing toward specific object features that are crucial for planning behaviors. The dACC is also richly interconnected with the general regions of frontoparietal cortex where the IPN is situated, but no study has yet investigated whether these connections specifically target the IPN. To address this question, we collected resting state fMRI recordings in seventeen individuals and independently localized the IPN in each person. We computed the resting state correlations of the dACC with voxels across the rest of the brain and found that the strongest functional connections of the dACC not only aligned well with the IPN at the group level, but also precisely mirrored individual differences in the positioning of IPN regions across participants. This tight correspondence points to the dACC being an important input to the IPN. Taken together with previous findings, our results suggest that the dACC might be a key structure for regulating the engagement of the mental physics engine based on motivation, and may provide an interface between the IPN and the brain systems for other cognitive domains such as social reasoning.

Perceptual and Semantic Representations at Encoding Contribute to True and False Recognition of Objects.

When encoding new episodic memories, visual and semantic processing is proposed to make distinct contributions to accurate memory and memory distortions. Here, we used fMRI and preregistered representational similarity analysis to uncover the representations that predict true and false recognition of unfamiliar objects. Two semantic models captured coarse-grained taxonomic categories and specific object features, respectively, while two perceptual models embodied low-level visual properties. Twenty-eight female and male participants encoded images of objects during fMRI scanning, and later had to discriminate studied objects from similar lures and novel objects in a recognition memory test. Both perceptual and semantic models predicted true memory. When studied objects were later identified correctly, neural patterns corresponded to low-level visual representations of these object images in the early visual cortex, lingual, and fusiform gyri. In a similar fashion, alignment of neural patterns with fine-grained semantic feature representations in the fusiform gyrus also predicted true recognition. However, emphasis on coarser taxonomic representations predicted forgetting more anteriorly in the anterior ventral temporal cortex, left inferior frontal gyrus and, in an exploratory analysis, left perirhinal cortex. In contrast, false recognition of similar lure objects was associated with weaker visual analysis posteriorly in early visual and left occipitotemporal cortex. The results implicate multiple perceptual and semantic representations in successful memory encoding and suggest that fine-grained semantic as well as visual analysis contributes to accurate later recognition, while processing visual image detail is critical for avoiding false recognition errors.SIGNIFICANCE STATEMENT People are able to store detailed memories of many similar objects. We offer new insights into the encoding of these specific memories by combining fMRI with explicit models of how image properties and object knowledge are represented in the brain. When people processed fine-grained visual properties in occipital and posterior temporal cortex, they were more likely to recognize the objects later and less likely to falsely recognize similar objects. In contrast, while object-specific feature representations in fusiform gyrus predicted accurate memory, coarse-grained categorical representations in frontal and temporal regions predicted forgetting. The data provide the first direct tests of theoretical assumptions about encoding true and false memories, suggesting that semantic representations contribute to specific memories as well as errors.

A System for Noise Control of the Technical Condition of Railroad Bridges and Tunnels in Seismically Active Regions

The authors analyze the technical condition of objects of railroad communications with modern bridges, tunnels, stations, overpasses, crossings and power installations. It is noted that, based on the specific features of such objects, control of their technical condition in most cases is carried out at certain intervals. At the same time, existing continuous control systems do not always adequately assess the technical condition of rail infrastructure objects due to the presence of additional noises in the processed signals at the time when a malfunction occurs. In this regard, one of the possible options is proposed for "continuous" monitoring of the beginning of changes in the technical condition of railroad tracks by means of noise technologies. It is pointed out that when the technical condition of rail infrastructure changes, vibration signals caused by the impact of rolling stock contain noises in addition to the useful component. The use of correlation and spectral analysis technologies, as well as other traditional methods does not allow ensuring the adequacy of the control results, due to the influence of the noise on useful vibration signals. Therefore, technologies are proposed for split analysis of the useful signal and the noise received from vibration, as well as for forming informative attributes of identification of the technical condition of rail infrastructure. In this case, the estimates of the characteristics of the useful signal and the noise are used as the main carrier of diagnostic information. Due to the simplicity and reliability of the developed theoretical algorithms, the implementation of the technical equipment and its installation in all objects of the railroad track present no particular difficulties. At the same time, the implementation of the Noise system will ensure real-time control of the beginning of changes in the technical condition of railroad tracks during the movement of the rolling stock. This, in turn, will allow timely detection of malfunctions, significantly enhancing the safety of passenger and cargo rail transportation.

Multitask Learning for Ship Detection From Synthetic Aperture Radar Images

Ship detection from synthetic aperture radar (SAR) images is inherently subject to the special imaging mechanism of SAR. In recent years, deep-learning-based techniques for detecting objects from optical images have rapidly advanced and promoted the development of SAR image detection technology. However, the strong speckle noise in SAR images degrades low-level feature learning in shallow layers, hindering the higher level learning of semantic features for object detection. In view of the problems encountered in direct end-to-end feature learning for object detection and the close relationship between objects and auxiliary cues, a multitask learning-based object detector (MTL-Det) is proposed in this article to distinguish ships in SAR images. The proposed approach models the ship detection problem, not as a single object detection task, but as three cooperative tasks. The model involves two auxiliary subtasks that are focused on learning object-specific cues ( e.g ., texture and shape) for the ship detection task, which is constrained by the pseudoground truth generated by the main task. Assisted by auxiliary subtasks, the low-level features are robust to speckle noise and reliably support high-level feature learning. Compared with traditional single-task-based object detectors, more discriminative object-specific features are learned by multitask learning without the extra cost of manual labeling. The experiments conducted in this study help demonstrate the advantages of MTL-Det in improving the ship detection performance on two SAR datasets: high-resolution SAR images dataset and large-scale SAR ship detection dataset-v1.0.

Attn-Eh ALN: complex text-to-image generation with attention-enhancing adversarial learning networks

Text-to-image generation can be widely applied in various fields, such as scene retrieval and computer-aided design. The existing approaches can generate realistic images from simple text descriptions, whereas rendering images from complex text descriptions is still not satisfactory for practical applications. To generate accurate high-resolution images from given complex texts, we proposed an attention-enhancing adversarial learning network (Attn-Eh ALN) based upon conditional generative adversarial networks and the attention mechanism. This model consists of an encoding module and a generative module. In the encoding module, we proposed a local attention driven encoding network that allows words in the text with different weights to enhance the semantic representation of specific object features. The attention mechanism is employed to capture more details while ensuring global information. This enables the details in the generated images to be more fine-grained. In the discriminating stage, we take multiple discriminators to distinguish the realness of the generated images, avoiding the bias caused by a single discriminator. Moreover, a semantic similarity judgment module is introduced to improve the semantic consistency between the text description and visual content. Experimental results on benchmark datasets indicate that Attn-Eh ALN generates favorable results in comparison with other state-of-the-art methods from qualitative and quantitative assessments.

Multi-Agent Analysis of Scenarios for “Arctic Smart City”

An approach to formalizing problems of municipal management in the Russian Arctic via smart city technologies is considered on the example of city Salekhard. An analysis of modern smart city concepts and prospects for integrating such technologies as BIM, GIS, and CIM is given. A discussion is based on comparison of two options to implement smart city technologies. Those are: 1) the inertial scenario of development adopted in the Strategy of the municipality Salekhard city, and 2) an alternative scenario corresponding to the innovation model of multicomponent sustainable system which includes energy subsystems. A multi-agent formalization of city management presents specific object features, including factors of the Northern nature. The framework of a four-component model of the flow distribution of resources: material, energy, information, financial, is applied.

Memory-driven capture occurs for individual features of an object

Items held in working memory (WM) capture attention (memory-driven capture). People can selectively prioritize specific object features in WM. Here, we examined whether feature-specific prioritization within WM modulates memory-driven capture. In Experiment 1, after remembering the color and orientation of a triangle, participants were instructed, via retro-cue, whether the color, the orientation, or both features were relevant. To measure capture, we asked participants to execute a subsequent search task, and we compared performance in displays that did and did not contain the memory-matching feature. Color attracted attention only when it was relevant. No capture by orientation was found. In Experiment 2, we presented the retro-cue at one of the four locations of the search display to direct attention to specific objects. We found capture by color and this capture was larger when it was indicated as relevant. Crucially, orientation also attracted attention, but only when it was relevant. These findings provide evidence for reciprocal interaction between internal prioritization and external attention on the features level. Specifically, internal feature-specific prioritization modulates memory-driven capture but this capture also depends on the salience of the features.

Context-dependent modulation of natural approach behaviour in mice.

Specific features of visual objects innately draw approach responses in animals, and provide natural signals of potential reward. However, visual sampling behaviours and the detection of salient, rewarding stimuli are context and behavioural state-dependent and it remains unclear how visual perception and orienting responses change with specific expectations. To start to address this question, we employed a virtual stimulus orienting paradigm based on prey capture to quantify the conditional expression of visual stimulus-evoked innate approaches in freely moving mice. We found that specific combinations of stimulus features selectively evoked innate approach or freezing responses when stimuli were unexpected. We discovered that prey capture experience, and therefore the expectation of prey in the environment, selectively modified approach frequency, as well as altered those visual features that evoked approach. Thus, we found that mice exhibit robust and selective orienting responses to parameterized visual stimuli that can be robustly and specifically modified via natural experience. This work provides critical insight into how natural appetitive behaviours are driven by both specific features of visual motion and internal states that alter stimulus salience.

Computational propaganda: Structural characteristics and vectors of research

The term “computer propaganda” appeared several years ago because of the intersection of a number of sciences (computer sciences, political science, sociology, linguistics, social psychology, etc.). This phenomenon attracts attention for both technological and societal reasons. Therefore, the authors aim to reveal and analyze the main vectors of the development of theoretical concept of computer propaganda from the standpoint of the socio-communication approach. For this purpose, they identify the main structural characteristics of the concept corresponding to the characteristics of the process of information influence (object of propaganda, forms, channels, subjects of propaganda). Based on this position, the authors consider the original concept of propaganda presented in classical works on theory and practice of propaganda, and reveal the specifics of the new concept of computer propaganda. New characteristics of the target propaganda audience, a segmented structure of network virtual communities with the property of uncritical perception of “convenient and familiar” information, form specific features of the computer propaganda object. The authors outline that purposefully designed and circulated fake information in social networks is a new form of computer propaganda, and social bots as algorithmized programs, that allow for such distribution with maximum speed and scale, are a new channel of distribution for such information. The subjects of computer propaganda are the new political and business elites that have joined forces with representatives of the technological elite. In addition, current negative connotations dominate in the interpretation of computer propaganda as a communicative practice of using new computer technologies for manipulation and disinformation in online space. In conclusion, the authors discuss the possible perspectives of this topic, related to the understanding of the broader (neutral-information) context in understanding the phenomenon of computer propaganda.

Major deposits and occurrences of platinum ores of the Kola belt layered intrusions (Kola Peninsula, Russia)

Research subject. This paper presents data characterizing major occurrences and deposits of platinum group elements (PGE) of Kola belt layered mafic-ultramafic intrusions (Kola Peninsula).Materials and methods. The study was based on extensive experimental data collected by the author over a long-term period and a comprehensive analysis of published and archive literature pertaining to this field.Results. Certificates (so-called passports) were compiled for all major PGE objects in theKola Peninsula, which include diverse characterization parameters (geological, structural, isotope-geochemical, mineralogical). The formation of PGE mineralization was compared with both the age characteristics of large layered complexes and the sequence of intrusion of individual magmatic phases.Conclusion. The proposed parameters can be used to determine specific features of PGE objects, thus allowing identification of objects promising in terms of industrial development. The obtained results demonstrate the importance of taking into account these specific features during mineral deposit exploitation.

The dynamic model of agricultural land structure on the space images in the precision agriculture tasks

The study is devoted to the analysis of specific features of spacial objects referred to “agricultural land” class in Central Siberia according to the results of the Earth remote sensing from the space for information support in the precision agriculture tasks. The subject of the study is temporal variability of spectral, textural and geometrical features of a land area with homogenous vegetation (hereinafter agricultural contour). During the vegetation period the agricultural contour is subject to changes caused by a combination of natural and antropogenic factors. These factors are the result of the natural course of vegetation (change of phenological phases), weather conditions and agricultural engineering measures implemented. They typically cause the change of the spacial structure of the agricultural contour resulting in non-homogenous vegetation of an agricultural crop within the agricultural contour.

A Multi-Level Approach for Change Detection of Buildings Using Satellite Imagery

In this paper a novel technique for building change detection from remote sensing imagery is presented. It includes two main stages: (1) Object-specific discriminative features are extracted using Morphological Building Index (MBI) to automatically detect the existence of buildings in remote sensing images. (2) Pixel-based image matching is measured on the basis of Mutual Information (MI) of the images by Normalized Mutual Information (NMI). Here, the MBI features values are computed for each of the pair images taken over the same region at two different times and then changes in these two MBI images are measured to indicate the building change. MI is estimated locally for all the pixels for image matching and then thresholding is applied for eliminating those pixels which are responsible for strong similarity. Finally, after getting the MBI and NMI images, a further fusion of these two images is done for refinement of the change result. For evaluation purpose, the experiments are carried on QuickBird, IKONOS images and images taken from Google Earth. The results show that the proposed technique can attain acceptable correctness rates above 90% with Overall Accuracy (OA) 89.52%.

Dynamic and robust method for detection and locating vehicles in the video images sequences with use of image processing algorithm

There are various methods in the field of moving-object tracking in the video images that each of them implies on the specific features of object. Among tracking methods based on features, algorithms based on color are able to provide a precise description of the object and track the object with high speed. One of the efficient methods in the field of object tracking based on color information is mean-shift algorithm. If the color of moving object approaches toward a background model or image background has a low contrast and brightness, then the color information is not enough for target tracking. In this paper, the new tracking method is proposed which with combination of moved object information with color information, the new proposed method will be capable to track object under condition that color information is not enough for tracking. With use of background subtraction method based on Gaussian combination, the binary image which includes moving information will use in the mean-shift algorithm. Usage of object movement information will compensate the lack of spatial information and will increase robustness of algorithm especially in the complicated conditions. Also in order to achieve the robust algorithm against changes in shapes, size, and rotation of object, extended mean-shift algorithm is used. Results show the robustness of proposed algorithm in object tracking especially under conditions which object color is same as background color and have better results in the low contrast condition in comparison to mean-shift and extended mean-shift algorithms.

Persistent negative effects of alcohol drinking on aspects of novelty-directed behavior in male rhesus macaques.

Humans with histories of prolonged heavy alcohol use exhibit poorer performance on cognitive tasks associated with problem solving, short-term memory, and visuospatial reasoning, even following the cessation of drinking, when compared with healthy controls. It is unclear, however, whether the cognitive problems are a consequence of alcohol exposure or a contributing factor to alcohol-use disorders. Here, we examined the relationship between performance on a novel object recognition (NOR) task and total alcohol consumption (TAC) in adult male rhesus macaques (n=12; ETHgroup; trained to self-administer alcohol). NOR performance in this group was assessed prior to induction of alcohol drinking ("pre") and, again, after a 1-year abstinence period ("post") and was compared to the performance of a second group (n=6; Control group), which was alcohol-naïve. In the NOR task, difficulty was manipulated across three phases by varying specific object features and/or by varying duration of access to objects. For each monkey, we measured aspects of novelty-related behavior including novelty detection, novelty reactivity, and perseverative behavior. TAC during induction and a "free" access period in which the monkey could choose between water and a 4% w/v ethanol solution also was determined. We found that performance deficits in the NOR task were a consequence of high total alcohol intake instead of a predictor of subsequent high intake. Poor NOR performance in drinkers with the highest intakes was characterized by increased perseverative behavior rather than an inability to detect or react to novelty. Finally, the observed deficits are long-lasting - persisting even after a year of abstinence. Given the prevalent and persistent nature of alcohol-induced cognitive deficits in patients in treatment settings, understanding the nature of the deficit and its neural basis could ultimately offer novel treatment approaches based on the reversal of alcohol-induced impairment.