Semantic Module Research Articles

Verbal vocabulary as a means of expressing interpersonal relations in Russian and Chinese

The subject of the study is the semantic and functional features of the lexico-semantic group of verbs denoting interpersonal relations in the Russian and Chinese languages. The verbal vocabulary representing the category of relationship describes the relationships that arise between people in the form of feelings, judgments and appeals to each other in the course of everyday life. The purpose of the proposed article is to identify the semantic and functional features of the verbs of the lexico-semantic group of interpersonal relations in the system of Russian and Chinese languages. The study revealed similarities and differences in the meaning of these verbs. As the analysis showed, some Chinese verbs do not match the meaning of the verbs of the Russian language. This article also examines the types of semantic changes in the semantic structure of the verbal word form functioning in the context. The main method of studying this group of verbs in Russian and Chinese is the comparative method. The descriptive method and the functional-semantic method, as well as the method of component analysis, were used in the selection and use of linguistic material. The scientific novelty of the study lies in the fact that the verbs of interpersonal relations are still insufficiently studied on the materials of the Russian and Chinese languages. The results of the research can be used in the practice of teaching university courses in such disciplines as cognitive linguistics, linguoculturology, and intercultural communication. The study allows us to conclude that the verbs of interpersonal relationships are quite often used in both languages. The meanings of Chinese and Russian verbs are not always equivalent. Their semantic structures may also differ. The analysis of interlanguage gaps reveals the presence of incomplete lexical correspondence to a foreign word. Some verbal lexicons express interpersonal relationships in their direct meanings, while others develop this ability as a result of semantic modulation and semantic derivation. Interpersonal relationships can be expressed by verbs from other lexico-semantic groups, acquiring the semantics of interpersonal relationships in the context. In conclusion, we note that expressions of interpersonal relationships can also be verb-noun combinations, which, when analyzing various specifiers in the context, indicate the reasons for a positive or negative attitude towards a person.

Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition

Graph convolutional networks (GCNs) have attracted great attention and achieved remarkable performance in skeleton-based action recognition. However, most of the previous works are designed to refine skeleton topology without considering the types of different joints and edges, making them infeasible to represent the semantic information. In this paper, we proposed a dynamic semantic-based graph convolution network (DS-GCN) for skeleton-based human action recognition, where the joints and edge types were encoded in the skeleton topology in an implicit way. Specifically, two semantic modules, the joints type-aware adaptive topology and the edge type-aware adaptive topology, were proposed. Combining proposed semantics modules with temporal convolution, a powerful framework named DS-GCN was developed for skeleton-based action recognition. Extensive experiments in two datasets, NTU-RGB+D and Kinetics-400 show that the proposed semantic modules were generalized enough to be utilized in various backbones for boosting recognition accuracy. Meanwhile, the proposed DS-GCN notably outperformed state-of-the-art methods. The code is released here https://github.com/davelailai/DS-GCN

Real-time semantic segmentation via mutual optimization of spatial details and semantic information

Semantic segmentation is a pivotal task in the field of computer vision, encompassing diverse applications and undergoing continuous development. Despite the growing dominance of deep learning methods in this field, many existing network models suffer from trade-offs between accuracy and computational cost, or between speed and accuracy. In essence, semantic segmentation aims to extract semantic information from deep features and optimize them before upsampling output. However, shallow features tend to contain more detailed information but also more noise, while deep features have strong semantic information but lose some spatial information. To address this issue, we propose a novel mutual optimization strategy based on shallow spatial information and deep semantic information, and construct a details and semantic mutual optimization network (DSMONet). This effectively reduces the noise in the shallow features and guides the deep features to reconstruct the lost spatial information, avoiding cumbersome side auxiliary or complex decoders. The Mutual Optimization Module (MOM) includes Semantic Adjustment Details Module (SADM) and Detail Guided Semantic Module (DGSM), which enables mutual optimization of shallow spatial information and deep semantic information. Comparative evaluations against other methods demonstrate that DSMONet achieves a favorable balance between accuracy and speed. On the Cityscapes dataset, DSMONet achieves performances of 79.3% mean of class-wise intersection-over-union (mIoU)/44.6 frames per second (FPS) and 78.0% mIoU/102 FPS. The code is available at https://github.com/m828/DSMONet.

Semantic congruency modulates the speed-up of multisensory responses

Responses to multisensory signals are often faster compared to their unisensory components. This speed-up is typically attributed to target redundancy in that a correct response can be triggered by one or the other signal. In addition, semantic congruency of signals can also modulate multisensory responses; however, the contribution of semantic content is difficult to isolate as its manipulation commonly changes signal redundancy as well. To disentangle the effects of redundancy and semantic congruency, we manipulated semantic content but kept redundancy constant. We presented semantically congruent/incongruent animal pictures and sounds and asked participants to respond with the same response to two target animals (cats and dogs). We find that the speed-up of multisensory responses is larger for congruent (e.g., barking dogs) than incongruent combinations (e.g., barking cats). We then used a computational modelling approach to analyse audio-visual processing interferences that may underlie the effect. Our data is best described by a model that explains the semantic congruency modulation with a parameter that was previously linked to trial sequence effects, which in our experiment occur from the repetition/switching of both sensory modality and animal category. Yet, a systematic analysis of such trial sequence effects shows that the reported congruency effect is an independent phenomenon. Consequently, we discuss potential contributors to the semantic modulation of multisensory responses.

GeSeNet: A General Semantic-Guided Network With Couple Mask Ensemble for Medical Image Fusion.

At present, multimodal medical image fusion technology has become an essential means for researchers and doctors to predict diseases and study pathology. Nevertheless, how to reserve more unique features from different modal source images on the premise of ensuring time efficiency is a tricky problem. To handle this issue, we propose a flexible semantic-guided architecture with a mask-optimized framework in an end-to-end manner, termed as GeSeNet. Specifically, a region mask module is devised to deepen the learning of important information while pruning redundant computation for reducing the runtime. An edge enhancement module and a global refinement module are presented to modify the extracted features for boosting the edge textures and adjusting overall visual performance. In addition, we introduce a semantic module that is cascaded with the proposed fusion network to deliver semantic information into our generated results. Sufficient qualitative and quantitative comparative experiments (i.e., MRI-CT, MRI-PET, and MRI-SPECT) are deployed between our proposed method and ten state-of-the-art methods, which shows our generated images lead the way. Moreover, we also conduct operational efficiency comparisons and ablation experiments to prove that our proposed method can perform excellently in the field of multimodal medical image fusion. The code is available at https://github.com/lok-18/GeSeNet.

Концепция “захвата земли”: глобальный и национальный аспекты

The correct understanding of the current world political agenda associated with changes in the global agrifood system is accompanied by the development of new analytical models. The present work is also devoted to the study of the “Land Grabbing” concept as one of innovative tools of the theoretical apparatus of political science. Using the method of historical and logical unity, the author evaluates the role of the “Land Grabbing” strategy, in comparison with “Double Movement” theory and the typology of international food regimes. In particular, the article is devoted to the study of the stages of emergence and evolution of this concept, unfamiliar to the Russian academic community. Based on a comparative analysis, all theories used to describe the expropriation of ecosystem resources are compared. As a result of the procedure, the compilation feature of all related concepts is diagnosed, and the hidden discursive disagreement is eliminated. Using the method of critical analysis, the author develops a “Two-phase model of the occupation of control”, which emphasizes the dominant position of the Conflict paradigm – the semantic module of the idea of “Land Grabbing”. In the experimental part of the article, the effectiveness of the “Land Grabbing” concept is verified on a specific example – the agricultural sector of the Russian Federation. Via the method of statistical observation, the author analyzes the dynamics of property rights and systematizes the register of commercial contracts concluded with agricultural land in the period from 2000 to 2023. It is proved that foreign corporations are the ultimate beneficiaries in more than 90% of cases of all land transactions. Relying on the method of secondary data analysis, the author identifies the largest commercial owners of agricultural land and the leading countries in offshore exploitation of the general domestic ecosystem resource. By the visualization method, a “Tree-factor model of Land Grabbing” is constructed, the indicators of which are the processes of Corporatization, Foreignization and Catastrophization. In the final part of the work, the author simulates a predictive scenario for the transformation of the global food system based on a retrospective analysis of international food regimes. At the same time, a legal examination of the strategy for national security of the Russian Federation is conducted. Drawing on the analysis performed, the author formulates recommendations relevant to the current geopolitical situation.

Distance metric-based learning for long-tail object detection

Despite the recent success of general object detection, almost all models perform unsatisfactorily on long-tail datasets. The main cause of performance degradation is the imbalance in the number of positive samples between categories. The traditional approaches can lead to distortion of the classification feature space, which in turn can seriously affect the classification ability of the network. To address the above issues, we propose a novel distance metric-based learning approach for long-tail object detection (LTDL) in this paper. Specifically, we directly use the feature space as the optimization target, thus allowing clearer decision boundaries between classes. In order to optimize the decision boundary, we adjust the intra-class and inter-class distances by Margin Module (MAM). Meanwhile, to further exploit the information provided by the dataset, we introduce supervised information of labels for distance weighting using the Semantic Module (SEM). In addition, to protect the learning of tail samples and optimize the classifier, we propose a Distance-based Equilibrium Loss (DEL). Extensive experiments conducted on the LVIS benchmark have demonstrated the strength of our proposed approach. The experimental results show that our method improves the baseline by 2.9% AP. And our best model can outperform almost all other representative methods.

Remote Sensing Image Super-Resolution via Multi-Scale Texture Transfer Network

As the degradation factors of remote sensing images become increasingly complex, it becomes challenging to infer the high-frequency details of remote sensing images compared to ordinary digital photographs. For super-resolution (SR) tasks, existing deep learning-based single remote sensing image SR methods tend to rely on texture information, leading to various limitations. To fill this gap, we propose a remote sensing image SR algorithm based on a multi-scale texture transfer network (MTTN). The proposed MTTN enhances the texture feature information of reconstructed images by adaptively transferring texture information according to the texture similarity of the reference image. The proposed method adopts a multi-scale texture-matching strategy, which promotes the transmission of multi-scale texture information of remote sensing images and obtains finer-texture information from more relevant semantic modules. Experimental results show that the proposed method outperforms state-of-the-art SR techniques on the Kaggle open-source remote sensing dataset from both quantitative and qualitative perspectives.

MVS‐SLAM: Enhanced multiview geometry for improved semantic RGBD SLAM in dynamic environment

AbstractSimultaneous Localization and Mapping (SLAM) is a crucial technology for intelligent mobile robots to operate successfully in unknown environments. While many excellent SLAM systems have been developed in recent years, most assume that the environment is static, resulting in poor performance in dynamic environments. To address this limitation, we propose multiview stereo (MVS)‐SLAM (MVS‐SLAM), a real‐time semantic RGBD SLAM system with improved‐multiview geometry, built on the RGBD mode of ORB‐SLAM3. MVS‐SLAM tightly integrates semantic and geometric information to tackle the challenges posed by dynamic scenes. To meet the real‐time requirements, the semantic module leverages the latest and fastest object detection network, YOLOv7, to provide semantic prior knowledge for the geometric module. We introduce a novel geometric constraint method that capitalizes on depth images and semantic information to recover three‐dimensional (3D) feature points and initial camera pose. We use a 3D coordinate error threshold to identify dynamic points and remove them using the K‐means clustering algorithm. This approach effectively reduces the impact of dynamic points. We validate MVS‐SLAM using challenging dynamic sequences from the TUM data set, demonstrating that it significantly improves localization accuracy and system robustness in all types of dynamic environments.

Transferencja wiedzy specjalistycznej w zakresie Funduszy Europejskich 2021–2027

This paper attempts to analyse selected structural-semantic properties of the “Priorities of the European Funds for Mazovia Program 2021-2027” in light of the prototype theory of categorization by Eleanor Rosch. A modular framework will be applied to describe prototype effect within texts which define the content framework for initiatives concerning distinct fields of expertise. Two semantic modules will be distinguished: the module of basic discipline comprises salient terms from the field of EU structural funds, whereas the module of secondary discipline includes terms ranging from R&D, digitalization and e-services to small and medium-sized enterprises, etc. The modularity of the two main semantic modules is determined by the cue validity in categories whose objects are denoted by salient lexical entities. A relatively low cue validity within the scope of denotation of salient lexical entities reveals two apparently contradictory tendencies: text authors intend to set the content framework for the initiatives as precisely, i.e. as restrictively, as possible while attempting not to exclude too many initiatives from participation in the funding program. The co-existence of these tendencies makes it possible to expand the set of designata, e.g. if changes need to be made to the scope of support. Specific semantic interdependencies between these tendencies will be described and explained in light of the concept of prototype effect.

Bitemporal Remote Sensing Image Change Detection Network Based on Siamese-Attention Feedback Architecture

Recently, deep learning-based change detection methods for bitemporal remote sensing images have achieved promising results based on fully convolutional neural networks. However, due to the inherent characteristics of convolutional neural networks, if the previous block fails to correctly segment the entire target, erroneous predictions might accumulate in the subsequent blocks, leading to incomplete change detection results in terms of structure. To address this issue, we propose a bitemporal remote sensing image change detection network based on a Siamese-attention feedback architecture, referred to as SAFNet. First, we propose a global semantic module (GSM) on the encoder network, aiming to generate a low-resolution semantic change map to capture the changed objects. Second, we introduce a temporal interaction module (TIM), which is built through each encoding and decoding block, using the feature feedback between two temporal blocks to enhance the network’s perception ability of the entire changed target. Finally, we propose two auxiliary modules—the change feature extraction module (CFEM) and the feature refinement module (FRM)—which are further used to learn the fine boundaries of the changed target. The deep model we propose produced satisfying results in dual-temporal remote sensing image change detection. Extensive experiments on two remote sensing image change detection datasets demonstrate that the SAFNet algorithm exhibits state-of-the-art performance.

PECULIARITIES OF THE UKRAINIAN TRANSLATION OF METAPHORS IN THE FANTASY NOVEL GENRE

The article is devoted to the analysis of the peculiarities of metaphor translation in fiction, in particular in a fantasy novel. Characteristic features of metaphor are considered, namely universality, conceptuality, systematicity. The classification of metaphor types according to the time and space indicator is analyzed, namely ontological metaphor, orientational metaphor, and structural metaphor. The main methods of metaphor translation are given – full translation, addition / omission, replacement, structural transformation, traditional accordance, parallel naming of metaphoricality. Hypothesesconditions for the translation of metaphors are listed on the example of English and Ukrainian languages: 1) metaphors in the attributive function are more characteristic for English than for Ukrainian; 2) phrasal metaphors are more numerous in Ukrainian than in English; 3) conceptual metaphors can be represented in English and Ukrainian by structurally different equivalents and 4) syntactic-functional and lexical-structural differences of metaphorical equivalents in different languages can prompt the translator to resort to semantic modulation or, in particular, descriptive translation. In the next part of the article, examples of metaphors from Stephen King's novel are presented, and metaphors are highlighted, then divided according to the principle of otological, orientational and structural. For each type, translation methods are analyzed and a comment is provided. Thus, ontological metaphors were translated using substitution, omission, addition, full translation, traditional accordance, and structural transformation. To reproduce structural metaphors, the translator chose to use substitution, omission, addition, full translation, the method of traditional accordance, structural transformation, replacement of a lexical component. Orientation metaphors were reproduction by replacing a lexical component, addition and omission, full translation, structural transformation, traditional accordance.

SCE-SLAM: a real-time semantic RGBD SLAM system in dynamic scenes based on spatial coordinate error

Simultaneous localization and mapping (SLAM) is one of the prerequisite technologies for intelligent mobile robots to accomplish various tasks in unknown environments. In recent years, many excellent SLAM systems have emerged, but most of them have a basic assumption that the environment is static, which results in their poor performance in dynamic environments. To solve this problem, this paper presents SCE-SLAM: a novel real-time semantic RGB-D SLAM system that is built on the RGB-D mode of ORB-SLAM3. SCE-SLAM tightly combines semantic and geometric information. Considering the real-time requirements, the semantic module provides semantic prior knowledge for the geometric module using the latest and fastest object detection network YOLOv7. Then, a new geometric constraint method is proposed to filter dynamic feature points. This method takes full advantage of depth images and semantic information to recover three-dimensional (3D) feature points and the initial camera pose. A 3D coordinate error is used as a threshold, and SCE-SLAM removes dynamic points using the K-means clustering algorithm. In this way, SCE-SLAM effectively reduces the impact of dynamic points. Furthermore, we validate SCE-SLAM with challenging dynamic sequences of the TUM dataset. The results demonstrate that SCE-SLAM significantly improves the localization accuracy and system robustness in all kinds of dynamic environments.

Hybrid Contextual Semantic Network for Accurate Segmentation and Detection of Small-Size Stroke Lesions From MRI.

Stroke is a cerebrovascular disease with high mortality and disability rates. The occurrence of the stroke typically produces lesions of different sizes, with the accurate segmentation and detection of small-size stroke lesions being closely related to the prognosis of patients. However, the large lesions are usually correctly identified, the small-size lesions are usually ignored. This paper provides a hybrid contextual semantic network (HCSNet) that can accurately and simultaneously segment and detect small-size stroke lesions from magnetic resonance images. HCSNet inherits the advantages of the encoder-decoder architecture and applies a novel hybrid contextual semantic module that generates high-quality contextual semantic features from the spatial and channel contextual semantic features through the skip connection layer. Moreover, a mixing-loss function is proposed to optimize HCSNet for unbalanced small-size lesions. HCSNet is trained and evaluated on 2D magnetic resonance images produced from the Anatomical Tracings of Lesions After Stroke challenge (ATLAS R2.0). Extensive experiments demonstrate that HCSNet outperforms several other state-of-the-art methods in its ability to segment and detect small-size stroke lesions. Visualization and ablation experiments reveal that the hybrid semantic module improves the segmentation and detection performance of HCSNet.

Knowledge-Enriched Attention Network With Group-Wise Semantic for Visual Storytelling.

As a technically challenging topic, visual storytelling aims at generating an imaginary and coherent story with narrative multi-sentences from a group of relevant images. Existing methods often generate direct and rigid descriptions of apparent image-based contents, because they are not capable of exploring implicit information beyond images. Hence, these schemes could not capture consistent dependencies from holistic representation, impairing the generation of reasonable and fluent stories. To address these problems, a novel knowledge-enriched attention network with group-wise semantic model is proposed. Three main novel components are designed and supported by substantial experiments to reveal practical advantages. First, a knowledge-enriched attention network is designed to extract implicit concepts from external knowledge system, and these concepts are followed by a cascade cross-modal attention mechanism to characterize imaginative and concrete representations. Second, a group-wise semantic module with second-order pooling is developed to explore the globally consistent guidance. Third, a unified one-stage story generation model with encoder-decoder structure is proposed to simultaneously train and infer the knowledge-enriched attention network, group-wise semantic module and multi-modal story generation decoder in an end-to-end fashion. Substantial experiments on the visual storytelling datasets with both objective and subjective evaluation metrics demonstrate the superior performance of the proposed scheme as compared with other state-of-the-art methods. The source code of this work can be found in https://mic.tongji.edu.cn.

Semantic and Relation Modulation for Audio-Visual Event Localization.

We study the problem of localizing audio-visual events that are both audible and visible in a video. Existing works focus on encoding and aligning audio and visual features at the segment level while neglecting informative correlation between segments of the two modalities and between multi-scale event proposals. We propose a novel Semantic and Relation Modulation Network (SRMN) to learn the above correlation and leverage it to modulate the related auditory, visual, and fused features. In particular, for semantic modulation, we propose intra-modal normalization and cross-modal normalization. The former modulates features of a single modality with the event-relevant semantic guidance of the same modality. The latter modulates features of two modalities by establishing and exploiting the cross-modal relationship. For relation modulation, we propose a multi-scale proposal modulating module and a multi-alignment segment modulating module to introduce multi-scale event proposals and enable dense matching between cross-modal segments, which strengthen correlations between successive segments within one proposal and between all segments. With the features modulated by the correlation information regarding audio-visual events, SRMN performs accurate event localization. Extensive experiments conducted on the public AVE dataset demonstrate that our method outperforms the state-of-the-art methods in both supervised event localization and cross-modality localization tasks.

Texture and semantic convolutional auto‐encoder for anomaly detection and segmentation

AbstractAnomaly detection is a challenging task, especially detecting and segmenting tiny defect regions in images without anomaly priors. Although deep encoder‐decoder‐based convolutional neural networks have achieved good anomaly detection results, existing methods operate uniformly on all extracted image features without considering disentangling these features. To fully explore the texture and semantic information of images, A novel unsupervised anomaly detection method is proposed. Specifically, discriminative features are extracted from images by using a deep pre‐trained network, where shallow and deep features are aggregated into texture and semantic modules, respectively. Then, a feature fusion module is developed to interactively enable feature information in two different modules. The texture and semantic segmentation results are obtained by comparing the texture features and semantic features before and after reconstruction, respectively. Finally, an anomaly segmentation module is designed to generate anomaly detection results by integrating the results of the texture and semantic modules by setting a threshold. Experimental results on benchmark datasets for anomaly detection demonstrate that our proposed method can efficiently and effectively detect anomalies, outperforming some state‐of‐the‐art methods by 2.7% and 0.6% in classification and segmentation.

MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding

Understanding urban scenes is a fundamental ability requirement for assisted driving and autonomous vehicles. Most of the available urban scene understanding methods use red-green-blue (RGB) images; however, their segmentation performances are prone to degradation under adverse lighting conditions. Recently, many effective artificial neural networks have been presented for urban scene understanding and have shown that incorporating RGB and thermal (RGB-T) images can improve segmentation accuracy even under unsatisfactory lighting conditions. However, the potential of multimodal feature fusion has not been fully exploited because operations such as simply concatenating the RGB and thermal features or averaging their maps have been adopted. To improve the fusion of multimodal features and the segmentation accuracy, we propose a multitask-aware network (MTANet) with hierarchical multimodal fusion (multiscale fusion strategy) for RGB-T urban scene understanding. We developed a hierarchical multimodal fusion module to enhance feature fusion and built a high-level semantic module to extract semantic information for merging with coarse features at various abstraction levels. Using the multilevel fusion module, we exploited low-, mid-, and high-level fusion to improve segmentation accuracy. The multitask module uses boundary, binary, and semantic supervision to optimize the MTANet parameters. Extensive experiments were performed on two benchmark RGB-T datasets to verify the improved performance of the proposed MTANet compared with state-of-the-art methods. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

As strong as an NPI in LSF, NGT and LIS

Negative polarity items emerge from the interaction between some propertiesof the semantic module of human language and its lexicon. This leads tothe expectation that they should be equally common in spoken and sign language,contrary to what has been documented. We describe the sign UNTIL in French SignLanguage, Italian Sign Language and Sign Language of the Netherlands. We showthat under its punctual reading, UNTIL behaves as a strong negative polarity item,just like English until. We also discuss why more prototypical cases of polarityitems like any or ever are much harder to find in sign language

Semantic Interpretations of Proper Names in Literary Translation: Terry Pratchett’s “Wyrd Sisters” in Bulgarian

Name crafting has been and still is of importance when devising a literary character with certain traits and features that are meant to outstand a character’s personality. Thus, literary names serve as a handy tool in any piece of writing, since they complete their bearers in a discrete, yet a vivid way when given an appropriate name by the author of a piece of writing. As far as fantasy is concerned, the choice of literary names is freer, but still requires more creativity, given the fact that fantasy names can be translated. When rendered from one language into another, names undergo various structural alterations, semantic modulations, or even syntactic reconstructions. Therefore, the current paper aims at analysing literary names in Terry Pratchett’s fantasy novel “Wyrd Sisters” with focus on their rendering into Bulgarian. Etymology and semantic interpretations are to be sought for as well as morphological and syntactic structure of names in both languages of interest in favour of the hypothesis that literary names carry meaning which, when revealed, gives a more concrete idea of a personage in a novel.