Semantic Classification Research Articles

Object-Centric Representation Learning for Video Scene Understanding.

Depth-aware Video Panoptic Segmentation (DVPS) is a challenging task that requires predicting the semantic class and 3D depth of each pixel in a video, while also segmenting and consistently tracking objects across frames. Predominant methodologies treat this as a multi-task learning problem, tackling each constituent task independently, thus restricting their capacity to leverage interrelationships amongst tasks and requiring parameter tuning for each task. To surmount these constraints, we present Slot-IVPS, a new approach employing an object-centric model to acquire unified object representations, thereby facilitating the model's ability to simultaneously capture semantic and depth information. Specifically, we introduce a novel representation, Integrated Panoptic Slots (IPS), to capture both semantic and depth information for all panoptic objects within a video, encompassing background semantics and foreground instances. Subsequently, we propose an integrated feature generator and enhancer to extract depth-aware features, alongside the Integrated Video Panoptic Retriever (IVPR), which iteratively retrieves spatial-temporal coherent object features and encodes them into IPS. The resulting IPS can be effortlessly decoded into an array of video outputs, including depth maps, classifications, masks, and object instance IDs. We undertake comprehensive analyses across four datasets, attaining state-of-the-art performance in both Depth-aware Video Panoptic Segmentation and Video Panoptic Segmentation tasks.

A semantic classification of nominal technical terms in secondary school biology textbooks.

Nominal technical terms (NTTs), as crucial builders for disciplinary knowledge, can cause difficulties for students. However, previous studies have rarely associated NTTs with disciplinary knowledge construction. Apart from that, scholars of English for Specific Purposes (ESP) have mainly focused on making wordlists for one specific discipline based on corpora rather than on meanings. Moreover, the current categorization of technical terms cannot reveal their role in constructing disciplinary knowledge. Against this backdrop, we carried out a corpus-based study to classify NTTs in secondary school biology textbooks and to unveil the knowledge constructed by different types of those NTTs. As a result, we found that NTTs in those textbooks could fall into five major categories: Thing, Activity, Semiotic, Place, and Time. We also found intra-disciplinary differences in NTT distributions. The lexicogrammatical analysis indicates that the five types of NTTs can construct different knowledge. With the findings, we put forward implications for teaching biology in secondary schools.

Spcolor: Semantic prior guided exemplar-based image colorization

Exemplar-based image colorization aims to colorize a target grayscale image based on a color reference image, and the key is to establish accurate pixel-level semantic correspondence between these two images. Previous methods directly search for correspondence over the entire reference image, and this type of global matching is prone to mismatch. Intuitively, a reasonable correspondence should be established between objects which are semantically similar. Motivated by this, we introduce the idea of semantic prior and propose SPColor, a semantic prior guided exemplar-based image colorization framework. Several novel components are systematically designed in SPColor, including a semantic prior guided correspondence network (SPC), a category reduction algorithm (CRA), and a similarity masked perceptual loss (SMP loss). Different from previous methods, SPColor establishes the correspondence between the pixels in the same semantic class locally. In this way, improper correspondence between different semantic classes is explicitly excluded, and the mismatch is obviously alleviated. In addition, SPColor supports region-level class assignments before SPC in the pipeline. With this feature, a category manipulation process (CMP) is proposed as an interactive interface to control colorization, which can also produce more varied colorization results and improve the flexibility of reference selection. Experiments demonstrate that our model outperforms recent state-of-the-art methods both quantitatively and qualitatively on public dataset. Our code is available at https://github.com/viector/spcolor.

Multi-Modal LiDAR Point Cloud Semantic Segmentation with Salience Refinement and Boundary Perception

Point cloud segmentation is essential for scene understanding, which provides advanced information for many applications, such as autonomous driving, robots, and virtual reality. To improve the accuracy and robustness of point cloud segmentation, many researchers have attempted to fuze camera images to complement the color and texture information. The common fusion strategy is the combination of convolutional operations with concatenation, element-wise addition or element-wise multiplication. However, conventional convolutional operators tend to confine the fusion of modal features within their receptive fields, which can be incomplete and limited. In addition, the inability of encoder–decoder segmentation networks to explicitly perceive segmentation boundary information results in semantic ambiguity and classification errors at object edges. These errors are further amplified in point cloud segmentation tasks, significantly affecting the accuracy of point cloud segmentation. To address the above issues, we propose a novel self-attention multi-modal fusion semantic segmentation network for point cloud semantic segmentation. Firstly, to effectively fuze different modal features, we propose a self-cross fusion module (SCF), which models long-range modality dependencies and transfers complementary image information to the point cloud to fully leverage the modality-specific advantages. Secondly, we design the salience refinement module (SR), which calculates the importance of channels in the feature maps and global descriptors to enhance the representation capability of salient modal features. Finally, we propose the local-aware anisotropy loss measure the element-level importance in the data and explicitly provide boundary information for the model, which alleviates the inherent semantic ambiguity problem in segmentation networks. Extensive experiments on two benchmark datasets demonstrate that our proposed method surpasses current state-of-the-art methods.

Automatic Semantic Segmentation and Classification of Remote Sensing Image Data for Flood Detection Using Novel LSTM Neural Network

Automatic Semantic Segmentation and Classification of Remote Sensing Image Data for Flood Detection Using Novel LSTM Neural Network

Adjectives ‘otdalyonnyy’ [distant], ‘priblizitelnyy’ [approximate], and ‘neulovimyy’ [elusive] as Means of Expressing Semantics of Implicit Similarity

This article is dedicated to linguistic means that denote implicit similarity between one object and another. The author aims to identify common patterns in constructing contexts that describe situations of implicit similarity. The study focuses on the specific usage of the adjectives ‘otdalyonnyy’ [distant], ‘priblizitelnyy’ [approximate], and ‘neulovimyy’ [elusive], along with their derived adverbs, as tools for expressing implicit similarity. The research employs definitional, componential, distributional, and contextual analysis methods, utilizing data from linguistic dictionaries and the Russian National Corpus. The analysis of corpus data reveals that situations of implicit similarity can be characterized by four criteria: “semantic class,” “basis for comparison,” “degree of similarity,” and “presence of explanations.” It is demonstrated that the contextual synonyms ‘otdalyonnyy (-o)’ [distant (-ly)], ‘priblizitelnyy (-o)’ [approximate (-ly)], and ‘neulovimyy (-o)’ [elusive (-ly)] exhibit several distinctions in their functioning across various criteria: frequency of use, collocational compatibility, semantic class of the compared objects, basis for comparison, and degree of expressed implicit similarity. In most cases, implicit similarity between objects is not thoroughly motivated but is presented as a ready result of perception, comparison, and interpretation carried out by the speaker.

Domain embeddings for generating complex descriptions of concepts in Italian language.

In this work, we propose a Distributional Semantic resource enriched with linguistic and lexical information extracted from electronic dictionaries. This resource is designed to bridge the gap between the continuous semantic values represented by distributional vectors and the discrete descriptions provided by general semantics theory. Recently, many researchers have focused on the connection between embeddings and a comprehensive theory of semantics and meaning. This often involves translating the representation of word meanings in Distributional Models into a set of discrete, manually constructed properties, such as semantic primitives or features, using neural decoding techniques. Our approach introduces an alternative strategy based on linguistic data. We have developed a collection of domain-specific co-occurrence matrices derived from two sources: a list of Italian nouns classified into four semantic traits and 20 concrete noun sub-categories and Italian verbs classified by their semantic classes. In these matrices, the co-occurrence values for each word are calculated exclusively with a defined set of words relevant to a particular lexical domain. The resource includes 21 domain-specific matrices, one comprehensive matrix, and a Graphical User Interface. Our model facilitates the generation of reasoned semantic descriptions of concepts by selecting matrices directly associated with concrete conceptual knowledge, such as a matrix based on location nouns and the concept of animal habitats. We assessed the utility of the resource through two experiments, achieving promising outcomes in both the automatic classification of animal nouns and the extraction of animal features.

ML Approaches for the Study of Significant Heritage Contexts: An Application on Coastal Landscapes in Sardinia

Remote Sensing (RS) and Geographic Information Science (GIS) techniques are powerful tools for spatial data collection, analysis, management, and digitization within cultural heritage frameworks. Despite their capabilities, challenges remain in automating data semantic classification for conservation purposes. To address this, leveraging airborne Light Detection And Ranging (LiDAR) point clouds, complex spatial analyses, and automated data structuring is crucial for supporting heritage preservation and knowledge processes. In this context, the present contribution investigates the latest Artificial Intelligence (AI) technologies for automating existing LiDAR data structuring, focusing on the case study of Sardinia coastlines. Moreover, the study preliminary addresses automation challenges in the perspective of historical defensive landscapes mapping. Since historical defensive architectures and landscapes are characterized by several challenging complexities—including their association with dark periods in recent history and chronological stratification—their digitization and preservation are highly multidisciplinary issues. This research aims to improve data structuring automation in these large heritage contexts with a multiscale approach by applying Machine Learning (ML) techniques to low-scale 3D Airborne Laser Scanning (ALS) point clouds. The study thus develops a predictive Deep Learning Model (DLM) for the semantic segmentation of sparse point clouds (<10 pts/m2), adaptable to large landscape heritage contexts and heterogeneous data scales. Additionally, a preliminary investigation into object-detection methods has been conducted to map specific fortification artifacts efficiently.

THE TOPONYMY OF THE VILLAGE OF PADESH, BLAGOEVGRAD AREA – SEMANTIC CLASSIFICATION AND STRUCTURAL SPECIFICS

The present text describes the toponymy of the village of Padesh, Blagoevgrad area. It represents a semantic classification of the place names and observes their structural specifics. The text also mentions some word-formation and morphological peculiarities. More than 210 microtoponyms and oykonyms are classified in three main groups. The first group analyses toponyms derived from geographical characteristics or from some other specifics of the place. The group contains 98 names and the analysis shows that 47 of them include geographical terms. The second group observes toponyms reflected by cultural history of Padesh - names related to the village agriculture and forestry, religious concepts and settlement structure. The most of the toponyms are classified as a possessives in the third group. The least of them are formed by а personal name, а nickname or by an adjective. The other ones are names for ownership, derived by proper names and some specific suffixes such as -ица and -ец. The most of the toponyms in that group come from resident/ family names or have as a constituent a possessive adjective. All the names are analyzed as simple toponyms, complex toponyms and compounds. The text finds that the toponymy of the village of Padesh contains mostly simple place names, less often the toponyms formed by an adjective and a noun and just two of the place names are compounds.

Peculiarities of Adverb Placement in English Sentences (exemplified by the adverb "fairly")

The article deals with the problem of adverb placement in English sentences. The paper aims at studying the main tendencies and patterns which influence the choice of the syntactic position of adverbs in English. Special attention is paid to the correlation between the semantic and syntactic features of adverbs. The article also describes possible syntactic positions of adverbs belonging to different semantic classes and the factors which determine the change of the place of the adverb in the sentence. The paper also considers the peculiarities of functioning of adverbs in the sentence based on the analysis of the adverb "fairly". The material for study includes contexts of use of the adverb "fairly" taken from the British National Corpus (BNC). The research uses the following methods: descriptive and statistical methods, methods of contextual analysis and syntactic analysis. The relevance of the subject of the research is due to the fact that in modern English adverbs are characterized by a high level of variability in syntactic placement, and even adverbs belonging to the same semantic class may have different syntactic properties. The analysis showed that "fairly" can be used as an intensifying adverb, an emphasizer, an adverb of manner, an evaluation adverb; in a number of cases it can also acquire additional modal meanings or serve as a speech act-related adverb. Each meaning of the adverb is characterised by its specific variants of syntactic positioning: before the word it modifies, in medial position, in end position and as a parenthetic word detached from the rest of the sentence. The results of the research show the necessity to study the syntactic properties of adverbs in more detail and to clarify their existing dictionary definitions.

The Semantic Function of Modern Chinese “Negation + X” Modal Words Based on Communication Technology and Big Data Corpus

The semantic function of modern Chinese “negation + X” modal words based on communication technology and big data corpus has gained wide attention. As the basis of SOA architecture, Web services provide the key resources for worldwide information transfer and information sharing with their characteristics of loose coupling, platform independence, and data exchange without additional support from third-party hardware and software. However, along with the popularization and improvement of Web service technology, the number and types of Web services in the Internet are also increasing massively, and there are a large number of Web services with various functions, quality and granularity. Therefore, how to quickly and accurately discover Web services that satisfy users’ query requests from a large and complex set of services has become a critical problem to be solved in the current Web service discovery research. Based on the real corpus, this paper analyzes the similarities and differences in the semantic functions of modern Chinese “negation + X” modal words by combining lexicalization and grammatization, cognitive linguistics, systemic functional grammar and other related theories. The experimental results demonstrate that the model is designed for automatic annotation of semantic word classes, and the annotation algorithm based on the hidden horse model, combined with the Viterbi algorithm based on dynamic programming, achieves a correct rate of 94.3% in the closed test and 89.1% in the open test despite the small size of the training corpus and severe data sparsity, and the model fitting effect meets the dynamic expectations.

Semantic Segmentation and Classification of Active and Abandoned Agricultural Fields through Deep Learning in the Southern Peruvian Andes

The monumental scale agricultural infrastructure systems built by Andean peoples during pre-Hispanic times have enabled intensive agriculture in the high-relief, arid/semi-arid landscape of the Southern Peruvian Andes. Large tracts of these labor-intensive systems have been abandoned, however, owing in large measure to a range of demographic, economic, and political crises precipitated by the Spanish invasion of the 16th century CE. This research seeks to better understand the dynamics of agricultural intensification and deintensification in the Andes by inventorying through the semantic segmentation of active and abandoned agricultural fields in satellite imagery across approximately 77,000 km2 of the Southern Peruvian Highlands. While manual digitization of agricultural fields in satellite imagery is time-consuming and labor-intensive, deep learning-based semantic segmentation makes it possible to map and classify en masse Andean agricultural infrastructure. Using high resolution satellite imagery, training and validation data were manually produced in distributed sample areas and were used to transfer-train a convolutional neural network for semantic segmentation. The resulting dataset was compared to manual surveys of the region and results suggest that deep learning can generate larger and more accurate datasets than those generated by hand.

Schooling and language usage matter in heritage bilingual processing: Sortal classifiers in Mandarin

Mandarin sortal classifiers simultaneously encode semantic and grammatical form class cues. Building on a second language (L2) study of Grüter et al. we used the same visual world eye-tracking experiment, designed to examine the relative use of the two cues, testing Mandarin heritage speakers (HSs) living in an English-speaking environment. Given the importance of understanding individual differences, the present study also examined if/how individual HSs may systematically differ as a function of experience with Mandarin. As a group, HSs – like the first language (L1) group in Grüter et al.’s study – showed a clear reliance on the grammatical form class cue. Nevertheless, individual HSs with Mandarin schooling and with more Mandarin social exposure/use showed more reliance on semantics, the L2 pattern observed in Grüter et al. We discuss why this latter pattern might have obtained (formal and informal literacy), while highlighting the value of individual difference approaches to understanding HS processing.

Classification of hyperspectral and LiDAR data by transformer-based enhancement

ABSTRACT The integration of multi-modal data allows for a more accurate representation of the ground characteristics. For a comprehensive interpretation of remote sensing data, existing multi-modal data fusion research mainly focuses on the joint utilization of 3D Light Detection and Ranging (LiDAR) and 2D Hyperspectral Image (HSI) data. However, existing algorithms do not pay much attention to the interaction of high-level semantic information between different modal data before fusion. This paper proposes a novel multi-modal data fusion deep learning network with the Cross-Modal Self-Attentive Feature Fusion Transformer (SAFFT). The framework employs a multi-head self-attention layer to fuse various attention information from multiple heads, effectively enhancing advanced feature information from different modalities for comprehensive integration. Experimental results on the Houston 2013 dataset demonstrate the effectiveness of the proposed method, which achieves an overall accuracy (OA) of 94.3757% in classifying 15 semantic classes.

A Study on Resolving Dynamic analysis using deep learning Framework Logical Methods

Deep learning technologies have gained a great deal of interest in recent months for demonstrating material removal capabilities in a variety of separation, categorization, as well as other machine vision activities. The majority of these deep networks are built employing convolution or completely convolution structures. Our suggested Dynamic and Static gestures System guided by a hand gesture high dimensional data methodology We use a snapshot of a human's thoracic spine to determine the person's depth and the size of the space around his or her hands. In this research, we provide a novel object-based deep-learning framework for semantic segmentation of extremely high-resolution satellite data. In specifically, we leverage object-based prior record by augmenting a fully convolutional neural network's training strategy with an anisotropic diffusion data pre-processing phase and an additional loss term. The goal of this restricted framework is to ensure that similar visual data is assigned to the same semantic class. Here, we employ intermediate steps based on traditional image processing techniques to aid in the resolution of the subsequent problem of classification, detection, or segmentation. Research shows that adding pre- and post-processing steps to a deep learning pipeline can boost model performance over using only the network. Recent advances in UQ algorithms used for deep learning are analysed, and their potential for use in relevance feedback is addressed. It also emphasizes basic research difficulties and directions linked with UQ. Quantifiably, man-made classes with more precise geometry, such as buildings, benefited the most from our strategy, particularly along object borders, indicating the developed approach's enormous potential. The purpose of this paper is to offer an overview of the approaches used inside deep learning frameworks to either appropriately prepare the input (pre-processing) or enhance the outcomes of the network output (post-processing), with an emphasis on digital pathology image analysis.

Analysis of Bi-LSTM CRF Series Models for Semantic Classification of NAVTEX Navigational Safety Messages

NAVTEX is a key component in the Global Maritime Distress and Safety System (GMDSS) that automatically transmits urgent maritime safety information such as navigational and meteorological warnings and forecasts to vessels. For the safe navigation of smart ships, this information from different systems should be shared harmoniously in the Common Maritime Data Structure (CMDS). To share NAVTEX messages as CMDS, words in NAVTEX messages must be semantically classified and placed within the CMDS structure. While traditional parsing methods are typically used to understand message semantics, NAVTEX requires natural language processing methods with deep learning due to its unstructured messages. This paper applies six types of Bi-LSTM CRF-based deep learning models to NAVTEX navigational safety messages and analyzes the results to find the most suitable model for understanding the semantics of each word in NAVTEX messages. This technique can be applied to accurately convey the meaning of NAVTEX navigational safety messages to equipment that requires navigational safety information on smart ships without human intervention.

Improving deep representation learning via auxiliary learnable target coding

Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks. However, existing methods for semantic classification typically employ pre-defined target codes such as the one-hot and the Hadamard codes, which can either fail or be less flexible to model inter-class correlation. In light of this, this paper introduces a novel learnable target coding as an auxiliary regularization of deep representation learning, which can not only incorporate latent dependency across classes but also impose geometric properties of target codes into representation space. Specifically, a margin-based triplet loss and a correlation consistency loss on the proposed target codes are designed to encourage more discriminative representations owing to enlarging between-class margins in representation space and favoring equal semantic correlation of learnable target codes respectively. Experimental results on several popular visual classification and retrieval benchmarks can demonstrate the effectiveness of our method on improving representation learning, especially for imbalanced data.

The principal components of meaning, revisited.

Osgood, Suci, and Tannebaum were the first to attempt to identify the principal components of semantics using dimensional reduction of a high-dimensional model of semantics constructed from human judgments of word relatedness. Modern word-embedding models analyze patterns of words to construct higher dimensional models of semantics that can be similarly subjected to dimensional reduction. Hollis and Westbury characterized the first eight principal components (PCs) of a word-embedding model by correlating them with several well-known lexical measures, such as logged word frequency, age of acquisition, valence, arousal, dominance, and concreteness. The results show some clear differentiation of interpretation between the PCs. Here, we extend this work by analyzing a larger word-embedding matrix using semantic measures initially derived from subjective inspection of the PCs. We then use quantitative analysis to confirm the utility of these subjective measures for predicting PC values and cross-validate them on two word-embedding matrices developed on distinct corpora. Several semantic and word class measures are strongly predictive of early PC values, including first-person and second-person verbs, personal relevance of abstract and concrete words, affect terms, and names of places and people. The predictors of the lowest magnitude PCs generalized well to word-embedding matrices constructed from separate corpora, including matrices constructed using different word-embedding methods. The predictive categories we describe are consistent with Wittgenstein's argument that an autonomous level of social interaction grounds linguistic meaning.

Multimodal Semantic Collaborative Classification for Hyperspectral Images and LiDAR Data

Multimodal Semantic Collaborative Classification for Hyperspectral Images and LiDAR Data

LDVI-SLAM: A Lightweight Monocular Visual-Inertial SLAM System for Dynamic Environments Based on Motion Constraints

Abstract Traditional Simultaneous Localization and Mapping (SLAM) systems are typically based on the assumption of a static environment. However, in practical applications, the presence of moving objects significantly reduces localization accuracy, limiting the system's versatility. To address the challenges of SLAM systems in dynamic environments, the academic community often employs computationally intensive methods such as deep learning, and some algorithms rely on expensive sensors (e.g., LiDAR or RGBD cameras) to obtain depth information. These factors increase computational complexity or hardware costs, complicating practical deployment. To improve localization accuracy and adaptability of SLAM systems in dynamic scenarios while maintaining low deployment costs, this paper proposes a dynamic environment robust monocular inertial SLAM system named LDVI-SLAM. The system uses more cost-effective sensors—monocular cameras and Inertial Measurement Unit (IMU)—along with lightweight computational methods. In LDVI-SLAM, first, the reliability of IMU data is verified. Then, using the ego-motion information provided by the IMU, along with epipolar constraint and an improved Rotation-aware Flow Vector Bound (R-FVB) constraint, dynamic feature points are eliminated. Additionally, this paper proposes a continuous tracking across interval frames method to enhance the distinction between static and dynamic feature points. Experimental results demonstrate that LDVI-SLAM performs effectively in dynamic environments and is easy to deploy. On the VIODE dataset, experimental results show that compared to the deep learning-based DynaSLAM, this method reduces the RMSE (Root Mean Square Error) of absolute trajectory error by 10.3%. Moreover, in terms of speed, under the same computing power, the single-frame processing speed of this method is comparable to ORB-SLAM3 and is two orders of magnitude faster than DynaSLAM, significantly outperforming deep learning-based SLAM algorithms. Experiments on the OMD dataset further prove that this method effectively avoids the risk of semantic classification errors, demonstrating better robustness and generality.