Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Spatial-semantic model.
Статті в журналах з теми "Spatial-semantic model"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Spatial-semantic model".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Li, Wenchao, Xin Liu, Chenggang Yan, Guiguang Ding, Yaoqi Sun, and Jiyong Zhang. "STS: Spatial–Temporal–Semantic Personalized Location Recommendation." ISPRS International Journal of Geo-Information 9, no. 9 (September 8, 2020): 538. http://dx.doi.org/10.3390/ijgi9090538.
Повний текст джерелаАнотація:
The rapidly growing location-based social network (LBSN) has become a promising platform for studying users’ mobility patterns. Many online applications can be built based on such studies, among which, recommending locations is of particular interest. Previous studies have shown the importance of spatial and temporal influences on location recommendation; however, most existing approaches build a universal spatial–temporal model for all users despite the fact that users always demonstrate heterogeneous check-in behavior patterns. In order to realize truly personalized location recommendations, we propose a Gaussian process based model for each user to systematically and non-linearly combine temporal and spatial information to predict the user’s displacement from their currently checked-in location to the next one. The locations whose distances to the user’s current checked-in location are the closest to the predicted displacement are recommended. We also propose an enhancement to take into account category information of locations for semantic-aware recommendation. A unified recommendation framework called spatial–temporal–semantic (STS) is introduced to combine displacement prediction and the semantic-aware enhancement to provide final top-N recommendation. Extensive experiments over real datasets show that the proposed STS framework significantly outperforms the state-of-the-art location recommendation models in terms of precision and mean reciprocal rank (MRR).
2
Han, Dongfeng, Wenhui Li, and Zongcheng Li. "Semantic image classification using statistical local spatial relations model." Multimedia Tools and Applications 39, no. 2 (March 13, 2008): 169–88. http://dx.doi.org/10.1007/s11042-008-0203-6.
Повний текст джерела
3
Abburu, Sunitha. "Geospatial Semantic Query Engine for Urban Spatial Data Infrastructure." International Journal on Semantic Web and Information Systems 15, no. 4 (October 2019): 31–51. http://dx.doi.org/10.4018/ijswis.2019100103.
Повний текст джерелаАнотація:
The research aims at design and develop a special semantic query engine “CityGML Spatial Semantic Web Client (CSSWC)” that facilitates ontology-based multicriteria queries on CityGML data in OGC standard. Presently, there is no spatial method, spatial information infrastructure or any tool to establish the spatial semantic relationship between the 3D city objects in CityGML model. The present work establishes the spatial and semantic relationships between the 3DCityObjects and facilitates ontology-driven spatial semantic query engine on 3D city objects, class with multiple attributes, spatial semantic relations like crosses, nearby, etc., with all other city objects. This is a novel and original work practically implemented generic product for any 3D CityGML model on the globe. A user-friendly form-based interface is designed to compose effective ontology based GeoSPARQL query. CSSWC enhances CityGML applications performance through effective and efficient querying system.
4
Wu, Tao, Jianxin Qin, and Yiliang Wan. "TOST: A Topological Semantic Model for GPS Trajectories Inside Road Networks." ISPRS International Journal of Geo-Information 8, no. 9 (September 12, 2019): 410. http://dx.doi.org/10.3390/ijgi8090410.
Повний текст джерелаАнотація:
To organize trajectory data is a challenging issue for both studies on spatial databases and spatial data mining in the last decade, especially where there is semantic information involved. The high-level semantic features of trajectory data exploit human movement interrelated with geographic context, which is becoming increasingly important in representing and analyzing actual information contained in movements and further processing. This paper argues for a novel semantic trajectory model named TOST. It considers both semantic and geographic information of trajectory data happens along network infrastructure simultaneously. In TOST, a flexible intersection-based semantic representation is designed to express movement typically constrained by urban road networks by combining sets of local semantic details along the time axis. A relational schema based on this model was instantiated against real datasets, which illustrated the effectivity of our proposed model.
5
Mościcka, Albina. "Europeana Data Model in GIS for movable heritage." Geografie 120, no. 4 (2015): 527–41. http://dx.doi.org/10.37040/geografie2015120040527.
Повний текст джерелаАнотація:
The paper proposes to use European resources in GIS as a set of multi-spatial objects with semantic relations to the space. It improves the analysis and visualization of geographic or contextual associations between various items. This paper aims to integrate the Europeana Data Model with GIS for movable heritage based on semantic relations of movable objects with the space. All classes and properties of the EDM were analyzed. Classes and properties containing spatial information were examined and their semantic relations to the space were proposed. All aspects of the relations of movable heritage objects and space were taken into consideration, and examples of the GIS-based pilot resources saved with the use of EDM rules are proposed.
6
Han, Hui-Hui, and Lei Fan. "A New Semantic Segmentation Model for Supplementing More Spatial Information." IEEE Access 7 (2019): 86979–88. http://dx.doi.org/10.1109/access.2019.2915088.
Повний текст джерела
7
Wang, Shiwei, Long Lan, Xiang Zhang, and Zhigang Luo. "GateCap: Gated spatial and semantic attention model for image captioning." Multimedia Tools and Applications 79, no. 17-18 (January 6, 2020): 11531–49. http://dx.doi.org/10.1007/s11042-019-08567-0.
Повний текст джерела
8
Jiang, Peilong, and Xiao Ke. "Lightweight spatial pyramid pooling network for real-time semantic segmentation." Journal of Physics: Conference Series 2234, no. 1 (April 1, 2022): 012012. http://dx.doi.org/10.1088/1742-6596/2234/1/012012.
Повний текст джерелаАнотація:
Abstract In recent years, the state-of-the-art semantic segmentation models have made extremely successful in various challenging scenes. However, the high computation costs of these models make it difficult to deploy to mobile devices. To better serve in computation constraint scenes, the semantic segmentation model should not only have high segmentation performance, but also fast inference speed. In this paper, we proposed an efficient multi-scale context module named LSPPM, which can gather abundant context information at a low computation cost. Base on this, we present a real-time semantic segmentation model called LSPPNet which is specially designed for real-time application. We have done an exhaustive experiment to evaluate LSPPNet in the challenge urban street scenes datasets Cityscapes. Extensive experiment shows that LSPPNet gets a better trade-off between segmentation performance and inference speed. We test LSPPNet on an NVIDIA 2080 super graphics card and it can achieve 75.8% MIoU in Cityscapes test set in real-time speed.
9
Feng, Jiangfan, Xuejun Fu, Yao Zhou, Yuling Zhu, and Xiaobo Luo. "Image-Text Joint Learning for Social Images with Spatial Relation Model." Complexity 2020 (March 28, 2020): 1–11. http://dx.doi.org/10.1155/2020/1543947.
Повний текст джерелаАнотація:
The rapid developments in sensor technology and mobile devices bring a flourish of social images, and large-scale social images have attracted increasing attention to researchers. Existing approaches generally rely on recognizing object instances individually with geo-tags, visual patterns, etc. However, the social image represents a web of interconnected relations; these relations between entities carry semantic meaning and help a viewer differentiate between instances of a substance. This article forms the perspective of the spatial relationship to exploring the joint learning of social images. Precisely, the model consists of three parts: (a) a module for deep semantic understanding of images based on residual network (ResNet); (b) a deep semantic analysis module of text beyond traditional word bag methods; (c) a joint reasoning module from which the text weights obtained using image features on self-attention and a novel tree-based clustering algorithm. The experimental results demonstrate the effectiveness of using Flickr30k and Microsoft COCO datasets. Meanwhile, our method considers spatial relations while matching.
10
Wang, Peng, Jing Yang, and Jianpei Zhang. "A Spatial-Temporal-Semantic Method for Location Prediction in Indoor Spaces." Wireless Communications and Mobile Computing 2022 (March 3, 2022): 1–13. http://dx.doi.org/10.1155/2022/5210005.
Повний текст джерелаАнотація:
While a large number of works concentrated on forecasting trajectories in the outdoor environment, predicting the movement of users in indoor settings has attracted much more attention recently because of the development of smartphones and maturity of Wi-Fi services, e.g., in office buildings. Predicting a user’s movement in indoor spaces can not only help better understand his/her intentions but also improve his/her living experience. While most of the prediction approaches to date tackle the problem by constructing the mathematical models to learn the mobility of objects, they cannot efficiently model the movement of indoor users in the constraint but filled with spatial-temporal-semantic info settings. In order to solve this issue, we propose a frequent subtrajectory-based Markov model that incorporates the spatial location, the temporal aspect, and the shop category context into a unified framework. We first present the frequent subtrajectory algorithm to model and predict adjacent moving points from physical movement perspective, and then, by taking the duration of stay at a specific location into account, we further improve the prediction precision. Finally, by taking location context in the indoor environment (e.g., shop categories) into consideration, we successfully model and predict the user’s future visiting points from the semantic perspective. To validate the effectiveness of our model, we conduct a complete evaluation on a large-scale real-world dataset with more than 261,269 trajectories collected from over 120,000 customers in a shopping mall. The experiment results demonstrate that our method performs significantly superior prediction performance comparing the state-of-the-art models.
11
Ou, Weihua, and Wenjun Xiao. "Structured sparsity model with spatial similarity regularisation for semantic feature selection." International Journal of Advanced Media and Communication 7, no. 2 (2017): 138. http://dx.doi.org/10.1504/ijamc.2017.085941.
Повний текст джерела
12
Xiao, Wenjun, and Weihua Ou. "Structured sparsity model with spatial similarity regularisation for semantic feature selection." International Journal of Advanced Media and Communication 7, no. 2 (2017): 138. http://dx.doi.org/10.1504/ijamc.2017.10006892.
Повний текст джерела
13
Vinasco-Alvarez, D., J. Samuel, S. Servigne, and G. Gesquière. "TOWARDS LIMITING SEMANTIC DATA LOSS IN 4D URBAN DATA SEMANTIC GRAPH GENERATION." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences VIII-4/W2-2021 (October 7, 2021): 37–44. http://dx.doi.org/10.5194/isprs-annals-viii-4-w2-2021-37-2021.
Повний текст джерелаАнотація:
Abstract. To enrich urban digital twins and better understand city evolution, the integration of heterogeneous, spatio-temporal data has become a large area of research in the enrichment of 3D and 4D (3D + Time) semantic city models. These models, which can represent the 3D geospatial data of a city and their evolving semantic relations, may require data-driven integration approaches to provide temporal and concurrent views of the urban landscape. However, data integration often requires the transformation or conversion of data into a single shared data format, which can be prone to semantic data loss. To combat this, this paper proposes a model-centric ontology-based data integration approach towards limiting semantic data loss in 4D semantic urban data transformations to semantic graph formats. By integrating the underlying conceptual models of urban data standards, a unified spatio-temporal data model can be created as a network of ontologies. Transformation tools can use this model to map datasets to interoperable semantic graph formats of 4D city models. This paper will firstly illustrate how this approach facilitates the integration of rich 3D geospatial, spatio-temporal urban data and semantic web standards with a focus on limiting semantic data loss. Secondly, this paper will demonstrate how semantic graphs based on these models can be implemented for spatial and temporal queries toward 4D semantic city model enrichment.
14
Sun, Xia, Li, Shen, and Liu. "A Semantic Expansion Model for VGI Retrieval." ISPRS International Journal of Geo-Information 8, no. 12 (December 17, 2019): 589. http://dx.doi.org/10.3390/ijgi8120589.
Повний текст джерелаАнотація:
OpenStreetMap (OSM) is a representative volunteered geographic information (VGI) project. However, there have been difficulties in retrieving spatial information from OSM. Ontology is an effective knowledge organization and representation method that is often used to enrich the search capabilities of search systems. This paper constructed an OSM ontology model with semantic property items. A query expansion method is also proposed based on the similarity of properties of the ontology model. Moreover, a relevant experiment is conducted using OSM data related to China. The experimental results demonstrate that the recall and precision of the proposed method reach 80% and 87% for geographic information retrieval, respectively. This study provides a method that can be used as a reference for subsequent research on spatial information retrieval.
15
Poux, F., R. Neuville, P. Hallot, and R. Billen. "MODEL FOR SEMANTICALLY RICH POINT CLOUD DATA." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences IV-4/W5 (October 23, 2017): 107–15. http://dx.doi.org/10.5194/isprs-annals-iv-4-w5-107-2017.
Повний текст джерелаАнотація:
This paper proposes an interoperable model for managing high dimensional point clouds while integrating semantics. Point clouds from sensors are a direct source of information physically describing a 3D state of the recorded environment. As such, they are an exhaustive representation of the real world at every scale: 3D reality-based spatial data. Their generation is increasingly fast but processing routines and data models lack of knowledge to reason from information extraction rather than interpretation. The enhanced smart point cloud developed model allows to bring intelligence to point clouds via 3 connected meta-models while linking available knowledge and classification procedures that permits semantic injection. Interoperability drives the model adaptation to potentially many applications through specialized domain ontologies. A first prototype is implemented in Python and PostgreSQL database and allows to combine semantic and spatial concepts for basic hybrid queries on different point clouds.
16
Voelker, Aaron R., Peter Blouw, Xuan Choo, Nicole Sandra-Yaffa Dumont, Terrence C. Stewart, and Chris Eliasmith. "Simulating and Predicting Dynamical Systems With Spatial Semantic Pointers." Neural Computation 33, no. 8 (July 26, 2021): 2033–67. http://dx.doi.org/10.1162/neco_a_01410.
Повний текст джерелаАнотація:
While neural networks are highly effective at learning task-relevant representations from data, they typically do not learn representations with the kind of symbolic structure that is hypothesized to support high-level cognitive processes, nor do they naturally model such structures within problem domains that are continuous in space and time. To fill these gaps, this work exploits a method for defining vector representations that bind discrete (symbol-like) entities to points in continuous topological spaces in order to simulate and predict the behavior of a range of dynamical systems. These vector representations are spatial semantic pointers (SSPs), and we demonstrate that they can (1) be used to model dynamical systems involving multiple objects represented in a symbol-like manner and (2) be integrated with deep neural networks to predict the future of physical trajectories. These results help unify what have traditionally appeared to be disparate approaches in machine learning.
17
Muñoz, José Manuel. "Mental causation and neuroscience: The semantic pruning model." THEORIA. An International Journal for Theory, History and Foundations of Science 33, no. 3 (November 6, 2018): 379. http://dx.doi.org/10.1387/theoria.17312.
Повний текст джерелаАнотація:
In this paper I propose a hypothetical model of mental causation that I call semantic pruning and which could be defined as the causal influence of contents and meanings on the spatial configuration of the network of synapses of an individual. I will be guided by two central principles: 1) the causal influence of the mental occurs by virtue of external semantic constraints and consists in the selective activation of certain physical powers, 2) when the selective activation is continual, it triggers a process of synaptic pruning in the neural and neuromuscular network.
18
Mardiah, Zaqiatul, Afdol Tharik Wastono та Abdul Muta’ali. "A COGNITIVE PERSPECTIVE ON THE ARABIC SPATIAL NOUN/ فَوْقَ /FAWQA/ APPLYING THE PRINCIPLE POLYSEMY MODEL". Paradigma: Jurnal Kajian Budaya 9, № 2 (28 серпня 2019): 154. http://dx.doi.org/10.17510/paradigma.v9i2.286.
Повний текст джерелаАнотація:
<p class="TeksAbstrak">The present paper provides a cognitive linguistics (CL) framework for analyzing the semantic structure of Arabic spatial noun <em>fawqa</em> based on <em>Principled Polysemy Model </em>(PPM) of Tyler and Evans (2003). PPM approach can broaden the narrow view of classical cognitive linguists regarding the semantic variation in the concept of physical-geometry of a preposition. As a polysemous lexeme,<em> fawqa</em> used by Arabian native to express a broad range of meanings, not only spatial relation but also non-spatial relation. The substantial sense of the lexeme is investigated using a large amount of corpus data (<em>corpus.kacst.edu.sa</em>) and applying the five steps of PPM approach. Through this approach, we ascertain that every single usage of <em>fawqa </em>expressing extended senses is always in its semantic network. Our study reveals that the usages of this lexeme in many situations and many cases show non-up down spatial relation, and non-physical relation, but they essentially refer to the primary sense.</p>
19
Cheng, Shuli, Liejun Wang, and Anyu Du. "Deep Semantic-Preserving Reconstruction Hashing for Unsupervised Cross-Modal Retrieval." Entropy 22, no. 11 (November 7, 2020): 1266. http://dx.doi.org/10.3390/e22111266.
Повний текст джерелаАнотація:
Deep hashing is the mainstream algorithm for large-scale cross-modal retrieval due to its high retrieval speed and low storage capacity, but the problem of reconstruction of modal semantic information is still very challenging. In order to further solve the problem of unsupervised cross-modal retrieval semantic reconstruction, we propose a novel deep semantic-preserving reconstruction hashing (DSPRH). The algorithm combines spatial and channel semantic information, and mines modal semantic information based on adaptive self-encoding and joint semantic reconstruction loss. The main contributions are as follows: (1) We introduce a new spatial pooling network module based on tensor regular-polymorphic decomposition theory to generate rank-1 tensor to capture high-order context semantics, which can assist the backbone network to capture important contextual modal semantic information. (2) Based on optimization perspective, we use global covariance pooling to capture channel semantic information and accelerate network convergence. In feature reconstruction layer, we use two bottlenecks auto-encoding to achieve visual-text modal interaction. (3) In metric learning, we design a new loss function to optimize model parameters, which can preserve the correlation between image modalities and text modalities. The DSPRH algorithm is tested on MIRFlickr-25K and NUS-WIDE. The experimental results show that DSPRH has achieved better performance on retrieval tasks.
20
Zhang, Kaihua, Jin Chen, Bo Liu, and Qingshan Liu. "Deep Object Co-Segmentation via Spatial-Semantic Network Modulation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 12813–20. http://dx.doi.org/10.1609/aaai.v34i07.6977.
Повний текст джерелаАнотація:
Object co-segmentation is to segment the shared objects in multiple relevant images, which has numerous applications in computer vision. This paper presents a spatial and semantic modulated deep network framework for object co-segmentation. A backbone network is adopted to extract multi-resolution image features. With the multi-resolution features of the relevant images as input, we design a spatial modulator to learn a mask for each image. The spatial modulator captures the correlations of image feature descriptors via unsupervised learning. The learned mask can roughly localize the shared foreground object while suppressing the background. For the semantic modulator, we model it as a supervised image classification task. We propose a hierarchical second-order pooling module to transform the image features for classification use. The outputs of the two modulators manipulate the multi-resolution features by a shift-and-scale operation so that the features focus on segmenting co-object regions. The proposed model is trained end-to-end without any intricate post-processing. Extensive experiments on four image co-segmentation benchmark datasets demonstrate the superior accuracy of the proposed method compared to state-of-the-art methods. The codes are available at http://kaihuazhang.net/.
21
Bimonte, Sandro, Anne Tchounikine, Maryvonne Miquel, and François Pinet. "When Spatial Analysis Meets OLAP." International Journal of Data Warehousing and Mining 6, no. 4 (October 2010): 33–60. http://dx.doi.org/10.4018/jdwm.2010100103.
Повний текст джерелаАнотація:
Introducing spatial data into multidimensional models leads to the concept of Spatial OLAP (SOLAP). Existing SOLAP models do not completely integrate the semantic component of geographic information (alphanumeric attributes and relationships) or the flexibility of spatial analysis into multidimensional analysis. In this paper, the authors propose the GeoCube model and its associated operators to overcome these limitations. GeoCube enriches the SOLAP concepts of spatial measure and spatial dimension and take into account the semantic component of geographic information. The authors define geographic measures and dimensions as geographic and/or complex objects belonging to hierarchy schemas. GeoCube’s algebra extends SOLAP operators with five new operators, i.e., Classify, Specialize, Permute, OLAP-Buffer and OLAP-Overlay. In addition to classical drill-and-slice OLAP operators, GeoCube provides two operators for navigating the hierarchy of the measures, and two spatial analysis operators that dynamically modify the structure of the geographic hypercube. Finally, to exploit the symmetrical representation of dimensions and measures, GeoCube provides an operator capable of permuting dimension and measure. In this paper, GeoCube is presented using environmental data on the pollution of the Venetian Lagoon.
22
Du, S. Q., S. J. Tang, W. X. Wang, X. M. Li, Y. H. Lu, and R. Z. Guo. "PSCNET: EFFICIENT RGB-D SEMANTIC SEGMENTATION PARALLEL NETWORK BASED ON SPATIAL AND CHANNEL ATTENTION." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-1-2022 (May 17, 2022): 129–36. http://dx.doi.org/10.5194/isprs-annals-v-1-2022-129-2022.
Повний текст джерелаАнотація:
Abstract. RGB-D semantic segmentation algorithm is a key technology for indoor semantic map construction. The traditional RGB-D semantic segmentation network, which always suffer from redundant parameters and modules. In this paper, an improved semantic segmentation network PSCNet is designed to reduce redundant parameters and make models easier to implement. Based on the DeepLabv3+ framework, we have improved the original model in three ways, including attention module selection, backbone simplification, and Atrous Spatial Pyramid Pooling (ASPP) module simplification. The research proposes three improvement ideas to address these issues: using spatial-channel co-attention, removing the last module from Depth Backbone, and redesigning WW-ASPP by Depthwise convolution. Compared to Deeplabv3+, the proposed PSCNet are approximately the same number of parameters, but with a 5% improvement in MIoU. Meanwhile, PSCNet achieved inference at a rate of 47 FPS on RTX3090, which is much faster than state-of-the-art semantic segmentation networks.
23
陈, 立宜. "A Semantic Segmentation Model of 3D Point Clouds Based on Spatial Features." Computer Science and Application 12, no. 02 (2022): 331–37. http://dx.doi.org/10.12677/csa.2022.122033.
Повний текст джерела
24
Paul, Debjyoti, Feifei Li, and Jeff M. Phillips. "Semantic embedding for regions of interest." VLDB Journal 30, no. 3 (February 5, 2021): 311–31. http://dx.doi.org/10.1007/s00778-020-00647-0.
Повний текст джерелаАнотація:
AbstractThe available spatial data are rapidly growing and also diversifying. One may obtain in large quantities information such as annotated point/place of interest (POIs), check-in comments on those POIs, geo-tagged microblog comments, and demarked regions of interest (ROI). All sources interplay with each other, and together build a more complete picture of the spatial and social dynamics at play in a region. However, building a single fused representation of these data entries has been mainly rudimentary, such as allowing spatial joins. In this paper, we extend the concept of semantic embedding for POIs (points of interests) and devise the first semantic embedding of ROIs, and in particular ones that captures both its spatial and its semantic components. To accomplish this, we develop a multipart network model capturing the relationships between the diverse components, and through random-walk-based approaches, use this to embed the ROIs. We demonstrate the effectiveness of this embedding at simultaneously capturing both the spatial and semantic relationships between ROIs through extensive experiments. Applications like popularity region prediction demonstrate the benefit of using ROI embedding as features in comparison with baselines.
25
Zhao, Xin, Liufang Sang, Guiguang Ding, Jungong Han, Na Di, and Chenggang Yan. "Recurrent Attention Model for Pedestrian Attribute Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 9275–82. http://dx.doi.org/10.1609/aaai.v33i01.33019275.
Повний текст джерелаАнотація:
Pedestrian attribute recognition is to predict attribute labels of pedestrian from surveillance images, which is a very challenging task for computer vision due to poor imaging quality and small training dataset. It is observed that many semantic pedestrian attributes to be recognised tend to show spatial locality and semantic correlations by which they can be grouped while previous works mostly ignore this phenomenon. Inspired by Recurrent Neural Network (RNN)’s super capability of learning context correlations and Attention Model’s capability of highlighting the region of interest on feature map, this paper proposes end-to-end Recurrent Convolutional (RC) and Recurrent Attention (RA) models, which are complementary to each other. RC model mines the correlations among different attribute groups with convolutional LSTM unit, while RA model takes advantage of the intra-group spatial locality and inter-group attention correlation to improve the performance of pedestrian attribute recognition. Our RA method combines the Recurrent Learning and Attention Model to highlight the spatial position on feature map and mine the attention correlations among different attribute groups to obtain more precise attention. Extensive empirical evidence shows that our recurrent model frameworks achieve state-of-the-art results, based on pedestrian attribute datasets, i.e. standard PETA and RAP datasets.
26
Cui, Wei, Xin He, Meng Yao, Ziwei Wang, Yuanjie Hao, Jie Li, Weijie Wu, et al. "Knowledge and Spatial Pyramid Distance-Based Gated Graph Attention Network for Remote Sensing Semantic Segmentation." Remote Sensing 13, no. 7 (March 30, 2021): 1312. http://dx.doi.org/10.3390/rs13071312.
Повний текст джерелаАнотація:
The pixel-based semantic segmentation methods take pixels as recognitions units, and are restricted by the limited range of receptive fields, so they cannot carry richer and higher-level semantics. These reduce the accuracy of remote sensing (RS) semantic segmentation to a certain extent. Comparing with the pixel-based methods, the graph neural networks (GNNs) usually use objects as input nodes, so they not only have relatively small computational complexity, but also can carry richer semantic information. However, the traditional GNNs are more rely on the context information of the individual samples and lack geographic prior knowledge that reflects the overall situation of the research area. Therefore, these methods may be disturbed by the confusion of “different objects with the same spectrum” or “violating the first law of geography” in some areas. To address the above problems, we propose a remote sensing semantic segmentation model called knowledge and spatial pyramid distance-based gated graph attention network (KSPGAT), which is based on prior knowledge, spatial pyramid distance and a graph attention network (GAT) with gating mechanism. The model first uses superpixels (geographical objects) to form the nodes of a graph neural network and then uses a novel spatial pyramid distance recognition algorithm to recognize the spatial relationships. Finally, based on the integration of feature similarity and the spatial relationships of geographic objects, a multi-source attention mechanism and gating mechanism are designed to control the process of node aggregation, as a result, the high-level semantics, spatial relationships and prior knowledge can be introduced into a remote sensing semantic segmentation network. The experimental results show that our model improves the overall accuracy by 4.43% compared with the U-Net Network, and 3.80% compared with the baseline GAT network.
27
Ben Mahfoudh, Houssem, Ashley Caselli, and Giovanna Di Marzo Serugendo. "Learning-Based Coordination Model for On-the-Fly Self-Composing Services Using Semantic Matching." Journal of Sensor and Actuator Networks 10, no. 1 (January 20, 2021): 5. http://dx.doi.org/10.3390/jsan10010005.
Повний текст джерелаАнотація:
Forecasts announce that the number of connected objects will exceed 20 billion by 2025. Objects, such as sensors, drones or autonomous cars participate in pervasive applications of various domains ranging from smart cities, quality of life, transportation, energy, business or entertainment. These inter-connected devices provide storage, computing and activation capabilities currently under-exploited. To this end, we defined “Spatial services”, a new generation of services seamlessly supporting users in their everyday life by providing information or specific actions. Spatial services leverage IoT, exploit devices capabilities (sensing, acting), the data they locally store at different time and geographic locations, and arise from the spontaneous interactions among those devices. Thanks to a learning-based coordination model, and without any pre-designed composition, reliable and pertinent spatial services dynamically and fully automatically arise from the self-composition of available services provided by connected devices. In this paper, we show how we extended our learning-based coordination model with semantic matching, enhancing syntactic self-composition with semantic reasoning. The implementation of our coordination model results in a learning-based semantic middleware. We validated our approach on various experiments: deployments of the middleware in various settings; instantiation of a specific scenario and various other case studies; experiments with hundreds of synthetic services; and specific experiments for setting up key learning parameters. We also show how the learning-based coordination model using semantic matching favours service composition, by exploiting three ontological constructions (is-a, isComposedOf, and equivalentTo), de facto removing the syntactic barrier preventing pertinent compositions to arise. Spatial services arise from the interactions of various objects, provide complex and highly adaptive services to users in seamless way, and are pertinent in a variety of domains such as smart cities or emergency situations.
28
Ploux, Sabine, and Hyungsuk Ji. "A Model for Matching Semantic Maps between Languages (French/English, English/French)." Computational Linguistics 29, no. 2 (June 2003): 155–78. http://dx.doi.org/10.1162/089120103322145298.
Повний текст джерелаАнотація:
This article describes a spatial model for matching semantic values between two languages, French and English. Based on semantic similarity links, the model constructs a map that represents a word in the source language. Then the algorithm projects the map values onto a space in the target language. The new space abides by the semantic similarity links specific to the second language. Then the two maps are projected onto the same plane in order to detect overlapping values. For instructional purposes, the different steps are presented here using a few examples. The entire set of results is available at the following address: http://dico.isc.cnrs.fr .
29
Dobesova, Zdena. "Cognition of Graphical Notation for Processing Data in ERDAS IMAGINE." ISPRS International Journal of Geo-Information 10, no. 7 (July 15, 2021): 486. http://dx.doi.org/10.3390/ijgi10070486.
Повний текст джерелаАнотація:
This article presents an evaluation of the ERDAS IMAGINE Spatial Model Editor from the perspective of effective cognition. Workflow models designed in Spatial Model Editor are used for the automatic processing of remote sensing data. The process steps are designed as a chain of operations in the workflow model. The functionalities of the Spatial Model Editor and the visual vocabulary are both important for users. The cognitive quality of the visual vocabulary increases the comprehension of workflows during creation and utilization. The visual vocabulary influences the user’s exploitation of workflow models. The complex Physics of Notations theory was applied to the visual vocabulary on ERDAS IMAGINE Spatial Model Editor. The results were supplemented and verified using the eye-tracking method. The evaluation of user gaze and the movement of the eyes above workflow models brought real insight into the user’s cognition of the model. The main findings are that ERDAS Spatial Model Editor mostly fulfils the requirements for effective cognition of visual vocabulary. Namely, the semantic transparency and dual coding of symbols are very high, according to the Physics of Notations theory. The semantic transparency and perceptual discriminability of the symbols are verified through eye-tracking. The eye-tracking results show that the curved connector lines adversely affect the velocity of reading and produce errors. The application of the Physics of Notations theory and the eye-tracking method provides a useful evaluation of graphical notation as well as recommendations for the user design of workflow models in their practice.
30
Liao, Yong, and Qiong Liu. "Multi-Level and Multi-Scale Feature Aggregation Network for Semantic Segmentation in Vehicle-Mounted Scenes." Sensors 21, no. 9 (May 9, 2021): 3270. http://dx.doi.org/10.3390/s21093270.
Повний текст джерелаАнотація:
The main challenges of semantic segmentation in vehicle-mounted scenes are object scale variation and trading off model accuracy and efficiency. Lightweight backbone networks for semantic segmentation usually extract single-scale features layer-by-layer only by using a fixed receptive field. Most modern real-time semantic segmentation networks heavily compromise spatial details when encoding semantics, and sacrifice accuracy for speed. Many improving strategies adopt dilated convolution and add a sub-network, in which either intensive computation or redundant parameters are brought. We propose a multi-level and multi-scale feature aggregation network (MMFANet). A spatial pyramid module is designed by cascading dilated convolutions with different receptive fields to extract multi-scale features layer-by-layer. Subseqently, a lightweight backbone network is built by reducing the feature channel capacity of the module. To improve the accuracy of our network, we design two additional modules to separately capture spatial details and high-level semantics from the backbone network without significantly increasing the computation cost. Comprehensive experimental results show that our model achieves 79.3% MIoU on the Cityscapes test dataset at a speed of 58.5 FPS, and it is more accurate than SwiftNet (75.5% MIoU). Furthermore, the number of parameters of our model is at least 53.38% less than that of other state-of-the-art models.
31
Zhu, Qiqi, Yanfei Zhong, and Liangpei Zhang. "SCENE CLASSFICATION BASED ON THE SEMANTIC-FEATURE FUSION FULLY SPARSE TOPIC MODEL FOR HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGERY." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B7 (June 21, 2016): 451–57. http://dx.doi.org/10.5194/isprsarchives-xli-b7-451-2016.
Повний текст джерелаАнотація:
Topic modeling has been an increasingly mature method to bridge the semantic gap between the low-level features and high-level semantic information. However, with more and more high spatial resolution (HSR) images to deal with, conventional probabilistic topic model (PTM) usually presents the images with a dense semantic representation. This consumes more time and requires more storage space. In addition, due to the complex spectral and spatial information, a combination of multiple complementary features is proved to be an effective strategy to improve the performance for HSR image scene classification. But it should be noticed that how the distinct features are fused to fully describe the challenging HSR images, which is a critical factor for scene classification. In this paper, a semantic-feature fusion fully sparse topic model (SFF-FSTM) is proposed for HSR imagery scene classification. In SFF-FSTM, three heterogeneous features – the mean and standard deviation based spectral feature, wavelet based texture feature, and dense scale-invariant feature transform (SIFT) based structural feature are effectively fused at the latent semantic level. The combination of multiple semantic-feature fusion strategy and sparse based FSTM is able to provide adequate feature representations, and can achieve comparable performance with limited training samples. Experimental results on the UC Merced dataset and Google dataset of SIRI-WHU demonstrate that the proposed method can improve the performance of scene classification compared with other scene classification methods for HSR imagery.
32
Zhu, Qiqi, Yanfei Zhong, and Liangpei Zhang. "SCENE CLASSFICATION BASED ON THE SEMANTIC-FEATURE FUSION FULLY SPARSE TOPIC MODEL FOR HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGERY." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B7 (June 21, 2016): 451–57. http://dx.doi.org/10.5194/isprs-archives-xli-b7-451-2016.
Повний текст джерелаАнотація:
Topic modeling has been an increasingly mature method to bridge the semantic gap between the low-level features and high-level semantic information. However, with more and more high spatial resolution (HSR) images to deal with, conventional probabilistic topic model (PTM) usually presents the images with a dense semantic representation. This consumes more time and requires more storage space. In addition, due to the complex spectral and spatial information, a combination of multiple complementary features is proved to be an effective strategy to improve the performance for HSR image scene classification. But it should be noticed that how the distinct features are fused to fully describe the challenging HSR images, which is a critical factor for scene classification. In this paper, a semantic-feature fusion fully sparse topic model (SFF-FSTM) is proposed for HSR imagery scene classification. In SFF-FSTM, three heterogeneous features – the mean and standard deviation based spectral feature, wavelet based texture feature, and dense scale-invariant feature transform (SIFT) based structural feature are effectively fused at the latent semantic level. The combination of multiple semantic-feature fusion strategy and sparse based FSTM is able to provide adequate feature representations, and can achieve comparable performance with limited training samples. Experimental results on the UC Merced dataset and Google dataset of SIRI-WHU demonstrate that the proposed method can improve the performance of scene classification compared with other scene classification methods for HSR imagery.
33
Liu, Shuo, Wenrui Ding, Chunhui Liu, Yu Liu, Yufeng Wang, and Hongguang Li. "ERN: Edge Loss Reinforced Semantic Segmentation Network for Remote Sensing Images." Remote Sensing 10, no. 9 (August 22, 2018): 1339. http://dx.doi.org/10.3390/rs10091339.
Повний текст джерелаАнотація:
The semantic segmentation of remote sensing images faces two major challenges: high inter-class similarity and interference from ubiquitous shadows. In order to address these issues, we develop a novel edge loss reinforced semantic segmentation network (ERN) that leverages the spatial boundary context to reduce the semantic ambiguity. The main contributions of this paper are as follows: (1) we propose a novel end-to-end semantic segmentation network for remote sensing, which involves multiple weighted edge supervisions to retain spatial boundary information; (2) the main representations of the network are shared between the edge loss reinforced structures and semantic segmentation, which means that the ERN simultaneously achieves semantic segmentation and edge detection without significantly increasing the model complexity; and (3) we explore and discuss different ERN schemes to guide the design of future networks. Extensive experimental results on two remote sensing datasets demonstrate the effectiveness of our approach both in quantitative and qualitative evaluation. Specifically, the semantic segmentation performance in shadow-affected regions is significantly improved.
34
Jian, Yang, Jinhong Li, Lu Wei, Lei Gao, and Fuqi Mao. "Spatiotemporal DeepWalk Gated Recurrent Neural Network: A Deep Learning Framework for Traffic Learning and Forecasting." Journal of Advanced Transportation 2022 (April 18, 2022): 1–11. http://dx.doi.org/10.1155/2022/4260244.
Повний текст джерелаАнотація:
As a typical spatiotemporal problem, there are three main challenges in traffic forecasting. First, the road network is a nonregular topology, and it is difficult to extract complex spatial dependence accurately. Second, there are short- and long-term dependencies between traffic dates. Third, there are many other factors besides the influence of spatiotemporal dependence, such as semantic characteristics. To address these issues, we propose a spatiotemporal DeepWalk gated recurrent unit model (ST-DWGRU), a deep learning framework that fuses spatial, temporal, and semantic features for traffic speed forecasting. In the framework, the spatial dependency between nodes of an entire road network is extracted by graph convolutional network (GCN), whereas the temporal dependency between speeds is captured by a gated recurrent unit network (GRU). DeepWalk is used to extract semantic information from road networks. Three publicly available datasets with different time granularities of 15, 30, and 60 min are used to validate the short- and long-time prediction effect of this model. The results show that the ST-DWGRU model significantly outperforms the state-of-the-art baselines.
35
Bing, He, Xu Zhifeng, Xu Yangjie, Hu Jinxing, and Ma Zhanwu. "Integrating Semantic Zoning Information with the Prediction of Road Link Speed Based on Taxi GPS Data." Complexity 2020 (November 7, 2020): 1–14. http://dx.doi.org/10.1155/2020/6939328.
Повний текст джерелаАнотація:
Road link speed is one of the important indicators for traffic states. In order to incorporate the spatiotemporal dynamics and correlation characteristics of road links into speed prediction, this paper proposes a method based on LDA and GCN. First, we construct a trajectory dataset from map-matched GPS location data of taxis. Then, we use the LDA algorithm to extract the semantic function vectors of urban zones and quantify the spatial dynamic characteristics of road links based on taxi trajectories. Finally, we add semantic function vectors to the dataset and train a graph convolutional network to learn the spatial and temporal dependencies of road links. The learned model is used to predict the future speed of road links. The proposed method is compared with six baseline models on the same dataset generated by GPS equipped on taxis in Shenzhen, China, and the results show that our method has better prediction performance when semantic zoning information is added. Both composite and single-valued semantic zoning information can improve the performance of graph convolutional networks by 6.46% and 8.35%, respectively, while the baseline machine learning models work only for single-valued semantic zoning information on the experimental dataset.
36
Li, C., X. Zhu, W. Guo, Y. Liu, and H. Huang. "RESEARCH ON EXTENSION OF SPARQL ONTOLOGY QUERY LANGUAGE CONSIDERING THE COMPUTATION OF INDOOR SPATIAL RELATIONS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-4/W5 (May 11, 2015): 67–73. http://dx.doi.org/10.5194/isprsarchives-xl-4-w5-67-2015.
Повний текст джерелаАнотація:
A method suitable for indoor complex semantic query considering the computation of indoor spatial relations is provided According to the characteristics of indoor space. This paper designs ontology model describing the space related information of humans, events and Indoor space objects (e.g. Storey and Room) as well as their relations to meet the indoor semantic query. The ontology concepts are used in IndoorSPARQL query language which extends SPARQL syntax for representing and querying indoor space. And four types specific primitives for indoor query, "Adjacent", "Opposite", "Vertical" and "Contain", are defined as query functions in IndoorSPARQL used to support quantitative spatial computations. Also a method is proposed to analysis the query language. Finally this paper adopts this method to realize indoor semantic query on the study area through constructing the ontology model for the study building. The experimental results show that the method proposed in this paper can effectively support complex indoor space semantic query.
37
Song, Niu, and Li. "Combinatorial Spatial Data Model for Building Fire Simulation and Analysis." ISPRS International Journal of Geo-Information 8, no. 9 (September 12, 2019): 408. http://dx.doi.org/10.3390/ijgi8090408.
Повний текст джерелаАнотація:
Building fire is a complex geographic process related to the indoor spatial environment, a smart spatial data model can accurately describe the spatial-temporal information of a building fire scene, which is important for modeling a fire process. With the development of fire dynamics and computer science, many building fire models have been proposed and widely used. However, the spatial representation of these models is relatively weak. In this study, a fire process modeled via the Fire Dynamics Simulator (FDS) and the requirements of a spatial data model are initially analyzed. Then, a new spatial data model named the Combinatorial Spatial Data Model (CSDM) is combined with Geographic Information System (GIS). The key features of the CSDM, which include spatial, semantic, topological, event and state representations of a building fire scene modeled via the CSDM are subsequently presented. In addition, the Unified Modeling Language (UML) class diagram of the CSDM is also presented, and then experiments with a simplified building are conducted as a CSDM implementation case. A method of transferring data from the CSDM to FDS and a building fire analysis approach using the CSDM are subsequently proposed.
38
Yao, Sidan, Xiao Ling, Fiona Nueesch, Gerhard Schrotter, Simon Schubiger, Zheng Fang, Long Ma, and Zhen Tian. "Maintaining Semantic Information across Generic 3D Model Editing Operations." Remote Sensing 12, no. 2 (January 20, 2020): 335. http://dx.doi.org/10.3390/rs12020335.
Повний текст джерелаАнотація:
Many of today’s data models for 3D applications, such as City Geography Markup Language (CityGML) or Industry Foundation Classes (IFC) encode rich semantic information in addition to the traditional geometry and materials representation. However, 3D editing techniques fall short of maintaining the semantic information across edit operations if they are not tailored to a specific data model. While semantic information is often lost during edit operations, geometry, UV mappings, and materials are usually maintained. This article presents a data model synchronization method that preserves semantic information across editing operation relying only on geometry, UV mappings, and materials. This enables easy integration of existing and future 3D editing techniques with rich data models. The method links the original data model to the edited geometry using point set registration, recovering the existing information based on spatial and UV search methods, and automatically labels the newly created geometry. An implementation of a Level of Detail 3 (LoD3) building editor for the Virtual Singapore project, based on interactive push-pull and procedural generation of façades, verified the method with 30 common editing tasks. The implementation synchronized changes in the 3D geometry with a CityGML data model and was applied to more than 100 test buildings.
39
Huang, Tianxi, Dongdong Wu, Guiduo Duan, and Hao Huang. "Multi-label Image Classification Model via Label Correlation Matrix." Journal of Physics: Conference Series 2216, no. 1 (March 1, 2022): 012107. http://dx.doi.org/10.1088/1742-6596/2216/1/012107.
Повний текст джерелаАнотація:
Abstract Multi-label classification is one of the most essential tasks of computer vision. In the multi-label image classification model, using the correlation between labels is a powerful method for improving the classification effectiveness of the model. However, common methods ignore the interrelationship between the label pairs. On the other hand, introducing a spatial attention mechanism into the model could also improve the classification effectiveness of the model. However, most methods that use the attention mechanism module do not use the correlation information between labels. To solve these issues, we propose a novel multi-label image classification model using the label correlation in the paper. Our model generates label word vectors based on the BERT model that can describe the potential relationship between labels. And then we combine these vectors with static statistics information on labels to construct a new label correlation matrix. Moreover, we introduce label semantic information into the spatial attention mechanism. With the semantic information, the generated spatial attention map could focus on the image feature regions with label correlation, and complete the accurate classification of the model. On the Microsoft COCO data set, this model achieves the best score of 84.3% on mAP, which shows the effectiveness of our model.
40
He, Tieke, Hongzhi Yin, Zhenyu Chen, Xiaofang Zhou, Shazia Sadiq, and Bin Luo. "A Spatial-Temporal Topic Model for the Semantic Annotation of POIs in LBSNs." ACM Transactions on Intelligent Systems and Technology 8, no. 1 (October 3, 2016): 1–24. http://dx.doi.org/10.1145/2905373.
Повний текст джерела
41
Sun, X. "MULTILEVEL SEMANTIC MODELLING OF URBAN BUILDING SPACE BASED ON THE GEOMETRIC CHARACTERISTICS IN 3D ENVIRONMENT." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-4 (September 19, 2018): 603–7. http://dx.doi.org/10.5194/isprs-archives-xlii-4-603-2018.
Повний текст джерелаАнотація:
<p><strong>Abstract.</strong> Data model is the basis of all the functions of geographic information system. As the land use structure has become more and more complicated in cities, the traditional geometric model are not able to satisfy the increasing demands of precise urban form recognition and space management. Against the shortcomings, we propose to construct a multilevel semantic model for better description of the spatial composition of each building and the relationships among different buildings. Based on the 3D surface models constructed with photogrammetry and remote sensing methods, the semantic model is generated to depict the urban building space hierarchically, from stories, buildings, subareas to the entire city zone. On the one hand, to figure out the stories of each building, the geometric 3D model is segmented vertically with reference to the compositional structures and spatial distributions of the functional features on the surfaces. On the other hand, to determine the subareas of the city, the buildings are grouped into meaningful clusters according to their geometric shape characteristics. Experiments were conducted on a small district with both commercial and residential buildings, and the effectiveness of the proposed approach and usage of the semantic model were demonstrated.</p>
42
Li, Peng, Dezheng Zhang, Aziguli Wulamu, Xin Liu, and Peng Chen. "Semantic Relation Model and Dataset for Remote Sensing Scene Understanding." ISPRS International Journal of Geo-Information 10, no. 7 (July 17, 2021): 488. http://dx.doi.org/10.3390/ijgi10070488.
Повний текст джерелаАнотація:
A deep understanding of our visual world is more than an isolated perception on a series of objects, and the relationships between them also contain rich semantic information. Especially for those satellite remote sensing images, the span is so large that the various objects are always of different sizes and complex spatial compositions. Therefore, the recognition of semantic relations is conducive to strengthen the understanding of remote sensing scenes. In this paper, we propose a novel multi-scale semantic fusion network (MSFN). In this framework, dilated convolution is introduced into a graph convolutional network (GCN) based on an attentional mechanism to fuse and refine multi-scale semantic context, which is crucial to strengthen the cognitive ability of our model Besides, based on the mapping between visual features and semantic embeddings, we design a sparse relationship extraction module to remove meaningless connections among entities and improve the efficiency of scene graph generation. Meanwhile, to further promote the research of scene understanding in remote sensing field, this paper also proposes a remote sensing scene graph dataset (RSSGD). We carry out extensive experiments and the results show that our model significantly outperforms previous methods on scene graph generation. In addition, RSSGD effectively bridges the huge semantic gap between low-level perception and high-level cognition of remote sensing images.
43
Rodrigues, Edilson J., Paulo E. Santos, Marcos Lopes, Brandon Bennett, and Paul E. Oppenheimer. "Standpoint semantics for polysemy in spatial prepositions." Journal of Logic and Computation 30, no. 2 (January 11, 2020): 635–61. http://dx.doi.org/10.1093/logcom/exz034.
Повний текст джерелаАнотація:
Abstract In this paper, we present a formalism for handling polysemy in spatial expressions based on supervaluation semantics called standpoint semantics for polysemy (SSP). The goal of this formalism is, given a prepositional phrase, to define its possible spatial interpretations. For this, we propose to characterize spatial prepositions by means of a triplet $\langle $image schema, semantic feature, spatial axis$\rangle $. The core of SSP is predicate grounding theories, which are formulas of a first-order language that define a spatial preposition through the semantic features of its trajector and landmark. Precisifications are also established, which are a set of formulae of a qualitative spatial reasoning formalism that aims to provide the spatial characterization of the trajector with respect to the landmark. In addition to the theoretical model, we also present results of a computational implementation of SSP for the preposition ‘in’.
44
Xu, Mingying, Junping Du, Zeli Guan, Zhe Xue, Feifei Kou, Lei Shi, Xin Xu, and Ang Li. "A Multi-RNN Research Topic Prediction Model Based on Spatial Attention and Semantic Consistency-Based Scientific Influence Modeling." Computational Intelligence and Neuroscience 2021 (December 18, 2021): 1–15. http://dx.doi.org/10.1155/2021/1766743.
Повний текст джерелаАнотація:
Computer science discipline includes many research fields, which mutually influence and promote each other’s development. This poses two great challenges of predicting the research topics of each research field. One is how to model fine-grained topic representation of a research field. The other is how to model research topic of different fields and keep the semantic consistency of research topics when learning the scientific influence context from other related fields. Unfortunately, the existing research topic prediction approaches cannot handle these two challenges. To solve these problems, we employ multiple different Recurrent Neural Network chains which model research topics of different fields and propose a research topic prediction model based on spatial attention and semantic consistency-based scientific influence modeling. Spatial attention is employed in field topic representation which can selectively extract the attributes from the field topics to distinguish the importance of field topic attributes. Semantic consistency-based scientific influence modeling maps research topics of different fields to a unified semantic space to obtain the scientific influence context of other related fields. Extensive experiment results on five related research fields in the computer science (CS) discipline show that the proposed model is superior to the most advanced methods and achieves good topic prediction performance.
45
Cao, Yuchen, Lan Hu, and Laurent Kneip. "Representations and Benchmarking of Modern Visual SLAM Systems." Sensors 20, no. 9 (April 30, 2020): 2572. http://dx.doi.org/10.3390/s20092572.
Повний текст джерелаАнотація:
Simultaneous Localisation And Mapping (SLAM) has long been recognised as a core problem to be solved within countless emerging mobile applications that require intelligent interaction or navigation in an environment. Classical solutions to the problem primarily aim at localisation and reconstruction of a geometric 3D model of the scene. More recently, the community increasingly investigates the development of Spatial Artificial Intelligence (Spatial AI), an evolutionary paradigm pursuing a simultaneous recovery of object-level composition and semantic annotations of the recovered 3D model. Several interesting approaches have already been presented, producing object-level maps with both geometric and semantic properties rather than just accurate and robust localisation performance. As such, they require much broader ground truth information for validation purposes. We discuss the structure of the representations and optimisation problems involved in Spatial AI, and propose new synthetic datasets that, for the first time, include accurate ground truth information about the scene composition as well as individual object shapes and poses. We furthermore propose evaluation metrics for all aspects of such joint geometric-semantic representations and apply them to a new semantic SLAM framework. It is our hope that the introduction of these datasets and proper evaluation metrics will be instrumental in the evaluation of current and future Spatial AI systems and as such contribute substantially to the overall research progress on this important topic.
46
Wang, Yi, Wenke Yu, and Zhice Fang. "Multiple Kernel-Based SVM Classification of Hyperspectral Images by Combining Spectral, Spatial, and Semantic Information." Remote Sensing 12, no. 1 (January 1, 2020): 120. http://dx.doi.org/10.3390/rs12010120.
Повний текст джерелаАнотація:
In this study, we present a hyperspectral image classification method by combining spectral, spatial, and semantic information. The main steps of the proposed method are summarized as follows: First, principal component analysis transform is conducted on an original image to produce its extended morphological profile, Gabor features, and superpixel-based segmentation map. To model spatial information, the extended morphological profile and Gabor features are used to represent structure and texture features, respectively. Moreover, the mean filtering is performed within each superpixel to maintain the homogeneity of the spatial features. Then, the k-means clustering and the entropy rate superpixel segmentation are combined to produce semantic feature vectors by using a bag of visual-words model for each superpixel. Next, three kernel functions are constructed to describe the spectral, spatial, and semantic information, respectively. Finally, the composite kernel technique is used to fuse all the features into a multiple kernel function that is fed into a support vector machine classifier to produce a final classification map. Experiments demonstrate that the proposed method is superior to the most popular kernel-based classification methods in terms of both visual inspection and quantitative analysis, even if only very limited training samples are available.
47
Yokota, Masao. "Aware Computing in Spatial Language Understanding Guided by Cognitively Inspired Knowledge Representation." Applied Computational Intelligence and Soft Computing 2012 (2012): 1–10. http://dx.doi.org/10.1155/2012/184103.
Повний текст джерелаАнотація:
Mental image directed semantic theory (MIDST) has proposed an omnisensory mental image model and its description languageLmd. This language is designed to represent and compute human intuitive knowledge of space and can provide multimedia expressions with intermediate semantic descriptions in predicate logic. It is hypothesized that such knowledge and semantic descriptions are controlled by human attention toward the world and therefore subjective to each human individual. This paper describesLmdexpression of human subjective knowledge of space and its application to aware computing in cross-media operation between linguistic and pictorial expressions as spatial language understanding.
48
Jamali, Ali, Alias Abdul Rahman, and Pawel Boguslawski. "A Hybrid 3D Indoor Space Model." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W1 (October 26, 2016): 75–80. http://dx.doi.org/10.5194/isprs-archives-xlii-2-w1-75-2016.
Повний текст джерелаАнотація:
GIS integrates spatial information and spatial analysis. An important example of such integration is for emergency response which requires route planning inside and outside of a building. Route planning requires detailed information related to indoor and outdoor environment. Indoor navigation network models including Geometric Network Model (GNM), Navigable Space Model, sub-division model and regular-grid model lack indoor data sources and abstraction methods. In this paper, a hybrid indoor space model is proposed. In the proposed method, 3D modeling of indoor navigation network is based on surveying control points and it is less dependent on the 3D geometrical building model. This research proposes a method of indoor space modeling for the buildings which do not have proper 2D/3D geometrical models or they lack semantic or topological information. The proposed hybrid model consists of topological, geometrical and semantical space.
49
Shan, Xin, Jingyi Qiu, Bo Wang, Yongcheng Dang, Tingxiang LU, and Yiming Zheng. "Place Retrieval in Knowledge Graph." Scientific Programming 2020 (July 1, 2020): 1–10. http://dx.doi.org/10.1155/2020/5060635.
Повний текст джерелаАнотація:
With the rapid development of Internet and big data, place retrieval has become an indispensable part of daily life. However, traditional retrieval technology cannot meet the semantic needs of users. Knowledge graph has been introduced into the new-generation retrieval systems to improve retrieval performance. Knowledge graph abstracts things into entities and establishes relationships among entities, which are expressed in the form of triples. However, with the expansion of knowledge graph and the rapid increase of data volume, traditional place retrieval methods on knowledge graph have low performance. This paper designs a place retrieval method in order to improve the efficiency of place retrieval. Firstly, perform data preprocessing and problem model building in the offline stage. Meanwhile, build semantic distance index, spatial quadtree index, and spatial semantic hybrid index according to semantic and spatial information. At the same time, in the online retrieval stage, this paper designs an efficient query algorithm and ranking model based on the index information constructed in the offline stage, aiming at improving the overall performance of the retrieval system. Finally, we use experiment to verify the effectiveness and feasibility of the place retrieval method based on knowledge graph in terms of retrieval accuracy and retrieval efficiency under the real data.
50
Li, Xiaoman, Yanfei Zhong, Yu Su, and Richen Ye. "Scene-Change Detection Based on Multi-Feature-Fusion Latent Dirichlet Allocation Model for High-Spatial-Resolution Remote Sensing Imagery." Photogrammetric Engineering & Remote Sensing 87, no. 9 (September 1, 2021): 669–81. http://dx.doi.org/10.14358/pers.20-00054.
Повний текст джерелаАнотація:
With the continuous development of high-spatial-resolution ground observation technology, it is now becoming possible to obtain more and more high-resolution images, which provide us with the possibility to understand remote sensing images at the semantic level. Compared with traditional pixel- and object-oriented methods of change detection, scene-change detection can provide us with land use change information at the semantic level, and can thus provide reliable information for urban land use change detection, urban planning, and government management. Most of the current scene-change detection methods are based on the visual-words expression of the bag-of-visual-words model and the single-feature-based latent Dirichlet allocation model. In this article, a scene-change detection method for high-spatial-resolution imagery is proposed based on a multi-feature-fusion latent Dirich- let allocation model. This method combines the spectral, textural, and spatial features of the high-spatial-resolution images, and the final scene expression is realized through the topic features extracted from the more abstract latent Dirichlet allocation model. Post-classification comparison is then used to detect changes in the scene images at different times. A series of experiments demonstrates that, compared with the traditional bag-of-words and topic models, the proposed method can obtain superior scene-change detection results.