The field of artificial intelligence has advanced significantly in recent years,but achieving a human-like or Artificial General Intelligence(AGI)remains a theoretical challenge.One hypothesis suggests that a key issu...The field of artificial intelligence has advanced significantly in recent years,but achieving a human-like or Artificial General Intelligence(AGI)remains a theoretical challenge.One hypothesis suggests that a key issue is the formalisation of extracting meaning from information.Meaning emerges through a three-stage interpretative process,where the spectrum of possible interpretations is collapsed into a singular outcome by a particular context.However,this approach currently lacks practical grounding.In this research,we developed a model based on contexts,which applies interpretation principles to the visual information to address this gap.The field of computer vision and object recognition has progressed essentially with artificial neural networks,but these models struggle with geometrically transformed images,such as those that are rotated or shifted,limiting their robustness in real-world applications.Various approaches have been proposed to address this problem.Some of them(Hu moments,spatial transformers,capsule networks,attention and memory mechanisms)share a conceptual connection with the contextual model(CM)discussed in this study.This paper investigates whether CM principles are applicable for interpreting rotated images from the MNIST and Fashion MNIST datasets.The model was implemented in the Rust programming language.It consists of a contextual module and a convolutional neural network(CNN).The CMwas trained on the rotated Mono Icons dataset,which is significantly different from the testing datasets.The CNN module was trained on the original MNIST and Fashion MNIST datasets for interpretation recognition.As a result,the CM was able to recognise the original datasets but encountered rotated images only during testing.The findings show that the model effectively interpreted transformed images by considering them in all available contexts and restoring their original form.This provides a practical foundation for further development of the contextual hypothesis and its relation to theAGI domain.展开更多
Structured study of spatial objects and their relationships leads to a better cognition of the geospatial information and creates the concept of context at a higher level of abstraction.This study is aimed at providin...Structured study of spatial objects and their relationships leads to a better cognition of the geospatial information and creates the concept of context at a higher level of abstraction.This study is aimed at providing a comprehensive definition of the context for geospatial objects.A combination of binary qualitative spatial relationships(i.e.direction,distance,and topological relations)among the members of a set of spatial objects will be used accordingly.In addition,by incorporating the general concept of context,obtained from either static data(attributes in a database)or dynamic data(sensors),the compact context of spatial objects will be introduced.Our framework for presentation of the involved knowledge and conception about the objects in context is also explored using ontology and description logic because of powerful conceptualization of relationships,either spatial or non-spatial,integrally.For this purpose,the hierarchies of main structure and object properties are formed at first.The constraint and characteristics of classes,such as subclasses,equivalent classes,cardinality etc.,and object properties,such as being functional,transitive,symmetric,asymmetric,inverse functional,disjoint etc.,are discovered and presented in more detail using web ontology language in description logic mode.The implementation is then performed in the framework of semantic web and extensible markup language syntaxes.The method ultimately facilitates,spatial reasoning by effective querying in a semantic framework taking pellet reasoner and SPARQL(a recursive acronym for SPARQL Protocol and RDF Query Language).展开更多
The GeoEduc3D project aims to provide educational games for smartphones based on Geomatics and use augmented reality techniques in order to make these games more immersive. To improve the immersive and interactive asp...The GeoEduc3D project aims to provide educational games for smartphones based on Geomatics and use augmented reality techniques in order to make these games more immersive. To improve the immersive and interactive aspects of those games, we focused on the exploitation of spatial context in this particular application framework (serious games, augmented reality, smart phones, and multi-users environment). Our work has thus led to the design of a solution dedicated to the management of spatial context in a multi-players environment on and for smartphones. Several contributions have been made: modeling spatial context, proposing a service-oriented architecture to manage this context, defining a Web Service Spatial Context (WSCS) and implementation of a WSCS prototype and a mobile client according to an environment exploiting FourSquare, a geo-social application.展开更多
Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variati...Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variations inUAV flight altitude,differences in object scales,as well as factors like flight speed and motion blur.To enhancethe detection efficacy of small targets in drone aerial imagery,we propose an enhanced You Only Look Onceversion 7(YOLOv7)algorithm based on multi-scale spatial context.We build the MSC-YOLO model,whichincorporates an additional prediction head,denoted as P2,to improve adaptability for small objects.We replaceconventional downsampling with a Spatial-to-Depth Convolutional Combination(CSPDC)module to mitigatethe loss of intricate feature details related to small objects.Furthermore,we propose a Spatial Context Pyramidwith Multi-Scale Attention(SCPMA)module,which captures spatial and channel-dependent features of smalltargets acrossmultiple scales.This module enhances the perception of spatial contextual features and the utilizationof multiscale feature information.On the Visdrone2023 and UAVDT datasets,MSC-YOLO achieves remarkableresults,outperforming the baseline method YOLOv7 by 3.0%in terms ofmean average precision(mAP).The MSCYOLOalgorithm proposed in this paper has demonstrated satisfactory performance in detecting small targets inUAV aerial photography,providing strong support for practical applications.展开更多
Taking Zhaoyu Historical City in Qixian County as an example,this paper explores the production process of tourism space in Zhaoyu Historical City in the context of consumption,based on Lefebvre's triadic dialecti...Taking Zhaoyu Historical City in Qixian County as an example,this paper explores the production process of tourism space in Zhaoyu Historical City in the context of consumption,based on Lefebvre's triadic dialectic theory.The study reveals that,driven by the development of tourism,subjects such as the government and planners possess absolute dominance over spatial representations,while residents demonstrate receptive and adaptive action strategies and social relations are reproduced,presenting a harmonious state.Further exploring the tourism community in the environmental performance of the subject of action,social relations,consumption demand,daily life practice,cultural capital,etc.,the daily life practice of the tourism community has transcended the original logic of tourism spatial production and has a certain extension.The mechanism analysis in this paper can help guide the healthy development of tourism space in the neighboring historical cities or communities and achieve the dual purpose of promoting the economic development of the community and heritage protection.展开更多
Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies a...Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies among human joints while ignoring the temporal cues and the complex relationships across non-consecutive frames.These limitations hinder the model’s ability to generate accurate predictions over longer time horizons and in scenarios with complex motion patterns.To address the above problems,we proposed a novel multi-level spatial and temporal learning model,which consists of a Cross Spatial Dependencies Encoding Module(CSM)and a Dynamic Temporal Connection Encoding Module(DTM).Specifically,the CSM is designed to capture complementary local and global spatial dependent information at both the joint level and the joint pair level.We further present DTM to encode diverse temporal evolution contexts and compress motion features to a deep level,enabling the model to capture both short-term and long-term dependencies efficiently.Extensive experiments conducted on the Human 3.6M and CMU Mocap datasets demonstrate that our model achieves state-of-the-art performance in both short-term and long-term predictions,outperforming existing methods by up to 20.3% in accuracy.Furthermore,ablation studies confirm the significant contributions of the CSM and DTM in enhancing prediction accuracy.展开更多
Climate crises necessitate adaptive,cost-effective,and community-driven strategies to enhance urban resilience.Tactical urban design,which includes temporary and experimental interventions,is becoming increasingly vit...Climate crises necessitate adaptive,cost-effective,and community-driven strategies to enhance urban resilience.Tactical urban design,which includes temporary and experimental interventions,is becoming increasingly vital,particularly in indigenous contexts.This study explores the spatial agency approach within tactical urbanism,emphasizing low-technology techniques,indigenous knowledge,and decentralized design as active elements in transforming public spaces.It aims to review recent trends and alternative tactical strategies in indigenous settings while identifying the attributes and mechanisms that contribute to the creation of sustainable public spaces through spatial agency.Employing an interpretive qualitative methodology that includes case studies and content analysis,the research focuses on the Open-Air Lab in Dakar,Senegal(Codesign Lab,Paolo Cascone).This project,a small-scale public infrastructure initiative born from participatory design,exemplifies a hybrid model that combines traditional craftsmanship,low-tech digital fabrication,and environmentally conscious solutions.The findings indicate that framing spatial agency as an actor-network process brings marginalized actors and practices to the forefront,fostering empowerment,social synergy,and climate-responsive design.The study advocates for a shift in tactical urban design from ephemeral placemaking toward long-term,adaptive strategies grounded in local materiality,community engagement,knowledge systems,and decentralized networks.These insights reshape the understanding of urban adaptability and provide practical guidance for architects and planners aiming to create inclusive,climate-resilient public spaces in indigenous and Global South contexts.展开更多
Interregional migration has broad and far-reaching impacts on regional urbanization process in ethnic minority areas of Southwest China.The previous literature of interregional migration paid less attention on the eth...Interregional migration has broad and far-reaching impacts on regional urbanization process in ethnic minority areas of Southwest China.The previous literature of interregional migration paid less attention on the ethnic minority areas with fragile geographical feature and marginal socio-economic context in the developing world due to the dearth of reliable data.Based on the 2015 national 1%population sampling survey at the village/community scale,taking Yulong Naxi Autonomous County,Yunnan Province,China as the case study,this paper analyzed the spatial differentiation pattern.The results showed that:(1)migration in Yulong Naxi Autonomous County exhibited obvious spatial differentiation characteristics in terms of population aggregation,population loss,migration direction,and migration activity;(2)the overall spatial differentiation of migration exhibited a"layer+sector"pattern in Yulong Naxi Autonomous County:the first layer was active areas with net inflows(<20 km from the seat of the county government),the second layer was inactive areas(within 20–60 km of the seat of the county government),and the third layer was a mixed"layer+sector"zone(>60 km to the seat of the county government),comprised of inactive areas and active areas with net outflows;(3)the spatial differentiation pattern of migration was highly correlated with the regional contexts including the regional economic development,regional transportation accessibility and regional social development,while regional physical geographical factors had insignificant relationships with the migration pattern.展开更多
Animal survival necessitates adaptive behav-iors in volatile environmental contexts.Virtual reality(VR)technology is instrumental to study the neural mechanisms underlying behaviors modulated by environmental con-text...Animal survival necessitates adaptive behav-iors in volatile environmental contexts.Virtual reality(VR)technology is instrumental to study the neural mechanisms underlying behaviors modulated by environmental con-text by simulating the real world with maximized control of contextual elements.Yet current VR tools for rodents have limited flexibility and performance(e.g.,frame rate)for context-dependent cognitive research.Here,we describe a high-performance VR platform with which to study con-textual behaviors immersed in editable virtual contexts.This platform was assembled from modular hardware and custom-written software with flexibility and upgradability.Using this platform,we trained mice to perform context-dependent cognitive tasks with rules ranging from discrim-ination to delayed-sample-to-match while recording from thousands of hippocampal place cells.By precise manipula-tions of context elements,we found that the context recogni-tion was intact with partial context elements,but impaired by exchanges of context elements.Collectively,our work establishes a configurable VR platform with which to investigate context-dependent cognition with large-scale neural recording.展开更多
Recently,the focus of semantic segmentation research has shifted to the aggregation of context prior and refined boundary.A typical network adopts context aggregation modules to extract rich semantic features.It also ...Recently,the focus of semantic segmentation research has shifted to the aggregation of context prior and refined boundary.A typical network adopts context aggregation modules to extract rich semantic features.It also utilizes top-down connection and skips connections for refining boundary details.But it still remains disadvantage,an obvious fact is that the problem of false segmentation occurs as the object has very different textures.The fusion of weak semantic and low-level features leads to context prior degradation.To tackle the issue,we propose a simple yet effective network,which integrates dual context prior and spatial propagation-dubbed DSPNet.It extends two mainstreams of current segmentation researches:(1)Designing a dual context prior module,which pays attention to context prior again with a shortcut connection.(2)The network can inherently learn semantic aware affinity values for each pixel and refine the segmentation.We will present detailed comparisons,which perform on PASCAL VOC 2012 and Cityscapes.The result demonstrates the validation of our approach.展开更多
A new algorithm taking the spatial context of local features into account by utilizing contextualized histograms was proposed to recognize facial expression. The contextualized histograms were extracted fromtwo widely...A new algorithm taking the spatial context of local features into account by utilizing contextualized histograms was proposed to recognize facial expression. The contextualized histograms were extracted fromtwo widely used descriptors—the local binary pattern（ LBP） and weber local descriptor（ WLD）. The LBP and WLD feature histograms were extracted separately fromeach facial image,and contextualized histogram was generated as feature vectors to feed the classifier. In addition,the human face was divided into sub-blocks and each sub-block was assigned different weights by their different contributions to the intensity of facial expressions to improve the recognition rate. With the support vector machine（SVM） as classifier,the experimental results on the 2D texture images fromthe 3D-BU FE dataset indicated that contextualized histograms improved facial expression recognition performance when local features were employed.展开更多
Based on the research background of Pingyao ancient city and its ancient residential buildings, combined with architecture and space research, folk culture and sociology research, visual design and other related theor...Based on the research background of Pingyao ancient city and its ancient residential buildings, combined with architecture and space research, folk culture and sociology research, visual design and other related theoretical research as theoretical basis, this paper studies the unique place space experience and place spirit expression of Pingyao ancient city through theoretical analysis. This paper analyzes from the perspective of space theory, from the regional culture, the relationship between people and places, extending to the shaping of visual environment, architectural decoration elements and means, etc., and explains it with the help of relevant theoretical basis. At different specific levels, the expression of humanization, rationality, applicability and humanistic value of ancient city space is introduced from the spirit of place, and it is used as the basic theoretical basis and theoretical guidance of related theoretical research, which makes the research process tend to be possible, realistic and operable.展开更多
文摘The field of artificial intelligence has advanced significantly in recent years,but achieving a human-like or Artificial General Intelligence(AGI)remains a theoretical challenge.One hypothesis suggests that a key issue is the formalisation of extracting meaning from information.Meaning emerges through a three-stage interpretative process,where the spectrum of possible interpretations is collapsed into a singular outcome by a particular context.However,this approach currently lacks practical grounding.In this research,we developed a model based on contexts,which applies interpretation principles to the visual information to address this gap.The field of computer vision and object recognition has progressed essentially with artificial neural networks,but these models struggle with geometrically transformed images,such as those that are rotated or shifted,limiting their robustness in real-world applications.Various approaches have been proposed to address this problem.Some of them(Hu moments,spatial transformers,capsule networks,attention and memory mechanisms)share a conceptual connection with the contextual model(CM)discussed in this study.This paper investigates whether CM principles are applicable for interpreting rotated images from the MNIST and Fashion MNIST datasets.The model was implemented in the Rust programming language.It consists of a contextual module and a convolutional neural network(CNN).The CMwas trained on the rotated Mono Icons dataset,which is significantly different from the testing datasets.The CNN module was trained on the original MNIST and Fashion MNIST datasets for interpretation recognition.As a result,the CM was able to recognise the original datasets but encountered rotated images only during testing.The findings show that the model effectively interpreted transformed images by considering them in all available contexts and restoring their original form.This provides a practical foundation for further development of the contextual hypothesis and its relation to theAGI domain.
文摘Structured study of spatial objects and their relationships leads to a better cognition of the geospatial information and creates the concept of context at a higher level of abstraction.This study is aimed at providing a comprehensive definition of the context for geospatial objects.A combination of binary qualitative spatial relationships(i.e.direction,distance,and topological relations)among the members of a set of spatial objects will be used accordingly.In addition,by incorporating the general concept of context,obtained from either static data(attributes in a database)or dynamic data(sensors),the compact context of spatial objects will be introduced.Our framework for presentation of the involved knowledge and conception about the objects in context is also explored using ontology and description logic because of powerful conceptualization of relationships,either spatial or non-spatial,integrally.For this purpose,the hierarchies of main structure and object properties are formed at first.The constraint and characteristics of classes,such as subclasses,equivalent classes,cardinality etc.,and object properties,such as being functional,transitive,symmetric,asymmetric,inverse functional,disjoint etc.,are discovered and presented in more detail using web ontology language in description logic mode.The implementation is then performed in the framework of semantic web and extensible markup language syntaxes.The method ultimately facilitates,spatial reasoning by effective querying in a semantic framework taking pellet reasoner and SPARQL(a recursive acronym for SPARQL Protocol and RDF Query Language).
文摘The GeoEduc3D project aims to provide educational games for smartphones based on Geomatics and use augmented reality techniques in order to make these games more immersive. To improve the immersive and interactive aspects of those games, we focused on the exploitation of spatial context in this particular application framework (serious games, augmented reality, smart phones, and multi-users environment). Our work has thus led to the design of a solution dedicated to the management of spatial context in a multi-players environment on and for smartphones. Several contributions have been made: modeling spatial context, proposing a service-oriented architecture to manage this context, defining a Web Service Spatial Context (WSCS) and implementation of a WSCS prototype and a mobile client according to an environment exploiting FourSquare, a geo-social application.
基金the Key Research and Development Program of Hainan Province(Grant Nos.ZDYF2023GXJS163,ZDYF2024GXJS014)National Natural Science Foundation of China(NSFC)(Grant Nos.62162022,62162024)+2 种基金the Major Science and Technology Project of Hainan Province(Grant No.ZDKJ2020012)Hainan Provincial Natural Science Foundation of China(Grant No.620MS021)Youth Foundation Project of Hainan Natural Science Foundation(621QN211).
文摘Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variations inUAV flight altitude,differences in object scales,as well as factors like flight speed and motion blur.To enhancethe detection efficacy of small targets in drone aerial imagery,we propose an enhanced You Only Look Onceversion 7(YOLOv7)algorithm based on multi-scale spatial context.We build the MSC-YOLO model,whichincorporates an additional prediction head,denoted as P2,to improve adaptability for small objects.We replaceconventional downsampling with a Spatial-to-Depth Convolutional Combination(CSPDC)module to mitigatethe loss of intricate feature details related to small objects.Furthermore,we propose a Spatial Context Pyramidwith Multi-Scale Attention(SCPMA)module,which captures spatial and channel-dependent features of smalltargets acrossmultiple scales.This module enhances the perception of spatial contextual features and the utilizationof multiscale feature information.On the Visdrone2023 and UAVDT datasets,MSC-YOLO achieves remarkableresults,outperforming the baseline method YOLOv7 by 3.0%in terms ofmean average precision(mAP).The MSCYOLOalgorithm proposed in this paper has demonstrated satisfactory performance in detecting small targets inUAV aerial photography,providing strong support for practical applications.
文摘Taking Zhaoyu Historical City in Qixian County as an example,this paper explores the production process of tourism space in Zhaoyu Historical City in the context of consumption,based on Lefebvre's triadic dialectic theory.The study reveals that,driven by the development of tourism,subjects such as the government and planners possess absolute dominance over spatial representations,while residents demonstrate receptive and adaptive action strategies and social relations are reproduced,presenting a harmonious state.Further exploring the tourism community in the environmental performance of the subject of action,social relations,consumption demand,daily life practice,cultural capital,etc.,the daily life practice of the tourism community has transcended the original logic of tourism spatial production and has a certain extension.The mechanism analysis in this paper can help guide the healthy development of tourism space in the neighboring historical cities or communities and achieve the dual purpose of promoting the economic development of the community and heritage protection.
基金supported by the Urgent Need for Overseas Talent Project of Jiangxi Province(Grant No.20223BCJ25040)the Thousand Talents Plan of Jiangxi Province(Grant No.jxsg2023101085)+3 种基金the National Natural Science Foundation of China(Grant No.62106093)the Natural Science Foundation of Jiangxi(Grant Nos.20224BAB212011,20232BAB212008,20242BAB25078,and 20232BAB202051)The Youth Talent Cultivation Innovation Fund Project of Nanchang University(Grant No.XX202506030015)funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R759),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies among human joints while ignoring the temporal cues and the complex relationships across non-consecutive frames.These limitations hinder the model’s ability to generate accurate predictions over longer time horizons and in scenarios with complex motion patterns.To address the above problems,we proposed a novel multi-level spatial and temporal learning model,which consists of a Cross Spatial Dependencies Encoding Module(CSM)and a Dynamic Temporal Connection Encoding Module(DTM).Specifically,the CSM is designed to capture complementary local and global spatial dependent information at both the joint level and the joint pair level.We further present DTM to encode diverse temporal evolution contexts and compress motion features to a deep level,enabling the model to capture both short-term and long-term dependencies efficiently.Extensive experiments conducted on the Human 3.6M and CMU Mocap datasets demonstrate that our model achieves state-of-the-art performance in both short-term and long-term predictions,outperforming existing methods by up to 20.3% in accuracy.Furthermore,ablation studies confirm the significant contributions of the CSM and DTM in enhancing prediction accuracy.
文摘Climate crises necessitate adaptive,cost-effective,and community-driven strategies to enhance urban resilience.Tactical urban design,which includes temporary and experimental interventions,is becoming increasingly vital,particularly in indigenous contexts.This study explores the spatial agency approach within tactical urbanism,emphasizing low-technology techniques,indigenous knowledge,and decentralized design as active elements in transforming public spaces.It aims to review recent trends and alternative tactical strategies in indigenous settings while identifying the attributes and mechanisms that contribute to the creation of sustainable public spaces through spatial agency.Employing an interpretive qualitative methodology that includes case studies and content analysis,the research focuses on the Open-Air Lab in Dakar,Senegal(Codesign Lab,Paolo Cascone).This project,a small-scale public infrastructure initiative born from participatory design,exemplifies a hybrid model that combines traditional craftsmanship,low-tech digital fabrication,and environmentally conscious solutions.The findings indicate that framing spatial agency as an actor-network process brings marginalized actors and practices to the forefront,fostering empowerment,social synergy,and climate-responsive design.The study advocates for a shift in tactical urban design from ephemeral placemaking toward long-term,adaptive strategies grounded in local materiality,community engagement,knowledge systems,and decentralized networks.These insights reshape the understanding of urban adaptability and provide practical guidance for architects and planners aiming to create inclusive,climate-resilient public spaces in indigenous and Global South contexts.
基金This work was supported by the National Natural Science Foundation of China(41930644).
文摘Interregional migration has broad and far-reaching impacts on regional urbanization process in ethnic minority areas of Southwest China.The previous literature of interregional migration paid less attention on the ethnic minority areas with fragile geographical feature and marginal socio-economic context in the developing world due to the dearth of reliable data.Based on the 2015 national 1%population sampling survey at the village/community scale,taking Yulong Naxi Autonomous County,Yunnan Province,China as the case study,this paper analyzed the spatial differentiation pattern.The results showed that:(1)migration in Yulong Naxi Autonomous County exhibited obvious spatial differentiation characteristics in terms of population aggregation,population loss,migration direction,and migration activity;(2)the overall spatial differentiation of migration exhibited a"layer+sector"pattern in Yulong Naxi Autonomous County:the first layer was active areas with net inflows(<20 km from the seat of the county government),the second layer was inactive areas(within 20–60 km of the seat of the county government),and the third layer was a mixed"layer+sector"zone(>60 km to the seat of the county government),comprised of inactive areas and active areas with net outflows;(3)the spatial differentiation pattern of migration was highly correlated with the regional contexts including the regional economic development,regional transportation accessibility and regional social development,while regional physical geographical factors had insignificant relationships with the migration pattern.
基金supported by the National Science and Technology Innovation 2030 Major Program(2022ZD0205000)the National Key R&D Program of China,the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB32010105,XDBS01010100)+3 种基金Shanghai Municipal Science and Technology Major Project(2018SHZDZX05)Lingang Lab(LG202104-01-08)the National Natural Science Foundation of China(31771180 and 91732106)an International Collaborative Project of the Shanghai Science and Technology Committee(201978677).
文摘Animal survival necessitates adaptive behav-iors in volatile environmental contexts.Virtual reality(VR)technology is instrumental to study the neural mechanisms underlying behaviors modulated by environmental con-text by simulating the real world with maximized control of contextual elements.Yet current VR tools for rodents have limited flexibility and performance(e.g.,frame rate)for context-dependent cognitive research.Here,we describe a high-performance VR platform with which to study con-textual behaviors immersed in editable virtual contexts.This platform was assembled from modular hardware and custom-written software with flexibility and upgradability.Using this platform,we trained mice to perform context-dependent cognitive tasks with rules ranging from discrim-ination to delayed-sample-to-match while recording from thousands of hippocampal place cells.By precise manipula-tions of context elements,we found that the context recogni-tion was intact with partial context elements,but impaired by exchanges of context elements.Collectively,our work establishes a configurable VR platform with which to investigate context-dependent cognition with large-scale neural recording.
文摘Recently,the focus of semantic segmentation research has shifted to the aggregation of context prior and refined boundary.A typical network adopts context aggregation modules to extract rich semantic features.It also utilizes top-down connection and skips connections for refining boundary details.But it still remains disadvantage,an obvious fact is that the problem of false segmentation occurs as the object has very different textures.The fusion of weak semantic and low-level features leads to context prior degradation.To tackle the issue,we propose a simple yet effective network,which integrates dual context prior and spatial propagation-dubbed DSPNet.It extends two mainstreams of current segmentation researches:(1)Designing a dual context prior module,which pays attention to context prior again with a shortcut connection.(2)The network can inherently learn semantic aware affinity values for each pixel and refine the segmentation.We will present detailed comparisons,which perform on PASCAL VOC 2012 and Cityscapes.The result demonstrates the validation of our approach.
基金Supported by the National Natural Science Foundation of China(60772066)
文摘A new algorithm taking the spatial context of local features into account by utilizing contextualized histograms was proposed to recognize facial expression. The contextualized histograms were extracted fromtwo widely used descriptors—the local binary pattern（ LBP） and weber local descriptor（ WLD）. The LBP and WLD feature histograms were extracted separately fromeach facial image,and contextualized histogram was generated as feature vectors to feed the classifier. In addition,the human face was divided into sub-blocks and each sub-block was assigned different weights by their different contributions to the intensity of facial expressions to improve the recognition rate. With the support vector machine（SVM） as classifier,the experimental results on the 2D texture images fromthe 3D-BU FE dataset indicated that contextualized histograms improved facial expression recognition performance when local features were employed.
文摘Based on the research background of Pingyao ancient city and its ancient residential buildings, combined with architecture and space research, folk culture and sociology research, visual design and other related theoretical research as theoretical basis, this paper studies the unique place space experience and place spirit expression of Pingyao ancient city through theoretical analysis. This paper analyzes from the perspective of space theory, from the regional culture, the relationship between people and places, extending to the shaping of visual environment, architectural decoration elements and means, etc., and explains it with the help of relevant theoretical basis. At different specific levels, the expression of humanization, rationality, applicability and humanistic value of ancient city space is introduced from the spirit of place, and it is used as the basic theoretical basis and theoretical guidance of related theoretical research, which makes the research process tend to be possible, realistic and operable.
