Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning mode...Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.展开更多
Biography videos based on life performances of prominent figures in history aim to describe great mens' life.In this paper,a novel interactive video summarization for biography video based on multimodal fusion is ...Biography videos based on life performances of prominent figures in history aim to describe great mens' life.In this paper,a novel interactive video summarization for biography video based on multimodal fusion is proposed,which is a novel approach of visualizing the specific features for biography video and interacting with video content by taking advantage of the ability of multimodality.In general,a story of movie progresses by dialogues of characters and the subtitles are produced with the basis on the dialogues which contains all the information related to the movie.In this paper,JGibbsLDA is applied to extract key words from subtitles because the biography video consists of different aspects to depict the characters' whole life.In terms of fusing keywords and key-frames,affinity propagation is adopted to calculate the similarity between each key-frame cluster and keywords.Through the method mentioned above,a video summarization is presented based on multimodal fusion which describes video content more completely.In order to reduce the time spent on searching the interest video content and get the relationship between main characters,a kind of map is adopted to visualize video content and interact with video summarization.An experiment is conducted to evaluate video summarization and the results demonstrate that this system can formally facilitate the exploration of video content while improving interaction and finding events of interest efficiently.展开更多
In this paper,an interactive method is proposed to describe computer animation data and accelerate the process of animation generation.First,a semantic model and a resource description framework(RDF)are utilized to an...In this paper,an interactive method is proposed to describe computer animation data and accelerate the process of animation generation.First,a semantic model and a resource description framework(RDF)are utilized to analyze and describe the relationships between animation data.Second,a novel context model which is able to keep the context-awareness was proposed to facilitate data organization and storage.In our context model,all the main animation elements in a scene are operated as a whole.Then sketch is utilized as the main interactive method to describe the relationships between animation data,edit the context model and make some other user operations.Finally,a context-aware computer animation data description system based on sketch is generated and it also works well in animation generation process.展开更多
Background Crossing-based target selection motion may attain less error rates and higher interactive speed in some cases.Most of the research in target selection fields are focused on the analysis of the interaction r...Background Crossing-based target selection motion may attain less error rates and higher interactive speed in some cases.Most of the research in target selection fields are focused on the analysis of the interaction results.Additionally,as trajectories play a much more important role in crossing-based target selection compared to the other interactive techniques,an ideal model for trajectories can help computer designers make predictions about interaction results during the process of target selection rather than at the end of the whole process.Methods In this paper,a trajectory prediction model for crossing based target selection tasks is proposed by taking the reference of a dynamic model theory.Results Simulation results demonstrate that our model performed well with regard to the prediction of trajectories,endpoints and hitting time for target-selection motion,and the average error of trajectories,endpoints and hitting time values were found to be 17.28%,2.73mm and 11.50%,respectively.展开更多
基金Youth Innovation Promotion Association CAS,Grant/Award Number:2021103Strategic Priority Research Program of Chinese Academy of Sciences,Grant/Award Number:XDC02060500。
文摘Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.
基金Supported by the National Key Research and Development Plan(2016YFB1001200)the Natural Science Foundation of China(U1435220,61232013)Natural Science Research Projects of Universities in Jiangsu Province(16KJA520003)
文摘Biography videos based on life performances of prominent figures in history aim to describe great mens' life.In this paper,a novel interactive video summarization for biography video based on multimodal fusion is proposed,which is a novel approach of visualizing the specific features for biography video and interacting with video content by taking advantage of the ability of multimodality.In general,a story of movie progresses by dialogues of characters and the subtitles are produced with the basis on the dialogues which contains all the information related to the movie.In this paper,JGibbsLDA is applied to extract key words from subtitles because the biography video consists of different aspects to depict the characters' whole life.In terms of fusing keywords and key-frames,affinity propagation is adopted to calculate the similarity between each key-frame cluster and keywords.Through the method mentioned above,a video summarization is presented based on multimodal fusion which describes video content more completely.In order to reduce the time spent on searching the interest video content and get the relationship between main characters,a kind of map is adopted to visualize video content and interact with video summarization.An experiment is conducted to evaluate video summarization and the results demonstrate that this system can formally facilitate the exploration of video content while improving interaction and finding events of interest efficiently.
基金Supported by the National Key Research and Development Plan(2016YFB1001200)the National Natural Science Foundation of China(U1435220,61232013)
文摘In this paper,an interactive method is proposed to describe computer animation data and accelerate the process of animation generation.First,a semantic model and a resource description framework(RDF)are utilized to analyze and describe the relationships between animation data.Second,a novel context model which is able to keep the context-awareness was proposed to facilitate data organization and storage.In our context model,all the main animation elements in a scene are operated as a whole.Then sketch is utilized as the main interactive method to describe the relationships between animation data,edit the context model and make some other user operations.Finally,a context-aware computer animation data description system based on sketch is generated and it also works well in animation generation process.
基金National Key R&D Program of China(2016YFB1001405)the National Natural Science Foundation of China(61802379)Key Research Program of Frontier Sciences,CAS(QYZDY-SSW-JSC041).
文摘Background Crossing-based target selection motion may attain less error rates and higher interactive speed in some cases.Most of the research in target selection fields are focused on the analysis of the interaction results.Additionally,as trajectories play a much more important role in crossing-based target selection compared to the other interactive techniques,an ideal model for trajectories can help computer designers make predictions about interaction results during the process of target selection rather than at the end of the whole process.Methods In this paper,a trajectory prediction model for crossing based target selection tasks is proposed by taking the reference of a dynamic model theory.Results Simulation results demonstrate that our model performed well with regard to the prediction of trajectories,endpoints and hitting time for target-selection motion,and the average error of trajectories,endpoints and hitting time values were found to be 17.28%,2.73mm and 11.50%,respectively.
