针对免耕播种装备产品数据管理(Product data management,PDM)系统的实验影像资源在存储和查询过程中内容甄别困难、用户获取相关资源需求难以保证的问题,在VS(Microsoft Visual Studio)环境下应用VB.NET语言搭载SQL Server数据库开发...针对免耕播种装备产品数据管理(Product data management,PDM)系统的实验影像资源在存储和查询过程中内容甄别困难、用户获取相关资源需求难以保证的问题,在VS(Microsoft Visual Studio)环境下应用VB.NET语言搭载SQL Server数据库开发一种交互式资源管理系统,对实验影像资源内容进行多元信息标注并分配权重,应用ADO.NET(Microsoft ActiveX Data Objects.Net)技术实现影像资源多元信息的编辑和存储,基于多元信息权重创建推荐查询方法,联合浏览选择,实现影像资源的获取与应用。测试结果表明本系统可根据影像资源多元信息进行添加、删除、修改和查询,当输入字段与本地数据库无法精确匹配时可智能推荐数据,实现了对影像资源多元信息的有效管理。多元信息能够唯一准确标识影像资源并作为资源管理的依据,基于多元信息权重设计的推荐方法能够有效解决用户输入字段与本地数据表不完全匹配的问题。展开更多
Photo composition is one of the most important factors in the aesthetics of photographs.As a popular application,composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-le...Photo composition is one of the most important factors in the aesthetics of photographs.As a popular application,composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-learning-based composition recommendation approaches.In this paper,we propose a subject-aware image composition recommendation method,SAC-Net,which takes an RGB image and a binary subject window mask as input,and returns good compositions as crops containing the subject.Our model first determines candidate scores for all possible coarse cropping windows.The crops with high candidate scores are selected and further refined by regressing their corner points to generate the output recommended cropping windows.The final scores of the refined crops are predicted by a final score regression module.Unlike existing methods that need to preset several cropping windows,our network is able to automatically regress cropping windows with arbitrary aspect ratios and sizes.We propose novel stability losses for maximizing smoothness when changing cropping windows along with view changes.Experimental results show that our method outperforms state-of-the-art methods not only on the subject-aware image composition recommendation task,but also for general purpose composition recommendation.We also have designed a multistage labeling scheme so that a large amount of ranked pairs can be produced economically.We use this scheme to propose the first subject-aware composition dataset SACD,which contains 2777 images,and more than 5 million composition ranked pairs.The SACD dataset is publicly available at https://cg.cs.tsinghua.edu.cn/SACD/.展开更多
We propose a novel problem revolving around two tasks:(i)given a scene,recommend objects to insert,and(ii)given an object category,retrieve suitable background scenes.A bounding box for the inserted object is predicte...We propose a novel problem revolving around two tasks:(i)given a scene,recommend objects to insert,and(ii)given an object category,retrieve suitable background scenes.A bounding box for the inserted object is predicted in both tasks,which helps downstream applications such as semiautomated advertising and video composition.The major challenge lies in the fact that the target object is neither present nor localized in the input,and furthermore,available datasets only provide scenes with existing objects.To tackle this problem,we build an unsupervised algorithm based on object-level contexts,which explicitly models the joint probability distribution of object categories and bounding boxes using a Gaussian mixture model.Experiments on our own annotated test set demonstrate that our system outperforms existing baselines on all sub-tasks,and does so using a unified framework.Future extensions and applications are suggested.展开更多
Most real estate agents develop new objects by visiting unfamiliar clients, distributing leaflets, or browsing other real estate trading website platforms,whereas consumers often rely on websites to search and compar...Most real estate agents develop new objects by visiting unfamiliar clients, distributing leaflets, or browsing other real estate trading website platforms,whereas consumers often rely on websites to search and compare prices when purchasing real property. In addition to being time consuming, this search processrenders it difficult for agents and consumers to understand the status changes ofobjects. In this study, Python is used to write web crawler and image recognitionprograms to capture object information from the web pages of real estate agents;perform data screening, arranging, and cleaning;compare the text of real estateobject information;as well as integrate and use the convolutional neural networkof a deep learning algorithm to implement image recognition. In this study, dataare acquired from two business-to-consumer real estate agency networks, i.e., theSinyi real estate agent and the Yungching real estate agent, and one consumer-toconsumer real estate agency platform, i.e., the, FiveNineOne real estate agent. Theresults indicate that text mining can reveal the similarities and differences betweenthe objects, list the number of days that the object has been available for sale onthe website, and provide the price fluctuations and fluctuation times during thesales period. In addition, 213,325 object amplification images are used as a database for training using deep learning algorithms, and the maximum image recognition accuracy achieved is 95%. The dynamic recommendation system for realestate objects constructed by combining text mining and image recognition systems enables developers in the real estate industry to understand the differencesbetween their commodities and other businesses in approximately 2 min, as wellas rapidly determine developable objects via comparison results provided by thesystem. Meanwhile, consumers require less time in searching and comparingprices after they have understood the commodity dynamic information, therebyallowing them to use the most efficient approach to purchase展开更多
文摘针对免耕播种装备产品数据管理(Product data management,PDM)系统的实验影像资源在存储和查询过程中内容甄别困难、用户获取相关资源需求难以保证的问题,在VS(Microsoft Visual Studio)环境下应用VB.NET语言搭载SQL Server数据库开发一种交互式资源管理系统,对实验影像资源内容进行多元信息标注并分配权重,应用ADO.NET(Microsoft ActiveX Data Objects.Net)技术实现影像资源多元信息的编辑和存储,基于多元信息权重创建推荐查询方法,联合浏览选择,实现影像资源的获取与应用。测试结果表明本系统可根据影像资源多元信息进行添加、删除、修改和查询,当输入字段与本地数据库无法精确匹配时可智能推荐数据,实现了对影像资源多元信息的有效管理。多元信息能够唯一准确标识影像资源并作为资源管理的依据,基于多元信息权重设计的推荐方法能够有效解决用户输入字段与本地数据表不完全匹配的问题。
基金This work was supported by the National Natural Science Foundation of China(61521002,62132012)the Marsden Fund Council managed by the Royal Society of New Zealand(MFP-20-VUW-180).
文摘Photo composition is one of the most important factors in the aesthetics of photographs.As a popular application,composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-learning-based composition recommendation approaches.In this paper,we propose a subject-aware image composition recommendation method,SAC-Net,which takes an RGB image and a binary subject window mask as input,and returns good compositions as crops containing the subject.Our model first determines candidate scores for all possible coarse cropping windows.The crops with high candidate scores are selected and further refined by regressing their corner points to generate the output recommended cropping windows.The final scores of the refined crops are predicted by a final score regression module.Unlike existing methods that need to preset several cropping windows,our network is able to automatically regress cropping windows with arbitrary aspect ratios and sizes.We propose novel stability losses for maximizing smoothness when changing cropping windows along with view changes.Experimental results show that our method outperforms state-of-the-art methods not only on the subject-aware image composition recommendation task,but also for general purpose composition recommendation.We also have designed a multistage labeling scheme so that a large amount of ranked pairs can be produced economically.We use this scheme to propose the first subject-aware composition dataset SACD,which contains 2777 images,and more than 5 million composition ranked pairs.The SACD dataset is publicly available at https://cg.cs.tsinghua.edu.cn/SACD/.
基金supported by the National Key Technology R&D Program(Project Number 2016YFB1001402)the National Natural Science Foundation of China(Project Numbers61521002,61772298)+1 种基金Research Grant of Beijing Higher Institution Engineering Research CenterTsinghua–Tencent Joint Laboratory for Internet Innovation Technology.
文摘We propose a novel problem revolving around two tasks:(i)given a scene,recommend objects to insert,and(ii)given an object category,retrieve suitable background scenes.A bounding box for the inserted object is predicted in both tasks,which helps downstream applications such as semiautomated advertising and video composition.The major challenge lies in the fact that the target object is neither present nor localized in the input,and furthermore,available datasets only provide scenes with existing objects.To tackle this problem,we build an unsupervised algorithm based on object-level contexts,which explicitly models the joint probability distribution of object categories and bounding boxes using a Gaussian mixture model.Experiments on our own annotated test set demonstrate that our system outperforms existing baselines on all sub-tasks,and does so using a unified framework.Future extensions and applications are suggested.
文摘Most real estate agents develop new objects by visiting unfamiliar clients, distributing leaflets, or browsing other real estate trading website platforms,whereas consumers often rely on websites to search and compare prices when purchasing real property. In addition to being time consuming, this search processrenders it difficult for agents and consumers to understand the status changes ofobjects. In this study, Python is used to write web crawler and image recognitionprograms to capture object information from the web pages of real estate agents;perform data screening, arranging, and cleaning;compare the text of real estateobject information;as well as integrate and use the convolutional neural networkof a deep learning algorithm to implement image recognition. In this study, dataare acquired from two business-to-consumer real estate agency networks, i.e., theSinyi real estate agent and the Yungching real estate agent, and one consumer-toconsumer real estate agency platform, i.e., the, FiveNineOne real estate agent. Theresults indicate that text mining can reveal the similarities and differences betweenthe objects, list the number of days that the object has been available for sale onthe website, and provide the price fluctuations and fluctuation times during thesales period. In addition, 213,325 object amplification images are used as a database for training using deep learning algorithms, and the maximum image recognition accuracy achieved is 95%. The dynamic recommendation system for realestate objects constructed by combining text mining and image recognition systems enables developers in the real estate industry to understand the differencesbetween their commodities and other businesses in approximately 2 min, as wellas rapidly determine developable objects via comparison results provided by thesystem. Meanwhile, consumers require less time in searching and comparingprices after they have understood the commodity dynamic information, therebyallowing them to use the most efficient approach to purchase
