Pub Date : 2023-12-12DOI: 10.1007/978-981-99-8391-9_33
Trevor Londt, Xiaoying Gao, Peter M. Andreae, Yi Mei
{"title":"XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks","authors":"Trevor Londt, Xiaoying Gao, Peter M. Andreae, Yi Mei","doi":"10.1007/978-981-99-8391-9_33","DOIUrl":"https://doi.org/10.1007/978-981-99-8391-9_33","url":null,"abstract":"","PeriodicalId":91448,"journal":{"name":"Applied informatics","volume":"15 8","pages":"416-428"},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139007394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-06DOI: 10.1007/978-981-99-8388-9_37
Mitchell Keegan, Mahdi Abolghasemi
{"title":"Approximating Solutions to the Knapsack Problem Using the Lagrangian Dual Framework","authors":"Mitchell Keegan, Mahdi Abolghasemi","doi":"10.1007/978-981-99-8388-9_37","DOIUrl":"https://doi.org/10.1007/978-981-99-8388-9_37","url":null,"abstract":"","PeriodicalId":91448,"journal":{"name":"Applied informatics","volume":"55 15","pages":"455-467"},"PeriodicalIF":0.0,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138597722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1007/978-3-030-97546-3_47
Rachid Adrdor, L. Koutti
{"title":"Improvement of Arc Consistency in Asynchronous Forward Bounding Algorithm","authors":"Rachid Adrdor, L. Koutti","doi":"10.1007/978-3-030-97546-3_47","DOIUrl":"https://doi.org/10.1007/978-3-030-97546-3_47","url":null,"abstract":"","PeriodicalId":91448,"journal":{"name":"Applied informatics","volume":"1 1","pages":"582-591"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42374380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-09DOI: 10.48550/arXiv.2211.04773
Anh Duc Bui, S. Han, Josiah Poon
. Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated data, the scene graph generated from current methodologies can be biased toward common, non-informative relationship labels. Relationship can sometimes be non-mutually exclusive, which can be described from multiple perspectives like geometrical relationships or semantic relationships, making it even more challenging to predict the most suitable relationship label. In this work, we proposed the SG-Shuffle pipeline for scene graph generation with 3 components: 1) Parallel Transformer Encoder, which learns to predict object relationships in a more exclusive manner by grouping relationship labels into groups of similar purpose; 2) Shuffle Transformer, which learns to select the final relationship labels from the category-specific feature generated in the previous step; and 3) Weighted CE loss, used to alleviate the training bias caused by the imbalanced dataset.
场景图生成（SGG）为人类理解以及视觉理解任务提供图像的综合表示。由于可用注释数据中对象和谓词标签的长尾偏误问题，根据当前方法生成的场景图可能偏向于常见的、非信息性的关系标签。关系有时可能是非互斥的，可以从几何关系或语义关系等多个角度进行描述，这使得预测最合适的关系标签变得更加困难。在这项工作中，我们提出了用于场景图生成的SG-Shu-sulue管道，该管道由3个组件组成：1）并行转换器编码器，它通过将关系标签分组到具有类似目的的组中，学习以更排他性的方式预测对象关系；2） Shu sulu e Transformer，它学习从上一步生成的类别特定特征中选择最终的关系标签；以及3）加权CE损失，用于减轻由不平衡数据集引起的训练偏差。
{"title":"SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation","authors":"Anh Duc Bui, S. Han, Josiah Poon","doi":"10.48550/arXiv.2211.04773","DOIUrl":"https://doi.org/10.48550/arXiv.2211.04773","url":null,"abstract":". Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated data, the scene graph generated from current methodologies can be biased toward common, non-informative relationship labels. Relationship can sometimes be non-mutually exclusive, which can be described from multiple perspectives like geometrical relationships or semantic relationships, making it even more challenging to predict the most suitable relationship label. In this work, we proposed the SG-Shuffle pipeline for scene graph generation with 3 components: 1) Parallel Transformer Encoder, which learns to predict object relationships in a more exclusive manner by grouping relationship labels into groups of similar purpose; 2) Shuffle Transformer, which learns to select the final relationship labels from the category-specific feature generated in the previous step; and 3) Weighted CE loss, used to alleviate the training bias caused by the imbalanced dataset.","PeriodicalId":91448,"journal":{"name":"Applied informatics","volume":"1 1","pages":"87-101"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49414200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-06DOI: 10.1007/978-3-031-22695-3_2
Zainy M. Malakan, G. Hassan, A. Mian
{"title":"Vision Transformer Based Model for Describing a Set of Images as a Story","authors":"Zainy M. Malakan, G. Hassan, A. Mian","doi":"10.1007/978-3-031-22695-3_2","DOIUrl":"https://doi.org/10.1007/978-3-031-22695-3_2","url":null,"abstract":"","PeriodicalId":91448,"journal":{"name":"Applied informatics","volume":"1 1","pages":"15-28"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47525714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-21DOI: 10.48550/arXiv.2208.09838
Padraig X. Lamont
This paper presents Tyche, a Python library to facilitate probabilistic reasoning in uncertain worlds through the construction, querying, and learning of belief models. Tyche uses aleatoric description logic (ADL), which provides computational advantages in its evaluation over other description logics. Tyche belief models can be succinctly created by defining classes of individuals, the probabilistic beliefs about them (concepts), and the probabilistic relationships between them (roles). We also introduce a method of observation propagation to facilitate learning from complex ADL observations. A demonstration of Tyche to predict the author of anonymised messages, and to extract author writing tendencies from anonymised messages, is provided. Tyche has the potential to assist in the development of expert systems, knowledge extraction systems, and agents to play games with incomplete and probabilistic information.
{"title":"Tyche: A library for probabilistic reasoning and belief modelling in Python","authors":"Padraig X. Lamont","doi":"10.48550/arXiv.2208.09838","DOIUrl":"https://doi.org/10.48550/arXiv.2208.09838","url":null,"abstract":"This paper presents Tyche, a Python library to facilitate probabilistic reasoning in uncertain worlds through the construction, querying, and learning of belief models. Tyche uses aleatoric description logic (ADL), which provides computational advantages in its evaluation over other description logics. Tyche belief models can be succinctly created by defining classes of individuals, the probabilistic beliefs about them (concepts), and the probabilistic relationships between them (roles). We also introduce a method of observation propagation to facilitate learning from complex ADL observations. A demonstration of Tyche to predict the author of anonymised messages, and to extract author writing tendencies from anonymised messages, is provided. Tyche has the potential to assist in the development of expert systems, knowledge extraction systems, and agents to play games with incomplete and probabilistic information.","PeriodicalId":91448,"journal":{"name":"Applied informatics","volume":"1 1","pages":"381-396"},"PeriodicalIF":0.0,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47013311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-030-97546-3_45
Yikun Yang, F. Ren, Minjie Zhang
{"title":"A Hybrid Multiagent-Based Rescheduling Mechanism for Open and Stochastic Environments Concerning the Execution Stage","authors":"Yikun Yang, F. Ren, Minjie Zhang","doi":"10.1007/978-3-030-97546-3_45","DOIUrl":"https://doi.org/10.1007/978-3-030-97546-3_45","url":null,"abstract":"","PeriodicalId":91448,"journal":{"name":"Applied informatics","volume":"70 1","pages":"556-569"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73834248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：