... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing最新文献
{"title":"A convolutional neural network based approach towards real-time hard hat detection","authors":"Xie Zaipeng, Liu Hanxiang, L. Zewen, He Yuechao","doi":"10.1109/PIC.2018.8706269","DOIUrl":"https://doi.org/10.1109/PIC.2018.8706269","url":null,"abstract":"Health and safety management has been an important issue in construction industry. National regulations impose the using of hard hats in construction sites. However, there are often cases in which the construction workers neglect the regulations. It is desired to monitor the correct wearing of hard hat in real time and explore monitoring techniques facilitated by deep-learning algorithms. In this paper, a convolutional neural network based hard-hat detection algorithm is proposed. In this algorithm, the detection of construction workers and the hard hats are assisted by computer vision technique where deep learning model are trained to identify the proper wearing of hard hats. The optimization of the proposed neural networks can reduce the computational complexity while maintaining a relatively high recognition precision. Experiments have been performed using five different algorithms for comparison and results demonstrate that the proposed algorithm excels in the mAP and FPS performance metrics. The experimental results collected on an embedded platform reveal that the proposed algorithm presents a good candidate for similar applications where real-time deep-learning application is desired.","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88230802","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}
{"title":"湘南会議 The future of multimedia analysis and mining","authors":"N. Boujemaa, Alexander Hauptmann, S. Satoh","doi":"10.2201/NIIPI.2014.11.1","DOIUrl":"https://doi.org/10.2201/NIIPI.2014.11.1","url":null,"abstract":"Recent explosive growth of the amount of accessible multimedia information requires far more intelligent access to multimedia data. Multimedia analysis and mining play a key role to address this problem. For instance, multimedia analysis enables semantic access to multimedia information at any description level and for any applications or needs, even though the original multimedia data may not have any prior semantic annotation. Multimedia mining helps to provide highlevel semantic and structural information to expose key information within a large-scale multimedia database. However, the development of such technologies is often severely limited due to the famous “Semantic Gap” in multimedia content analysis. This is well-known as a supremely difficult issue that is very hard to overcome. On the other hand, researchers in this field now have access to far more computational resources thanks to recent developments in GPU use, multi-core technologies or the availability of cloud computing, as well as far more data resources thanks to the explosive growth of available multimedia data especially via Web. Several research projects have already begun to take advantage of these points independently. Based on the objective, we organized shonan meeting on “The Future of Multimedia Analysis and Mining,” from 3 to 6, November, 2012. In this meeting, we aim to discuss recent research trends and their impact on multimedia research. Then we consolidate key research challenges and explore promising new research directions, hopefully toward “Bridging the semantic gap.” Following the meeting, we organized the special issue on “The Future of Multimedia Analysis and Mining” in the Progress in Informatics. Important topics include the following:","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"9 1","pages":"41-44"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82442869","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}
{"title":"Report on the analyses and the applications of a large-scale news video archive: NII TV-RECS","authors":"I. Ide","doi":"10.2201/NIIPI.2014.11.3","DOIUrl":"https://doi.org/10.2201/NIIPI.2014.11.3","url":null,"abstract":"This paper summarizes the work done in the last twelve years and more, on the structuring and the application of a large-scale digital news video archive: TV-RECS constructed at the National Institute of Informatics. The applications include those that facilitate the exploring and the browsing of the archive, and also the recompilation of its contents for the generation of new video contents.","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"5 1","pages":"9"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74822254","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}
{"title":"Large-scale cross-media analysis and mining from socially curated contents","authors":"Akisato Kimura","doi":"10.2201/NIIPI.2014.11.4","DOIUrl":"https://doi.org/10.2201/NIIPI.2014.11.4","url":null,"abstract":"The major interest of the current social network service (SNS) developers and users are rapidly shifting from conventional text-based (micro)blogs such as Twitter and Facebook to multimedia contents such as Flickr, Snapchat, MySpace and Tumblr. However, the ability to analyze and exploit unorganized multimedia contents on those services still remain inadequate, even with state-of-the-art media processing and machine learning techniques. This paper focuses on another emerging trend called social curation, a human-in-the-loop alternative to automatic algorithms for social media analysis. Social curation can be defined as a spontaneous human process of remixing social media content for the purpose of further consumption. What characterize social curation are definitely the manual efforts involved in organizing a collection of social media contents, which indicates that socially curated content has a potential as a promising information source against automatic summaries generated by algorithms. Curated contents would also provide latent perspectives and contexts that are not explicitly presented in the original resources. Following this trend, this paper presents recent developments and growth of social curation services, and reviews several research trials for cross-media analysis and mining from socially curated contents.","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"59 1","pages":"19"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78700893","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}
{"title":"Scalable Approaches for Content -based Video Retrieval","authors":"T. Ngo","doi":"10.2201/NIIPI.2014.11.5","DOIUrl":"https://doi.org/10.2201/NIIPI.2014.11.5","url":null,"abstract":"This paper addresses content based video retrieval. First, we present an overview of a video retrieval framework and related approaches. Second, we consider two important applications of video retrieval nowadays which are video retrieval based on human face and video retrieval based on generic object categories. The goal is to develop approaches which require lowest annotation cost or computational cost while achieving competitive accuracy so that they can facilitate building scalable and comprehensive video retrieval systems.","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"47 1","pages":"31"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79182737","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}
{"title":"A link utilization estimation scheme for nodes with multiple-queues in output ports","authors":"Kiyofumi Igai, E. Oki","doi":"10.2201/NIIPI.2014.11.7","DOIUrl":"https://doi.org/10.2201/NIIPI.2014.11.7","url":null,"abstract":"This paper proposes a delay-based link utilization estimation scheme that assumes each output port in each node follows themultiple-queuemodel. The conventional alternative assumes only a single-queue model, where link utilization is estimated by using the probability of that the round-trip time of the packet exhibits the minimum delay. However, nodes in an actual network have multiple queues in each output port. Due to the multiple-queue model, the conventional scheme is unable to determine link utilization. This is because the probability that a packet has minimum delay is not directly related to the link utilization. The proposed scheme measures the probability of packet delay and the ratios of probe packets waiting in the queues; it solves simultaneous equations that include the probability of packet delay and queue utilization. Our simulation results show that it can estimate link utilization with error","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"21 1","pages":"45-55"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89536428","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}
{"title":"Dependently typed programming","authors":"Shin-Cheng Mu, Conor McBride, Stephanie Weirich","doi":"10.2201/NIIPI.2013.10.8","DOIUrl":"https://doi.org/10.2201/NIIPI.2013.10.8","url":null,"abstract":"","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"22 1","pages":"149-155"},"PeriodicalIF":0.0,"publicationDate":"2013-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74564675","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}
{"title":"Distributive laws of directed containers","authors":"Danel Ahman, Tarmo Uustalu","doi":"10.2201/NIIPI.2013.10.2","DOIUrl":"https://doi.org/10.2201/NIIPI.2013.10.2","url":null,"abstract":"Containers are an elegant representation of a wide class of datatypes in terms of positions and shapes. We have recently introduced directed containers as a special case to account for the common situation where every position in a shape determines another shape, informally the subshape rooted by that position. While containers interpret into set functors via a fully faithful functor, directed containers denote comonads fully faithfully. In fact, directed containers correspond to exactly those containers that carry a comonad structure. Directed containers can also be seen as a generalization (a dependently typed version) of monoids. While the category of containers (just as the category of set functors) carries a composition monoidal structure, directed containers (just as comonads) do not generally compose. In this paper, we develop a concept of a distributive law between two directed containers corresponding to that of a distributive law between two comonads and spell out the distributivelaw based composition construction of directed containers. This turns out to generalize the Zappa-Szép product of two monoids.","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"8 1","pages":"3"},"PeriodicalIF":0.0,"publicationDate":"2013-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75513249","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}
{"title":"Load-balanced routing with selective even traffic splitting ∗","authors":"M. Honma, S. Tsunoda, E. Oki","doi":"10.2201/NIIPI.2013.10.11","DOIUrl":"https://doi.org/10.2201/NIIPI.2013.10.11","url":null,"abstract":"This paper proposes an even-split Smart-OSPF (S-OSPF) scheme to reduce network congestion more than the conventional non-split S-OSPF and to distribute traffic more easily than the conventional split S-OSPF. In split S-OSPF, source edge nodes distribute traffic unevenly to their neighbor nodes, but the implementation becomes involved to split traffic with different distribution. In non-split S-OSPF, source edge nodes transmit traffic to only one neighbor so that network congestion can be minimized, where non-split S-OSPF distributes traffic more simply than split S-OSPF. In the proposed scheme, source edge nodes transmit traffic evenly to selected neighbor nodes to minimize network congestion. The optimization problem to select a suitable set of neighbor nodes for even traffic distribution raised by the proposed scheme is formulated as an Integer Linear Programming (ILP) problem. The difficulty of solving the ILP problem in a practical time leads us to introduce a heuristic algorithm. The performances of our developed heuristic algorithm are evaluated via simulation developed in terms of network size. Numerical results show that even-split S-OSPF offers better routing performance than non-split S-OSPF for small-size networks and matches that of split S-OSPF for large-size networks.","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"43 1","pages":"175"},"PeriodicalIF":0.0,"publicationDate":"2013-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80258378","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}
{"title":"Automated techniques for higher-order program verification","authors":"N. Kobayashi, Luke Ong, David Van Horn","doi":"10.2201/NIIPI.2013.10.9","DOIUrl":"https://doi.org/10.2201/NIIPI.2013.10.9","url":null,"abstract":"interpretation techniques are used to derive a control-flow analysis for a simple higher-order functional language. The analysis approximates the interprocedural control-flow of both function calls and returns in the presence of first-class functions and tail-call optimization. The analysis is systematically derived by abstract interpretation of the stack-based CaEK abstract machine of Flanagan et al. using a series of Galois connections. The analysis induces an equivalent constraint-based formulation, thereby providing a rational reconstruction of a constraintbased, higher-order CFA from abstract interpretation principles. Joint work with Jan Midtgaard. CFA2: Pushdown Flow Analysis for Higher-Order Languages Dimitrios Vardoulakis (Northeastern University) Flow analysis is a valuable tool for creating better programming languages; its applications span optimization, debugging, verification and program understanding. Despite its apparent usefulness, flow analysis of higher-order programs has not been made practical. The reason is that existing analyses do not model function call and return well: they remember only a bounded number of pending calls because they approximate programs with control-flow graphs. Call/return mismatch results in imprecision and increases the analysis time. In this talk I will describe CFA, a flow analysis that provides unbounded call/return matching in","PeriodicalId":91638,"journal":{"name":"... Proceedings of the ... IEEE International Conference on Progress in Informatics and Computing. IEEE International Conference on Progress in Informatics and Computing","volume":"32 1","pages":"157-165"},"PeriodicalIF":0.0,"publicationDate":"2013-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79648424","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}