Filters








45 Hits in 1.8 sec

Scalable object instance recognition based on keygraph matching

Estephan Dazzi, Teofilo de Campos, Adrian Hilton, Roberto M. Cesar -
2017 Pattern Recognition Letters  
Our experiments concern large-scale object instance recognition subject to occlusion, background clutter and appearance changes.  ...  By using 4-keygraphs, RANSAC needed 1% of the iterations in comparison with 2-keygraphs or simple keypoints.  ...  For example, object instance recognition applied to visual search, augmented reality or object manipulation by robots.  ... 
doi:10.1016/j.patrec.2017.10.038 fatcat:ycqldkjmybbj7alsxasxyji6aa

Improved Object Matching Using Structural Relations [chapter]

Estephan Dazzi, Teofilo de Campos, Roberto M. Cesar
2014 Lecture Notes in Computer Science  
This paper presents a method for object matching that uses local graphs called keygraphs instead of simple keypoints.  ...  This speeds up an object matching pipeline, particularly using RANSAC, because each keygraph match contains enough information to produce a pose hypothesis, significantly reducing the number of local matches  ...  [4] , which focused on fast object detection using a single training image.  ... 
doi:10.1007/978-3-662-44415-3_45 fatcat:hjoee53uzjf3nlbvk5pm32imfu

Chance discovery with data crystallization for scenario formation in solar cell technology

Tzu-Fu Chiu, Chao-Fu Hong, Ming-Yeu Wang, Yu-Ting Chiu
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
As the solar cell, one of renewable energies, is growing at a fast pace, the recognition of its technological situation becomes necessary for a company and stakeholders nowadays.  ...  Unobservable events and their relations with other events are to be visualized by applying KeyGraph [12] .  ...  Result of Diagram Integration By integrating the KeyGraph and crystallization diagram, a modified KeyGraph of thin-film was generated as an example in Fig. 4 .  ... 
doi:10.1109/icsmc.2009.5346813 dblp:conf/smc/ChiuHWC09 fatcat:h2vchtrdynfgxih3fvsjqygh5m

Efficient Event Detection for the Blogosphere

Patrick Hennig, Philipp Berger, Daniel Kurzynski, Hannes Rantzsch, Christoph Meinel
2014 2014 IEEE Fourth International Conference on Big Data and Cloud Computing  
The presented algorithms detects unique happenings at a given point in time by perceiving unusual frequent occurrences of words or word groups.  ...  In this paper we come up with a novel approach for the early detection of events in blog entries. The detection of trend is already discussed pretty often.  ...  Event detection algorithms could be used for disaster recognition. Sakaki et al. used Twitter in their work [1] to detect earthquakes before the disaster prevention could recognize them.  ... 
doi:10.1109/bdcloud.2014.67 dblp:conf/bdcloud/HennigBKRM14 fatcat:q5tubecth5h7hbzxlrdxj4jao4

Data mining of mental health issues of non-bone marrow donor siblings

Morihito Takita, Yuji Tanaka, Yuko Kodama, Naoko Murashige, Nobuyo Hatanaka, Yukiko Kishi, Tomoko Matsumura, Yukio Ohsawa, Masahiro Kami
2011 Journal of Clinical Bioinformatics  
The issues have been alleviated by her family.  ...  Also analysts should know the background of the objectives to interpret KeyGraph effectively as analysts understood social background of all-HSCT in this study.  ...  KeyGraph was created and tuned by an information engineer in discussion with healthcare professionals.  ... 
doi:10.1186/2043-9113-1-19 pmid:21884635 pmcid:PMC3164612 fatcat:pd7d7qqebjajthdfuip76fcm6e

IEEE Transactions on Industrial Electronics

2016 IEEE transactions on industrial electronics (1982. Print)  
This work was partly supported by the US government.  ...  The dark matter refers to hypothetical particles which do not emit or reflect radiation to be detected directly.  ...  KeyGraph fails to visualize such a latent strucutre.  ... 
doi:10.1109/tie.2016.2583341 fatcat:p73rzwgqzrhsvftj5x4wbzk4l4

IEEE Transactions on Industrial Electronics

2016 IEEE transactions on industrial electronics (1982. Print)  
This work was partly supported by the US government.  ...  The dark matter refers to hypothetical particles which do not emit or reflect radiation to be detected directly.  ...  KeyGraph fails to visualize such a latent strucutre.  ... 
doi:10.1109/tie.2016.2593650 fatcat:byhamlcvxnb2bk7crl5edc7j4a

IEEE Transactions on Industrial Electronics

2016 IEEE transactions on industrial electronics (1982. Print)  
This work was partly supported by the US government.  ...  The dark matter refers to hypothetical particles which do not emit or reflect radiation to be detected directly.  ...  KeyGraph fails to visualize such a latent strucutre.  ... 
doi:10.1109/tie.2016.2593610 fatcat:in6x7zmoxvb73jusazoybvugve

IEEE Transactions on Industrial Electronics

1983 IEEE transactions on industrial electronics (1982. Print)  
This work was partly supported by the US government.  ...  The dark matter refers to hypothetical particles which do not emit or reflect radiation to be detected directly.  ...  KeyGraph fails to visualize such a latent strucutre.  ... 
doi:10.1109/tie.1983.356694 fatcat:fvlgydtxnzfnhl4q6amq6uwmku

IEEE Transactions On Industrial Electronics

1982 IEEE transactions on industrial electronics (1982. Print)  
This work was partly supported by the US government.  ...  The dark matter refers to hypothetical particles which do not emit or reflect radiation to be detected directly.  ...  KeyGraph fails to visualize such a latent strucutre.  ... 
doi:10.1109/tie.1982.354126 fatcat:cfxqmqcsoff5hpslfaw75bxm6y

SocialTree

Gevorg Poghosyan, Georgiana Ifrim
2019 Proceedings of the 30th ACM Conference on Hypertext and Social Media - HT '19  
Existing event detection, topic-modeling, clustering and summarization methods yield news story summaries based only on noun phrases and named entities.  ...  In this work, we present an approach to efficiently extract structured summaries of news stories by augmenting news media with the structure of social discourse as reflected in social media in the form  ...  ACKNOWLEDGMENTS This work was funded by Science Foundation Ireland (SFI) under grant number 12/RC/2289_P2. The authors would like to thank Eileen Culloty and the reviewers for their helpful feedback.  ... 
doi:10.1145/3342220.3343668 dblp:conf/ht/PoghosyanI19 fatcat:mpci3nprwjhevphqrrw3ho3sa4

Matching Article Pairs with Graphical Decomposition and Convolutions [article]

Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu
2019 arXiv   pre-print
We then match a pair of articles by comparing the sentences that enclose the same concept vertex through a series of encoding techniques, and aggregate the matching signals through a graph convolutional  ...  Concepts can be extracted by applying community detection algorithms on the constructed KeyGraph.  ...  Each keyword is a vertex in the KeyGraph. We connect a pair of keywords by an edge if they co-occur in at least one sentence. Concept Detection.  ... 
arXiv:1802.07459v2 fatcat:x436jyfbxjeb7euf5fmbp5nxsa

Automatic Life-Logging: A novel approach to sense real-world activities by environmental sound cues and common sense

Mostafa Al Masum Shaikh, Md. Khademul Islam Molla, Keikichi Hirose
2008 2008 11th International Conference on Computer and Information Technology  
Only very recently the detection of real-world activities has been attempted by processing multiple sensors data along with inference logic for real-world activities.  ...  To the best of our knowledge, this system pioneers the use of environmental sound based activity recognition in mobile computing to reflect one's real-world activity for ambient communication.  ...  This work was supported in part by a grant from Japan Society for the Promotion of Science (JSPS).  ... 
doi:10.1109/iccitechn.2008.4803018 fatcat:n4plmhxdwbaphpedkwbdyxu2tm

Matching Article Pairs with Graphical Decomposition and Convolutions

Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
We then match a pair of articles by comparing the sentences that enclose the same concept vertex through a series of encoding techniques, and aggregate the matching signals through a graph convolutional  ...  Concept Detection (Optional). The structure of KeyGraph reveals the connections between keywords.  ...  By using overlapping community detection, each keyword may appear in multiple concepts.  ... 
doi:10.18653/v1/p19-1632 dblp:conf/acl/LiuNWGHLX19 fatcat:uotywfpby5eojahfnjnbke6fhq

Recognition of Real-World Activities from Environmental Sound Cues to Create Life-Log [chapter]

Mostafa Al Masum Shaikh, Keikichi Hirose, Mitsuru Ishizuk
2011 The Systemic Dimension of Globalization  
Acoustic Event Detection (AED) is a recent sub-area of computational auditory scene analysis (Wang and Brown, 2006 ) that deals with the first objective.  ...  Only very recently the detection of real-world activities has been attempted by processing multiple sensors data along with inference logic for real-world activities.  ...  The system (Philipose et al., 2004) utilized RFID tags to detect objects and thereby inference of activities is done from the interaction with the detected objects.  ... 
doi:10.5772/22491 fatcat:l66k3mgwzvhmvniy6b6mhmobce
« Previous Showing results 1 — 15 out of 45 results