Filters








50,659 Hits in 6.4 sec

Human Centric Recognition of 3D Ear Models

Guy De Tré, Robin De Mol, Dirk Vandermeulen, Peter Claes, Jeroen Hermans, Joachim Nielandt
2016 International Journal of Computational Intelligence Systems  
A novel bipolar measure for computing the similarity between corresponding feature lists is proposed.  ...  A feature list is then extracted from each 3D ear model and used in the recognition process.  ...  Assessing Data Quality Denote that a 3D ear model is an artificial representation of a real ear shape, which is constructed based on the available information.  ... 
doi:10.1080/18756891.2016.1150002 fatcat:pjsyx7xvyzgqvhgyx67sjv3x3y

Towards a general-purpose query language for visualization recommendation

Kanit Wongsuphasawat, Dominik Moritz, Anushka Anand, Jock Mackinlay, Bill Howe, Jeffrey Heer
2016 Proceedings of the Workshop on Human-In-the-Loop Data Analytics - HILDA '16  
We present the preliminary design of CompassQL, which defines (1) a partial specification that describes enumeration constraints, and (2) methods for choosing, ranking, and grouping recommended visualizations  ...  However, designing interfaces, ranking metrics, and scalable recommender systems remain important research challenges.  ...  This work was partly supported by the Intel Big Data ISTC, DARPA XDATA, the Gordon & Betty Moore Foundation, and the UW eScience Institute.  ... 
doi:10.1145/2939502.2939506 dblp:conf/sigmod/WongsuphasawatM16 fatcat:dsy5nuv6r5bybpq7au6phtm43e

Partial Shape Queries for 3D Object Retrieval [article]

Ioannis Pratikakis, Michalis A. Savelonas, Fotis Arnaoutoglou, George Ioannakis, Anestis Koutsoudis, Theoharis Theoharis, Minh-Triet Tran, Vinh-Tiep Nguyen, V.-K. Pham, Hai-Dang Nguyen, Hoang-An Le, Ba-Huu Tran (+16 others)
2016 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
Despite numerous recent efforts, 3D object retrieval based on partial shape queries remains a challenging problem, far from being solved.  ...  The problem can be defined as: given a partial view of a shape as query, retrieve all partially similar 3D models from a repository.  ...  For each partial query, a partial 3D object retrieval method is required to return a ranked list of complete objects, which are retrieved from a database and are ranked according to their similarity with  ... 
doi:10.2312/3dor.20161091 fatcat:byczfavqxnfrzptaar4frpnudy

Slide image retrieval

Guo Min Liew, Min-Yen Kan
2008 Proceedings of the 8th ACM/IEEE-CS joint conference on Digital libraries - JCDL '08  
We show promising results in both the ranking and binary relevance task and analyze the contribution of different features in the task performance.  ...  We consider the task of automatic slide image retrieval, in which slide images are ranked for relevance against a textual query.  ...  Content Based Image Retrieval (CBIR) has been generating substantial interest, employing color, texture and shape features.  ... 
doi:10.1145/1378889.1378951 dblp:conf/jcdl/LiewK08 fatcat:laayef2hjjarxjcl4bseplck2a

High-Dimensional Indexing for Video Retrieval [chapter]

Catalin Calistru, Cristina Ribeiro, Gabriel Davi
2012 Multimedia - A Multidisciplinary Approach to Complex Issues  
Thus, the model is not directly applicable on the original feature values, but on intermediate rank lists.  ...  In such a case, descriptor-wise rank lists are obtained, and a further aggregation strategy is required.  ... 
doi:10.5772/37303 fatcat:smjtgyx5sjh5pc45oyvqq5eotm

Analysis of Different Techniques for Person Re-Identification: An Assessment

Richa Jain, Prof. Seema Shukla
2019 Zenodo  
Also, person determined from utterly completely different camera views has very important variations on poses and viewpoints.  ...  Person re identification is also a tough analysis topic as a result of partial occlusions, low resolution images and massive illumination changes.  ...  Partial least square (PLS) is a powerful statistical tool used for weighting the features based on their discriminative power for different appearance.  ... 
doi:10.5281/zenodo.3605938 fatcat:4xadgmsfq5b35lj2mun5dinxqa

Robust rank aggregation for gene list integration and meta-analysis

Raivo Kolde, Sven Laur, Priit Adler, Jaak Vilo
2012 Computer applications in the biosciences : CABIOS  
Results: Standard rank aggregation methods are often ill-suited for biological settings where the gene lists are inherently noisy. As a remedy we propose a novel robust rank aggregation (RRA) method.  ...  Thus the rank aggregation methods can become a useful and general solution for the integration task.  ...  A general strategy for obtaining an aggregated preference list is to score each rank vector somehow and order the genes based on the scores.  ... 
doi:10.1093/bioinformatics/btr709 pmid:22247279 pmcid:PMC3278763 fatcat:7sn45nzggnd5lofj5jfkzmcgyi

Boosting the handwritten word spotting experience by including the user in the loop

Marçal Rusiñol, Josep Lladós
2014 Pattern Recognition  
The increase in terms of precision when the user is included in the loop is assessed using two datasets of historical handwritten documents and two baseline word spotting approaches both based on the bag-of-visual-words  ...  We finally present two alternative ways of presenting the results to the user that might be more attractive and suitable to the user's needs than the classic ranked list.  ...  Acknowledgment This work has been partially supported by the Spanish Ministry of Education and Science under projects TIN2009-14633-C03-03 and TIN2012-37475-C02-02.  ... 
doi:10.1016/j.patcog.2013.07.008 fatcat:ak6v7pvh6baajjigfl6fyrofla

Improving 3D similarity search by enhancing and combining 3D descriptors

Benjamin Bustos, Tobias Schreck, Michael Walter, Juan Manuel Barrios, Matthias Schaefer, Daniel Keim
2011 Multimedia tools and applications  
We give a systematic discussion of the descriptor combination space involving static and query-adaptive weighting schemes, and based on descriptors of different type and focus (model global vs. partial  ...  Many individual methods proposed to date rely on calculating global 3D model descriptors based on image, surface, volumetrie, or structural model properties.  ...  Acknowledgements We tha nk Dejan Vranic and Dietmar Saupe for providing the base 3D descriptor extractors used in our work.  ... 
doi:10.1007/s11042-010-0689-6 fatcat:prhzwvuz5jet5d6pbpbngrnfvy

Assessing photo quality with geo-context and crowdsourced photos

Wenyuan Yin, Tao Mei, Chang Wen Chen
2012 2012 Visual Communications and Image Processing  
Most existing approaches to photo quality assessment have predominantly focused on image content itself, while ignoring various contexts such as the associated geo-location and timestamp.  ...  Geo-contextual leveraged searching is performed to obtain relevant images with similar content to discover the scene-dependent photography principles for accurate photo quality assessment.  ...  Though the positive data and negative data can be generated by simply splitting the aesthetics based ranking list into two halves, the photos ranked in the middle increase the ambiguity in ratings.  ... 
doi:10.1109/vcip.2012.6410821 dblp:conf/vcip/YinMC12 fatcat:u26akiq2znb3licursgycl27ma

A multi-criteria group decision-making method for the thermal renovation of masonry buildings: The case of Algeria

Mohammed Seddiki, Karima Anouche, Amar Bennadji, Prince Boateng
2016 Energy and Buildings  
It had very week features in the risk of the loss of building historic 538 aesthetic features (C3). 539 Based on the above ranking of DM1, (A7) was the best action despite the fact that it has weak 540  ...  the thermal renovation of buildings can be ranked into two different approaches, 78 the partial aggregation approach, and the complete aggregations approach. 137 2. 2 1372 Multi objective optimization  ... 
doi:10.1016/j.enbuild.2016.08.023 fatcat:mh5cjohdmbfvvbvgtfdx2xheqy

Similarity Based Object Retrieval of Composite Neuronal Structures [article]

Florian Schulze, Martin Trapp, Katja Bühler, Tianxiao Lui, Barry Dickson
2012 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
To enable similarity based retrieval of neuronal objects we defined together with domain experts tailored dissimilarity measures for each of the three typical neuronal sub structures cell body, projection  ...  Circuit Neuroscience tries to solve one of the most challenging questions in biology: How does the brain work?  ...  The first case is based on unrelated geometric very similar shapes, whilst the second case also contains partial matches in the top ranks.  ... 
doi:10.2312/3dor/3dor12/001-008 fatcat:5ad6uq7pnra4zhuimdqssylrry

Bayesian Analysis of Rank Data with Covariates and Heterogeneous Rankers [article]

Xinran Li, Dingdong Yi, Jun S. Liu
2020 arXiv   pre-print
Data in the form of ranking lists are frequently encountered, and combining ranking results from different sources can potentially generate a better ranking list and help understand behaviors of the rankers  ...  The posterior samples also result in a Bayesian aggregated ranking list, with credible intervals quantifying its uncertainty.  ...  ACKNOWLEDGMENT This research is supported in part by the NSF Grants DMS-1712714 and MS-1903139.  ... 
arXiv:1607.06051v3 fatcat:c6ogbfuesbcdhmuqg3vxdnbwk4

Are We There Yet? A Review on Existing Perceptual Theory and Experiment Support for Visualization Recommendation Systems [article]

Zehua Zeng, Minhui Xie, Matthew Gouzoulis, Leilani Battle
2021 arXiv   pre-print
Based on our findings, we highlight new opportunities and challenges for the community in working towards a comprehensive visualization ranking for informing visualization recommendation systems.  ...  Thus, in this paper, we present a literature review comparing and ranking the quality of visualization designs in visual perception and human performance.  ...  ACKNOWLEDGMENTS Authors would like to thank the BAD Lab and our paper reviewers for their thoughtful feedback. This work was supported in part by NSF award IIS-1850115 and an Adobe Research Award.  ... 
arXiv:2109.01271v1 fatcat:7svhidek5zgwhoehvx6qo2p4ry

SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods [article]

Hyeoncheol Cho, Youngrock Oh, Eunjoo Jeon
2021 arXiv   pre-print
Experiments on matching motif-participating nodes from a given graph show great improvement in explanation accuracy of up to 12.71% and demonstrate the correlation between the auxiliary explanations and  ...  In this study, we propose a method to improve the explanation quality of node classification tasks that can be applied in a post hoc manner through aggregation of auxiliary explanations from important  ...  Acknowledgments and Disclosure of Funding We thank Taehee Lee for his helpful comments. Funding in direct support of this work was obtained from Samsung SDS.  ... 
arXiv:2106.08532v1 fatcat:kxkjuhmorjf5tfbrcbokl2j33i
« Previous Showing results 1 — 15 out of 50,659 results