Filters








97 Hits in 3.2 sec

Distance metric learning and feature combination for shape-based 3D model retrieval

Ryutarou Ohbuchi, Takahiko Furuya
2010 Proceedings of the ACM workshop on 3D object retrieval - 3DOR '10  
The proposed method then uses an unsupervised distance metric learning based on the Manifold Ranking (MR) [15] to compute distances between these features.  ...  This paper proposes a 3D model retrieval algorithm that employs an unsupervised distance metric learning with a combination of appearance-based features; two sets of local visual features and a set of  ...  This research has been funded in part by the Ministry of Education, Culture, Sports, Sciences, and Technology of Japan (No. 18300068).  ... 
doi:10.1145/1877808.1877822 dblp:conf/mm/OhbuchiF10 fatcat:a7mpsxzcgnculkge5cqaojzrwu

Unsupervised manifold learning through reciprocal kNN graph and Connected Components for image retrieval tasks

Daniel Carlos Guimarães Pedronette, Filipe Marcel Fernandes Gonçalves, Ivan Rizzo Guilherme
2018 Pattern Recognition  
This paper proposes a novel manifold learning approach that exploits the intrinsic dataset geometry for improving the effectiveness of image retrieval tasks.  ...  The underlying dataset manifold is modeled and analyzed in terms of a Reciprocal kNN Graph and its Connected Components.  ...  Acknowledgments The authors are grateful to FAPESP -São Paulo Research Foundation (grant # 2013/08645-0 ) and CAPES -Coordination for Higher Education Staff Development.  ... 
doi:10.1016/j.patcog.2017.05.009 fatcat:wdojfu33brf5zbzm6kzboms4ru

SHREC'10 Track: Non-rigid 3D Shape Retrieval [article]

Z. Lian, A. Godil, T. Fabry, T. Furuya, J. Hermans, R. Ohbuchi, C. Shu, D. Smeets, P. Suetens, D. Vandermeulen, S. Wuhrer
2010 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
The aim of the 3D Shape Retrieval Contest 2010 (SHREC'10) track on non-rigid 3D shape retrieval is to evaluate and compare the effectiveness of different methods run on a non-rigid 3D shape benchmark consisting  ...  of 200 watertight triangular meshes.  ...  We would like to thank the Shape Analysis Group in McGill University for providing the McGill 3D Shape Benchmark database, and we are also grateful to Benny Cheung for creating the web interface mentioned  ... 
doi:10.2312/3dor/3dor10/101-108 fatcat:mu62iibph5cojanbonil6vvvh4

Persistent-Homology-based Machine Learning and its Applications -- A Survey [article]

Chi Seng Pun and Kelin Xia and Si Xian Lee
2018 arXiv   pre-print
Essentially, this paper can work as a roadmap for the practical application of PH-based machine learning tools.  ...  In this paper, we provide a systematical review of PH and PH-based supervised and unsupervised models from a computational perspective.  ...  research is partially supported by Nanyang Technological University Startup Grants M4081840 and M4081842, Data Science and Artificial Intelligence Research Centre@NTU M4082115, and Singapore Ministry of  ... 
arXiv:1811.00252v1 fatcat:urarw3cvlreulcpdyapltj6caa

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

Bo Li, Yijuan Lu, Chunyuan Li, Afzal Godil, Tobias Schreck, Masaki Aono, Martin Burtscher, Qiang Chen, Nihad Karim Chowdhury, Bin Fang, Hongbo Fu, Takahiko Furuya (+10 others)
2015 Computer Vision and Image Understanding  
It was compiled to be a superset of existing benchmarks and presents a new challenge to retrieval methods as it comprises generic models as well as domain-specific model types.  ...  To measure and compare the performance of the participating and other promising Query-by-Model or Query-by-Sketch 3D shape retrieval methods and to solicit state-of-the-art approaches, we perform a more  ...  We would like to thank Mathias Eitz, James Hays and Marc Alexa who collected the 250 classes of sketches. We would also like to thank the following authors for building the 3D benchmarks:  ... 
doi:10.1016/j.cviu.2014.10.006 fatcat:d3feizyi6rg63g5lra7mczvj2a

A comparison of methods for sketch-based 3D shape retrieval

Bo Li, Yijuan Lu, Afzal Godil, Tobias Schreck, Benjamin Bustos, Alfredo Ferreira, Takahiko Furuya, Manuel J. Fonseca, Henry Johan, Takahiro Matsuda, Ryutarou Ohbuchi, Pedro B. Pascoal (+1 others)
2014 Computer Vision and Image Understanding  
To measure and compare the performance of the top participating and other existing promising sketch-based 3D shape retrieval methods and solicit the state-of-the-art approaches, we perform a more comprehensive  ...  The benchmarks, results, and evaluation tools for the two tracks are publicly available on our websites [1,2].  ...  The entries of their methods employ unsupervised distance metric learning to overcome this gap. First approach, called Uniform Manifold Ranking, or UMR, is of unsupervised kind.  ... 
doi:10.1016/j.cviu.2013.11.008 fatcat:3stzuphlo5ds5emnhtceepojcu

Machine Learning on Graphs: A Model and Comprehensive Taxonomy [article]

Ines Chami, Sami Abu-El-Haija, Bryan Perozzi, Christopher Ré, Kevin Murphy
2021 arXiv   pre-print
There has been a surge of recent interest in learning representations for graph-structured data.  ...  We propose a comprehensive taxonomy of representation learning methods for graph-structured data, aiming to unify several disparate bodies of work.  ...  We gratefully acknowledge the support of DARPA under Nos. S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
arXiv:2005.03675v2 fatcat:xqu7k5jihnfa5eotayd5xximnm

Adversarial Reconstruction Loss for Domain Generalization

Bekkouch Imad Eddine Ibrahim, Dragos Constantin Nicolae, Adil Khan, S. M. Ahsan Kazmi, Asad Masood Khattak, Bulat Ibragimov
2021 IEEE Access  
unlike manifold learning methods which are mostly unsupervised or lack the easy integration with other deep learning components.  ...  Reconstruction loss is also used for domain adaptation by jointly learning a shared encoding representation for: i) supervised classification ii) unsupervised reconstruction of unlabeled data [34] , this  ...  He is Senior Member of IEEE and appointed as ACM Distinguish Speaker.  ... 
doi:10.1109/access.2021.3066041 fatcat:ic2xcqbzobhqbdhwmjx4fwzhjq

SHREC'09 Track: Generic Shape Retrieval [article]

A. Godil, H. Dutagaci, C. Akgül, A. Axenopoulos, B. Bustos, M. Chaouch, P. Daras, T. Furuya, S. Kreft, Z. Lian, T. Napoléon, A. Mademlis (+9 others)
2009 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
Seven groups have participated in the track and they have submitted 22 sets of rank lists based on different methods and parameters.  ...  The aim of this track was to evaluate the performances of various 3D shape retrieval algorithms on the NIST generic shape benchmark.  ...  Manifold Ranking The performance of the composite shape descriptor can be further increased by utilizing the manifold ranking method.  ... 
doi:10.2312/3dor/3dor09/061-068 fatcat:5edwfisswnhbna44yap3wrvkte

One Plus One Makes Three (for Social Networks)

Emöke-Ágnes Horvát, Michael Hanselmann, Fred A. Hamprecht, Katharina A. Zweig, Sergio Gómez
2012 PLoS ONE  
Members of social network platforms often choose to reveal private information, and thus sacrifice some of their privacy, in exchange for the manifold opportunities and amenities offered by such platforms  ...  information to deduce a substantial proportion of relationships between non-members.  ...  Link prediction was mostly approached with unsupervised [11] and recently also with supervised learning methods [12] [13] [14] .  ... 
doi:10.1371/journal.pone.0034740 pmid:22493713 pmcid:PMC3321038 fatcat:qr55nomutzhsnfkzbtiyt4cc6u

Survey on graph embeddings and their applications to machine learning problems on graphs

Ilya Makarov, Dmitrii Kiselev, Nikita Nikitinsky, Lovro Subelj
2021 PeerJ Computer Science  
compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems.  ...  As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to  ...  j of manifold U.  ... 
doi:10.7717/peerj-cs.357 pmid:33817007 pmcid:PMC7959646 fatcat:ntronyrbgfbedez5dks6h4hoq4

Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0) [article]

Wen Li, Ying Zhang, Yifang Sun, Wei Wang, Wenjie Zhang, Xuemin Lin
2016 arXiv   pre-print
In this paper, we conduct a comprehensive experimental evaluation of many state-of-the-art methods for approximate nearest neighbor search.  ...  Furthermore, we propose a new method that achieves both high query efficiency and high recall empirically on majority of the datasets under a wide range of settings.  ...  Rank Cover Tree Rank cover tree (RCT) [23] is a probabilistic data structure for similarity search, which entirely avoids the use of numerical constraints such as triangle inequality.  ... 
arXiv:1610.02455v1 fatcat:skn6iftztnhr7d524fqvyqix3m

Acoustic Self-Awareness of Autonomous Systems in a World of Sounds

Alexander Schmidt, Heinrich W. Lollmann, Walter Kellermann
2020 Proceedings of the IEEE  
Then, a comprehensive overview of current techniques for ego-noise suppression, as a specific additional challenge for ASs, is presented.  ...  | Autonomous systems (ASs) operating in realworld environments are exposed to a plurality and diversity of sounds that carry a wealth of information for perception in cognitive dynamic systems.  ...  In [206] , Laplacian eigenmaps are used as manifold learning technique and constructed by an unsupervised approach using so-called auditory-evoked orientation behavior: as soon as an auditory event is  ... 
doi:10.1109/jproc.2020.2977372 fatcat:immaqhfnkna6xdwj3dqlh7qewi

A Tutorial on Network Embeddings [article]

Haochen Chen, Bryan Perozzi, Rami Al-Rfou, Steven Skiena
2018 arXiv   pre-print
Then, we discuss network embedding methods under different scenarios, such as supervised versus unsupervised learning, learning embeddings for homogeneous networks versus for heterogeneous networks, etc  ...  Network embedding methods aim at learning low-dimensional latent representation of nodes in a network.  ...  a biased random walking procedure which combines BFS style and DFS style neighborhood exploration. • Walklets [34] shows that DeepWalk learns network embeddings from a weighted combination of A, A 2  ... 
arXiv:1808.02590v1 fatcat:ramuqdavczfabb4o7r42kice7q

Review on Graph Feature Learning and Feature Extraction Techniques for Link Prediction [article]

Ece C. Mutlu, Toktam A. Oghaz, Amirarsalan Rajabi, Ivan Garibay
2020 arXiv   pre-print
Extensive studies have examined this problem from different aspects and proposed various methods, some of which might work very well for a specific application but not as a global solution.  ...  models, and learning-based methods.  ...  The model consists BFS algorithm to limit the number of edge prediction and accordingly, alleviate the computational complexity as a result of node ranking in the edge formation procedure.  ... 
arXiv:1901.03425v4 fatcat:o4mg2dopjrhe3kesmzfg3zegui
« Previous Showing results 1 — 15 out of 97 results