77 Hits in 6.5 sec

Multimodal Feature Fusion for 3D Shape Recognition and Retrieval

Shuhui Bu, Shaoguang Cheng, Zhenbao Liu, Junwei Han
2014 IEEE Multimedia  
for applying 3D objects in more realms.  ...  Geometry-and view-based methods, for example, only use partial information from a 3D object (see the "Geometry-and View-Based Methods for 3D Shape Analysis" sidebar).  ...  These two local descriptors are robust against nonrigid and complex shape deformations.  ... 
doi:10.1109/mmul.2014.52 fatcat:7zzv65poajfindfd6jtytxj2uy

Learning High-Level Feature by Deep Belief Networks for 3-D Model Retrieval and Recognition

Shuhui Bu, Zhenbao Liu, Junwei Han, Jun Wu, Rongrong Ji
2014 IEEE transactions on multimedia  
After that, high-level shape features are learned via deep belief networks, which are more discriminative for the tasks of shape classification and retrieval.  ...  Index Terms-3-D model recognition, 3-D model retrieval, bag-of-words, deep belief networks, deep learning.  ...  The core idea is to extract a middle-level position-independent feature from any low-level 3D descriptors, and then generate high-level features for 3D shape retrieval via deep learning.  ... 
doi:10.1109/tmm.2014.2351788 fatcat:p6l6xa5rg5a3pj7npyaeklupfe

Multi-feature Fusion Based on Multi-view Feature and 3D Shape Feature for Non-rigid 3D Model Retrieval

Hui Zeng, Qi Wang, Jiwei Liu
2019 IEEE Access  
The convolutional neural network is used for learning the 3D shape feature.  ...  Finally, we use the kernel canonical correlation analysis (KCCA) algorithm to fuse the multi-view feature and the 3D shape feature for retrieval.  ...  Then a many-to-one encoder is developed to learn the 3D shape descriptor for retrieval. Xie et al. proposed a deep multimetric network for 3D shape retrieval [29] .  ... 
doi:10.1109/access.2019.2907609 fatcat:qebiqbvc75f4fewicedl4fh4s4

Deeply Exploiting Long-Term View Dependency for 3D Shape Recognition

Yong Xu, Chaoda Zheng, Ruotao Xu, Yuhui Quan
2019 IEEE Access  
Recognition of 3D shapes is a fundamental task in computer vision. In recent years, view-based deep learning has emerged as an effective approach for 3D shape recognition.  ...  Incorporating the aggregation module into a standard convolutional network architecture, we develop an effective method for 3D shape classification and retrieval.  ...  Therefore, a majority of existing works on 3D object recognition are devoted to building 3D shape features for recognition (i.e. 3D shape recognition).  ... 
doi:10.1109/access.2019.2934650 fatcat:vo7jdyq7qnbnvok6uwhblgzkvm

Extracting Deformation-Aware Local Features by Learning to Deform [article]

Guilherme Potje, Renato Martins, Felipe Cadar, Erickson R. Nascimento
2021 arXiv   pre-print
Our deformation-aware local descriptor, named DEAL, leverages a polar sampling and a spatial transformer warping to provide invariance to rotation, scale, and image deformations.  ...  The experiments show that our method outperforms state-of-the-art handcrafted, learning-based image, and RGB-D descriptors in different datasets with both real and realistic synthetic deformable objects  ...  Acknowledgments and Disclosure of Funding The authors would like to thank CAPES (#88881.120236/2016-01), CNPq, FAPEMIG, and Petrobras for funding different parts of this work. R.  ... 
arXiv:2111.10617v1 fatcat:5yl4kiw6fvcmpjrpz5hvqbvdde

A Tutorial Review on Point Cloud Registrations: Principle, Classification, Comparison, and Technology Challenges

Leihui Li, Riwei Wang, Xuping Zhang, Paolo Spagnolo
2021 Mathematical Problems in Engineering  
A point cloud as a collection of points is poised to bring about a revolution in acquiring and generating three-dimensional (3D) surface information of an object in 3D reconstruction, industrial inspection  ...  scan, such that retrieving multiple point clouds at different viewpoints for better rebuilding the 3D environment or recovering the 3D shape of an object.  ...  Global-based features are often used in 3D object recognition and 3D object categorization, while some global descriptors can be used for pose estimation of the objects because they contain local descriptors  ... 
doi:10.1155/2021/9953910 fatcat:wuzhdxjfybb4herg3s7xdv2zki

Deep understanding of 3-D multimedia information retrieval on social media: implications and challenges

Ritika Wason, Vishal Jain, Gagandeep Singh Narula, Anupam Balyan
2019 Iran Journal of Computer Science  
This has imposed high demands on multimedia information retrieval (MIR) techniques. This manuscript illustrates the MIR concept in terms of its application to social media.  ...  It further positions the current research in the field of 3D MIR. Further it highlights the challenges in 3-D MIR on social media and finally translates them into significant research directions.  ...  shape-aware descriptor for nonrigid 3D object retrieval [15] , [50] , [65] Proposes 3D shape recovery through a multi-level facet learning method High computation time for training the model attributes  ... 
doi:10.1007/s42044-019-00030-5 fatcat:e7kgskeqxbaznbjh3hrmhw3nke

Shape Retrieval of Non-rigid 3D Human Models

D. Pickup, X. Sun, P. L. Rosin, R. R. Martin, Z. Cheng, Z. Lian, M. Aono, A. Ben Hamza, A. Bronstein, M. Bronstein, S. Bu, U. Castellani (+19 others)
2016 International Journal of Computer Vision  
We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models.  ...  3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem.  ...  features for 3D shape retrieval.  ... 
doi:10.1007/s11263-016-0903-8 fatcat:6tbv7dxwnfg7pik54vhs47jumu

Representation, Analysis, and Recognition of 3D Humans

Stefano Berretti, Mohamed Daoudi, Pavan Turaga, Anup Basu
2018 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
, and 3D retrieval [156] .  ...  REPRESENTATIONS OF 3D HUMANS Representations of the 3D human body and face are usually built on low level descriptors that model static (spatial) and dynamic (spatio-temporal) data for extracting meaningful  ...  [83] proposed the intrinsic shape context (ISC) descriptor for 3D shape surfaces as generalization of the 2D SC descriptor.  ... 
doi:10.1145/3182179 fatcat:ds55t4md2na2tibtyg4llerf3q

Intelligent Visual Media Processing: When Graphics Meets Vision

Ming-Ming Cheng, Qi-Bin Hou, Song-Hai Zhang, Paul L. Rosin
2017 Journal of Computer Science and Technology  
for 2D image understanding and 3D model analysis.  ...  processing tools, such as deep neural networks, provide effective ways for learning how to deal with heterogeneous visual data; iii) new data capture devices, such as the Kinect, bridge between algorithms  ...  Acknowledgments We would like to thank the anonymous reviewers for their useful feedback.  ... 
doi:10.1007/s11390-017-1681-7 fatcat:j6u7dzfbhfgnlpnluqajjbaxy4

Learning geodesic-aware local features from RGB-D images

Guilherme Potje, Renato Martins, Felipe Cadar, Erickson R. Nascimento
2022 Computer Vision and Image Understanding  
, as well as in object retrieval and non-rigid surface tracking experiments, with comparable processing times.  ...  We design two complementary local descriptors strategies to compute geodesic-aware features efficiently: one efficient binary descriptor based on handcrafted binary tests (named GeoBit), and one learning-based  ...  Acknowledgments The authors would like to thank CAPES (#88881.120236/2016-01), CNPq, and FAPEMIG for funding different parts of this work. R.  ... 
doi:10.1016/j.cviu.2022.103409 fatcat:mvlfe2p45zfgfkgqrdlrdnhkxa

Table of Contents

2021 IEEE transactions on multimedia  
Hoi 3-D Processing and Presentation Mesh Convolution: A Novel Feature Extraction Method for 3D Nonrigid Object Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Callet Deep Learning for Multimedia Processing 3D Pose Estimation Based on Reinforce Learning for 2D Image-Based 3D Model Retrieval . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tmm.2021.3132246 fatcat:el7u2udtybddrpbl5gxkvfricy

Data-driven shape analysis and processing

Kai Xu, Vladimir G. Kim, Qixing Huang, Niloy Mitra, Evangelos Kalogerakis
2016 SIGGRAPH ASIA 2016 Courses on - SA '16  
, etc.), offer great opportunities for developing data-driven approaches for 3D shape analysis and processing.  ...  This report is closely related to the recent survey on "structure-aware shape processing" by Mitra and co-workers ], which concentrates on techniques for structural analysis of 3D shapes, as well as high-level  ...  Acknowledgements We thank Zimo Li for proofreading this survey and the anonymous reviewers for helpful suggestions. Kalogerakis gratefully acknowledges support from NSF (CHS-1422441).  ... 
doi:10.1145/2988458.2988473 dblp:conf/siggraph/0004KHMK16 fatcat:tefja76ijnclzmpux2iaj45zgu

Data-Driven Shape Analysis and Processing

Kai Xu, Vladimir G. Kim, Qixing Huang, Evangelos Kalogerakis
2016 Computer graphics forum (Print)  
In contrast to traditional approaches that process shapes in isolation of each other, data-driven methods aggregate information from 3D model collections to improve the analysis, modelling and editing  ...  of shapes.  ...  Acknowledgements We thank Zimo Li for proofreading this survey and the anonymous reviewers for helpful suggestions. Kalogerakis gratefully acknowledges support from NSF (CHS-1422441).  ... 
doi:10.1111/cgf.12790 fatcat:q76sq2syjvce5fjjjb7yoafww4

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  
Large-scale 3D shape retrieval has become an important research direction in content-based 3D shape retrieval.  ...  Twelve and six distinct 3D shape retrieval methods have competed with each other in these two contests, respectively.  ...  We would also like to thank the following authors for building the 3D benchmarks:  ... 
doi:10.1016/j.cviu.2014.10.006 fatcat:d3feizyi6rg63g5lra7mczvj2a
« Previous Showing results 1 — 15 out of 77 results