3DOR 10

Permanent URI for this collection

https://diglib7.eg.org/handle/10.2312/311

Robust Volumetric Shape Descriptor

[meta data] [files:
001-005.pdf
]
Rustamov, Raif M.

A Robust 3D Interest Points Detector Based on Harris Operator

[meta data] [files:
007-014.pdf
]
Sipiran, Ivan
; 
Bustos, Benjamin

Semantics-Driven Approach for Automatic Selection of Best Views of 3D Shapes

[meta data] [files:
015-022.pdf
]
Laga, Hamid

Learning the Compositional Structure of Man-Made Objects for 3D Shape Retrieval

[meta data] [files:
039-046.pdf
]
Wessel, Raoul
; 
Klein, Reinhard

Feature Selection for Enhanced Spectral Shape Comparison

[meta data] [files:
031-038.pdf
]
Marini, Simone
; 
Patané, Giuseppe
; 
Spagnuolo, Michela
; 
Falcidieno, Bianca

The Fast Reject Schema for Part-in-Whole 3D Shape Matching

[meta data] [files:
023-030.pdf
]
Attene, Marco
; 
Marini, Simone
; 
Spagnuolo, Michela
; 
Falcidieno, Bianca

SHREC'10 Track: Robust Shape Retrieval

[meta data] [files:
071-078.pdf
]
Bronstein, A. M.
; 
Bronstein, M. M.
; 
Patané, G.
; 
Spagnuolo, M.
; 
Toldo, R.
; 
Castellani, U.
; 
Falcidieno, B.
; 
Fusiello, A.
; 
Godil, A.
; 
Guibas, L. J.
; 
Kokkinos, I.
; 
Lian, Z.
; 
Ovsjanikov, M.

Fast Human Classification of 3D Object Benchmarks

[meta data] [files:
055-062.pdf ,
Figure 12.pdf ,
figure13.jpg ,
Figure 14.jpg ,
Figure 15.jpg
]
Jagadeesan, A. P.
; 
Wenzel, J.
; 
Corney, Jonathan R.
; 
Yan, X.
; 
Sherlock, A.
; 
Torres-Sanchez, C.
; 
Regli, William

Person Independent 3D Facial Expression Recognition by a Selected Ensemble of SIFT Descriptors

[meta data] [files:
047-054.pdf
]
Berretti, Stefano
; 
Amor, Boulbaba Ben
; 
Daoudi, Mohamed
; 
Bimbo, Alberto Del

SHREC'10 Track: Large Scale Retrieval

[meta data] [files:
063-069.pdf
]
Veltkamp, Remco C.
; 
Giezeman, Geert-Jan
; 
Bast, Hannah
; 
Baumbach, Thomas
; 
Furuya, Takahiko
; 
Giesen, Joachim
; 
Godil, Afzal
; 
Lian, Zhouhui
; 
Ohbuchi, Ryutarou
; 
Saleem, Waqar

SHREC'10 Track: Generic 3D Warehouse

[meta data] [files:
093-100.pdf
]
Vanamali, T. P.
; 
Godil, A.
; 
Dutagaci, H.
; 
Furuya, T.
; 
Lian, Z.
; 
Ohbuchi, R.

SHREC'10 Track: Correspondence Finding

[meta data] [files:
087-091.pdf
]
Bronstein, A. M.
; 
Bronstein, M. M.
; 
Ovsjanikov, M.
; 
Sharma, A.
; 
Castellani, U.
; 
Dubrovina, A.
; 
Guibas, L. J.
; 
Horaud, R. P.
; 
Kimmel, R.
; 
Knossow, D.
; 
Lavante, E. von
; 
Mateus, D.

SHREC'10 Track: Feature Detection and Description

[meta data] [files:
079-086.pdf
]
Bronstein, A. M.
; 
Bronstein, M. M.
; 
Patané, G.
; 
Sipiran, I.
; 
Spagnuolo, M.
; 
Sun, J.
; 
Bustos, B.
; 
Castellani, U.
; 
Crisani, M.
; 
Falcidieno, B.
; 
Guibas, L. J.
; 
Kokkinos, I.
; 
Murino, V.
; 
Ovsjanikov, M.

SHREC'10 Track: Protein Model Classification

[meta data] [files:
117-124.pdf
]
Mavridis, L.
; 
Venkatraman, V.
; 
Burkhardt, H.
; 
Axenopoulos, A.
; 
Daras, P.
; 
Ritchie, D. W.
; 
Morikawa, N.
; 
Andonov, R.
; 
Cornu, A.
; 
Malod-Dognin, N.
; 
Nicolas, J.
; 
Temerinac-Ott, M.
; 
Reisert, M.

SHREC'10 Track: Range Scan Retrieval

[meta data] [files:
109-115.pdf
]
Dutagaci, H.
; 
Godil, A.
; 
Cheung, C. P.
; 
Furuya, T.
; 
Hillenbrand, U.
; 
Ohbuchi, R.

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

[meta data] [files:
101-108.pdf
]
Lian, Z.
; 
Godil, A.
; 
Wuhrer, S.
; 
Fabry, T.
; 
Furuya, T.
; 
Hermans, J.
; 
Ohbuchi, R.
; 
Shu, C.
; 
Smeets, D.
; 
Suetens, P.
; 
Vandermeulen, D.

BibTeX (3DOR 10)
@inproceedings{
10.2312:3DOR/3DOR10/001-005,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
Robust Volumetric Shape Descriptor}},

author = {
Rustamov, Raif M.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/001-005}

}
@inproceedings{
10.2312:3DOR/3DOR10/007-014,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
A Robust 3D Interest Points Detector Based on Harris Operator}},

author = {
Sipiran, Ivan
 and 
Bustos, Benjamin
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/007-014}

}
@inproceedings{
10.2312:3DOR/3DOR10/015-022,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
Semantics-Driven Approach for Automatic Selection of Best Views of 3D Shapes}},

author = {
Laga, Hamid
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/015-022}

}
@inproceedings{
10.2312:3DOR/3DOR10/039-046,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
Learning the Compositional Structure of Man-Made Objects for 3D Shape Retrieval}},

author = {
Wessel, Raoul
 and 
Klein, Reinhard
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/039-046}

}
@inproceedings{
10.2312:3DOR/3DOR10/031-038,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
Feature Selection for Enhanced Spectral Shape Comparison}},

author = {
Marini, Simone
 and 
Patané, Giuseppe
 and 
Spagnuolo, Michela
 and 
Falcidieno, Bianca
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/031-038}

}
@inproceedings{
10.2312:3DOR/3DOR10/023-030,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
The Fast Reject Schema for Part-in-Whole 3D Shape Matching}},

author = {
Attene, Marco
 and 
Marini, Simone
 and 
Spagnuolo, Michela
 and 
Falcidieno, Bianca
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/023-030}

}
@inproceedings{
10.2312:3DOR/3DOR10/071-078,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Robust Shape Retrieval}},

author = {
Bronstein, A. M.
 and 
Bronstein, M. M.
 and 
Patané, G.
 and 
Spagnuolo, M.
 and 
Toldo, R.
 and 
Castellani, U.
 and 
Falcidieno, B.
 and 
Fusiello, A.
 and 
Godil, A.
 and 
Guibas, L. J.
 and 
Kokkinos, I.
 and 
Lian, Z.
 and 
Ovsjanikov, M.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/071-078}

}
@inproceedings{
10.2312:3DOR/3DOR10/055-062,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
Fast Human Classification of 3D Object Benchmarks}},

author = {
Jagadeesan, A. P.
 and 
Wenzel, J.
 and 
Corney, Jonathan R.
 and 
Yan, X.
 and 
Sherlock, A.
 and 
Torres-Sanchez, C.
 and 
Regli, William
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/055-062}

}
@inproceedings{
10.2312:3DOR/3DOR10/047-054,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
Person Independent 3D Facial Expression Recognition by a Selected Ensemble of SIFT Descriptors}},

author = {
Berretti, Stefano
 and 
Amor, Boulbaba Ben
 and 
Daoudi, Mohamed
 and 
Bimbo, Alberto Del
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/047-054}

}
@inproceedings{
10.2312:3DOR/3DOR10/063-069,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Large Scale Retrieval}},

author = {
Veltkamp, Remco C.
 and 
Giezeman, Geert-Jan
 and 
Bast, Hannah
 and 
Baumbach, Thomas
 and 
Furuya, Takahiko
 and 
Giesen, Joachim
 and 
Godil, Afzal
 and 
Lian, Zhouhui
 and 
Ohbuchi, Ryutarou
 and 
Saleem, Waqar
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/063-069}

}
@inproceedings{
10.2312:3DOR/3DOR10/093-100,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Generic 3D Warehouse}},

author = {
Vanamali, T. P.
 and 
Godil, A.
 and 
Dutagaci, H.
 and 
Furuya, T.
 and 
Lian, Z.
 and 
Ohbuchi, R.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/093-100}

}
@inproceedings{
10.2312:3DOR/3DOR10/087-091,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Correspondence Finding}},

author = {
Bronstein, A. M.
 and 
Bronstein, M. M.
 and 
Ovsjanikov, M.
 and 
Sharma, A.
 and 
Castellani, U.
 and 
Dubrovina, A.
 and 
Guibas, L. J.
 and 
Horaud, R. P.
 and 
Kimmel, R.
 and 
Knossow, D.
 and 
Lavante, E. von
 and 
Mateus, D.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/087-091}

}
@inproceedings{
10.2312:3DOR/3DOR10/079-086,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Feature Detection and Description}},

author = {
Bronstein, A. M.
 and 
Bronstein, M. M.
 and 
Patané, G.
 and 
Sipiran, I.
 and 
Spagnuolo, M.
 and 
Sun, J.
 and 
Bustos, B.
 and 
Castellani, U.
 and 
Crisani, M.
 and 
Falcidieno, B.
 and 
Guibas, L. J.
 and 
Kokkinos, I.
 and 
Murino, V.
 and 
Ovsjanikov, M.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/079-086}

}
@inproceedings{
10.2312:3DOR/3DOR10/117-124,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Protein Model Classification}},

author = {
Mavridis, L.
 and 
Venkatraman, V.
 and 
Burkhardt, H.
 and 
Axenopoulos, A.
 and 
Daras, P.
 and 
Ritchie, D. W.
 and 
Morikawa, N.
 and 
Andonov, R.
 and 
Cornu, A.
 and 
Malod-Dognin, N.
 and 
Nicolas, J.
 and 
Temerinac-Ott, M.
 and 
Reisert, M.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/117-124}

}
@inproceedings{
10.2312:3DOR/3DOR10/109-115,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Range Scan Retrieval}},

author = {
Dutagaci, H.
 and 
Godil, A.
 and 
Cheung, C. P.
 and 
Furuya, T.
 and 
Hillenbrand, U.
 and 
Ohbuchi, R.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/109-115}

}
@inproceedings{
10.2312:3DOR/3DOR10/101-108,

booktitle = {
Eurographics Workshop on 3D Object Retrieval},

editor = {
Mohamed Daoudi and Tobias Schreck
},
title = {{
SHREC'10 Track: Non-rigid 3D Shape Retrieval}},

author = {
Lian, Z.
 and 
Godil, A.
 and 
Wuhrer, S.
 and 
Fabry, T.
 and 
Furuya, T.
 and 
Hermans, J.
 and 
Ohbuchi, R.
 and 
Shu, C.
 and 
Smeets, D.
 and 
Suetens, P.
 and 
Vandermeulen, D.
},
year = {
2010},

publisher = {
The Eurographics Association},


ISSN = {1997-0471},
ISBN = {978-3-905674-22-4},

DOI = {
10.2312/3DOR/3DOR10/101-108}

}

Browse

Recent Submissions

Now showing 1 - 16 of 16
  • Thumbnail Image
    Item
    Robust Volumetric Shape Descriptor
    (The Eurographics Association, 2010) Rustamov, Raif M.; Mohamed Daoudi and Tobias Schreck
    This paper introduces a volume-based shape descriptor that is robust with respect to changes in pose and topology. We use modified shape distributions of [OFCD02] in conjunction with the interior distances and barycentroid potential that are based on barycentric coordinates [RLF09]. In our approach, shape distributions are aggregated throughout the entire volume contained within the shape thus capturing information conveyed by the volumes of shapes. Since interior distances and barycentroid potential are practically insensitive to various poses/deformations and to non-pervasive topological changes (addition of small handles), our shape descriptor inherits such insensitivity as well. In addition, if any other modes of information (e.g. electrostatic potential within the protein volume) are available, they can be easily incorporated into the descriptor as additional dimensions in the histograms. Our descriptor has a connection to an existing surface based shape descriptor, the Global Point Signatures (GPS) [Rus07]. We use this connection to fairly examine the value of volumetric information for shape retrieval.We find that while, theoretically, strict isometry invariance requires concentrating on the intrinsic surface properties alone, yet, practically, pose insensitive shape retrieval still can be achieved/enhanced using volumetric information.
  • Thumbnail Image
    Item
    A Robust 3D Interest Points Detector Based on Harris Operator
    (The Eurographics Association, 2010) Sipiran, Ivan; Bustos, Benjamin; Mohamed Daoudi and Tobias Schreck
    With the increasing amount of 3D data and the ability of capture devices to produce low-cost multimedia data, the capability to select relevant information has become an interesting research field. In 3D objects, the aim is to detect a few salient structures which can be used, instead of the whole object, for applications like object registration, retrieval, and mesh simplification. In this paper, we present an interest points detector for 3D objects based on Harris operator, which has been used with good results in computer vision applications. We propose an adaptive technique to determine the neighborhood of a vertex, over which the Harris response on that vertex is calculated. Our method is robust to affine transformations(partially for object rotation) and distortion transformation such as noise addition. Moreover, the distribution of interest points on the surface of an object remains similar in transformed objects, which is a desirable behavior in applications such as shape matching and object registration.
  • Thumbnail Image
    Item
    Semantics-Driven Approach for Automatic Selection of Best Views of 3D Shapes
    (The Eurographics Association, 2010) Laga, Hamid; Mohamed Daoudi and Tobias Schreck
    We introduce a new framework for the automatic selection of the best views of 3D models. The approach is based on the assumption that models belonging to the same class of shapes share the same salient features that discriminate them from the models of other classes. The main issue is learning these features. We propose a datadriven approach where the best view selection problem is formulated as a classification and feature selection problem; First a 3D model is described with a set of view-based descriptors, each one computed from a different viewpoint. Then a classifier is trained, in a supervised manner, on a collection of 3D models belonging to several shape categories. The classifier learns the set of 2D views that maximize the similarity between shapes of the same class and also the views that discriminate shapes of different classes. Our experiments using the LightField (LFD) descriptors and the Princeton Shape Benchmark demonstrate the performance of the approach and its suitability for classification and online visual browsing of 3D data collections.
  • Thumbnail Image
    Item
    Learning the Compositional Structure of Man-Made Objects for 3D Shape Retrieval
    (The Eurographics Association, 2010) Wessel, Raoul; Klein, Reinhard; Mohamed Daoudi and Tobias Schreck
    While approaches based on local features play a more and more important role for 3D shape retrieval, the problems of feature selection and similarity measurement between sets of local features still remain open tasks. Common algorithms usually measure the similarity between two such sets by either establishing feature correspondences or by using Bag-of-Features (BoF) approaches. While establishing correspondences often involves a lot of manually chosen thresholds, BoF approaches can hardly model the spatial structure of the underlying 3D object. In this paper focusing on retrieval of 3D models representing man-made objects, we try to tackle both of these problems. Exploiting the fact that man-made objects usually consist of a small set of certain shape primitives, we propose a feature selection technique that decomposes 3D point clouds into sections that can be represented by a plane, a sphere, a cylinder, a cone, or a torus. We then introduce a probabilistic framework for analyzing and learning the spatial arrangement of the detected shape primitives with respect to training objects belonging to certain categories. The knowledge acquired in this learning process allows for efficient retrieval and classification of new 3D objects. We finally evaluate our algorithm on the recently introduced 3D Architecture Shape Benchmark, which mainly consists of 3D models representing man-made objects.
  • Thumbnail Image
    Item
    Feature Selection for Enhanced Spectral Shape Comparison
    (The Eurographics Association, 2010) Marini, Simone; Patané, Giuseppe; Spagnuolo, Michela; Falcidieno, Bianca; Mohamed Daoudi and Tobias Schreck
    In the context of shape matching, this paper proposes a framework for selecting the Laplacian eigenvalues of 3D shapes that are more relevant for shape comparison and classification. Three approaches are compared to identify a specific set of eigenvalues such that they maximise the retrieval and/or the classification performance on the input benchmark data set: the first k eigenvalues, by varying k over the cardinality of the spectrum; the Hill Climbing technique; and the AdaBoost algorithm. In this way, we demonstrate that the information coded by the whole spectrum is unnecessary and we improve the shape matching results using only a set of selected eigenvalues. Finally, we test the efficacy of the selected eigenvalues by coupling shape classification and retrieval.
  • Thumbnail Image
    Item
    The Fast Reject Schema for Part-in-Whole 3D Shape Matching
    (The Eurographics Association, 2010) Attene, Marco; Marini, Simone; Spagnuolo, Michela; Falcidieno, Bianca; Mohamed Daoudi and Tobias Schreck
    This paper proposes a new framework for an efficient detection of template shapes within a target 3D model, or scene. The proposed approach distinguishes from the previous literature because the part-in-whole matching between the template and the target is obtained by extracting off-line only the shape descriptor of the template, while the description of the target is dynamically and adaptively extracted during the matching process. This novel framework, called the Fast Reject schema, exploits the incremental nature of a class of local shape descriptors to significantly reduce the part-in-whole matching time, without any expensive processing of the models for the extraction of the shape descriptors. The schema have been tested on three different descriptors and results are discussed in details. Experiments show that the gain in computational performances does not compromise the accuracy of the matching results.
  • Thumbnail Image
    Item
    SHREC'10 Track: Robust Shape Retrieval
    (The Eurographics Association, 2010) Bronstein, A. M.; Bronstein, M. M.; Castellani, U.; Falcidieno, B.; Fusiello, A.; Godil, A.; Guibas, L. J.; Kokkinos, I.; Lian, Z.; Ovsjanikov, M.; Patané, G.; Spagnuolo, M.; Toldo, R.; Mohamed Daoudi and Tobias Schreck
    The 3D Shape Retrieval Contest 2010 (SHREC'10) robust shape retrieval benchmark simulates a retrieval scenario, in which the queries include multiple modifications and transformations of the same shape. The benchmark allows evaluating how algorithms cope with certain classes of transformations and what is the strength of the transformations that can be dealt with. The present paper is a report of the SHREC'10 robust shape retrieval benchmark results.
  • Thumbnail Image
    Item
    Fast Human Classification of 3D Object Benchmarks
    (The Eurographics Association, 2010) Jagadeesan, A. P.; Wenzel, J.; Corney, Jonathan R.; Yan, X.; Sherlock, A.; Torres-Sanchez, C.; Regli, William; Mohamed Daoudi and Tobias Schreck
    Although a significant number of benchmark data sets for 3D object based retrieval systems have been proposed over the last decade their value is dependent on a robust classification of their content being available. Ideally researchers would want hundreds of people to have classified thousands of parts and the results recorded in a manner that explicitly shows how the similarity assessments varies with the precision used to make the judgement. This paper reports a study which investigated the proposition that Internet Crowdsourcing could be used to quickly and cheaply provide benchmark classifications of 3D shapes. The collective judgments of the anonymous workers produce a classification that has surprisingly fine granularity and precision. The paper reports the results of validating Crowdsourced judgements of 3D similarity against Purdue's ESB and concludes with an estimate of the overall costs associated with large scale classification tasks involving many tens of thousands of models.
  • Thumbnail Image
    Item
    Person Independent 3D Facial Expression Recognition by a Selected Ensemble of SIFT Descriptors
    (The Eurographics Association, 2010) Berretti, Stefano; Amor, Boulbaba Ben; Daoudi, Mohamed; Bimbo, Alberto Del; Mohamed Daoudi and Tobias Schreck
    Facial expression recognition has been addressed mainly working on 2D images or videos. In this paper, the problem of person-independent facial expression recognition is addressed on 3D shapes. To this end, an original approach is proposed that relies on selecting the minimal-redundancy maximal-relevance features derived from a pool of SIFT feature descriptors computed in correspondence with facial landmarks of depth images. Training a Support Vector Machine for every basic facial expression to be recognized, and combining them to form a multiclass classifier, an average recognition rate of 77.5% on the BU-3DFE database has been obtained. Comparison with competitors approaches using a common experimental setting on the BU-3DFE database, shows that our solution is able to obtain state of the art results.
  • Thumbnail Image
    Item
    SHREC'10 Track: Large Scale Retrieval
    (The Eurographics Association, 2010) Veltkamp, Remco C.; Giezeman, Geert-Jan; Bast, Hannah; Baumbach, Thomas; Furuya, Takahiko; Giesen, Joachim; Godil, Afzal; Lian, Zhouhui; Ohbuchi, Ryutarou; Saleem, Waqar; Mohamed Daoudi and Tobias Schreck
    This paper is a report on the 3D Shape Retrieval Constest 2010 (SHREC'10) track on large scale retrieval. This benchmark allows evaluating how wel retrieval algorithms scale up to large collections of 3D models. The task was to perform 40 queries in a dataset of 10000 shapes. We describe the methods used and discuss the results and signifiance analysis.
  • Thumbnail Image
    Item
    SHREC'10 Track: Generic 3D Warehouse
    (The Eurographics Association, 2010) Vanamali, T. P.; Godil, A.; Dutagaci, H.; Furuya, T.; Lian, Z.; Ohbuchi, R.; Mohamed Daoudi and Tobias Schreck
    In this paper we present the results of the 3D Shape Retrieval Contest 2010 (SHREC'10) track Generic 3D Warehouse. The aim of this track was to evaluate the performances of various 3D shape retrieval algorithms on a large Generic benchmark based on the Google 3D Warehouse. We hope that the benchmark developed at NIST will provide valuable contributions to the 3D shape retrieval community. Three groups have participated in the track and they have submitted 7 set of results based on different methods and parameters. We also ran two standard algorithms on the track dataset. The performance evaluation of this track is based on six different metrics.
  • Thumbnail Image
    Item
    SHREC'10 Track: Correspondence Finding
    (The Eurographics Association, 2010) Bronstein, A. M.; Bronstein, M. M.; Castellani, U.; Dubrovina, A.; Guibas, L. J.; Horaud, R. P.; Kimmel, R.; Knossow, D.; Lavante, E. von; Mateus, D.; Ovsjanikov, M.; Sharma, A.; Mohamed Daoudi and Tobias Schreck
    The SHREC'10 correspondence finding benchmark simulates a one-to-one shape matching scenario, in which one of the shapes undergoes multiple modifications and transformations. The benchmark allows evaluating how correspondence algorithms cope with certain classes of transformations and what is the strength of the transformations that can be dealt with. The present paper is a report of the 3D Shape Retrieval Contest 2010 (SHREC'10) correspondence finding benchmark results.
  • Thumbnail Image
    Item
    SHREC'10 Track: Feature Detection and Description
    (The Eurographics Association, 2010) Bronstein, A. M.; Bronstein, M. M.; Bustos, B.; Castellani, U.; Crisani, M.; Falcidieno, B.; Guibas, L. J.; Kokkinos, I.; Murino, V.; Ovsjanikov, M.; Patané, G.; Sipiran, I.; Spagnuolo, M.; Sun, J.; Mohamed Daoudi and Tobias Schreck
    Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. The SHREC'10 feature detection and description benchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms. The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations. The benchmark allows evaluating how algorithms cope with certain classes of transformations and strength of the transformations that can be dealt with. The present paper is a report of the 3D Shape Retrieval Contest 2010 (SHREC'10) feature detection and description benchmark results.
  • Thumbnail Image
    Item
    SHREC'10 Track: Protein Model Classification
    (The Eurographics Association, 2010) Mavridis, L.; Venkatraman, V.; Ritchie, D. W.; Morikawa, N.; Andonov, R.; Cornu, A.; Malod-Dognin, N.; Nicolas, J.; Temerinac-Ott, M.; Reisert, M.; Burkhardt, H.; Axenopoulos, A.; Daras, P.; Mohamed Daoudi and Tobias Schreck
    This paper presents the results of the 3D Shape Retrieval Contest 2010 (SHREC'10) track Protein Models Classification. The aim of this track is to evaluate how well 3D shape recognition algorithms can classify protein structures according to the CATH [CSL?08] superfamily classification. Five groups participated in this track, using a total of six methods, and for each method a set of ranked predictions was submitted for each classification task. The evaluation of each method is based on the nearest neighbour and area under the curve(AUC) metrics.
  • Thumbnail Image
    Item
    SHREC'10 Track: Range Scan Retrieval
    (The Eurographics Association, 2010) Dutagaci, H.; Godil, A.; Cheung, C. P.; Furuya, T.; Hillenbrand, U.; Ohbuchi, R.; Mohamed Daoudi and Tobias Schreck
    The 3D Shape Retrieval Contest 2010 (SHREC'10) on range scan retrieval aims at comparing algorithms that match a range scan to complete 3D models in a target database. The queries are range scans of real objects, and the objective is to retrieve complete 3D models that are of the same class. This problem is essential to current and future vision systems that perform shape based matching and classification of the objects in the environment. Two groups have participated in the contest. They have provided rank lists for the query set, which is composed of 120 range scans of 40 objects.
  • Thumbnail Image
    Item
    SHREC'10 Track: Non-rigid 3D Shape Retrieval
    (The Eurographics Association, 2010) Lian, Z.; Godil, A.; Fabry, T.; Furuya, T.; Hermans, J.; Ohbuchi, R.; Shu, C.; Smeets, D.; Suetens, P.; Vandermeulen, D.; Wuhrer, S.; Mohamed Daoudi and Tobias Schreck
    Non-rigid shape matching is one of the most challenging fields in content-based 3D object retrieval. 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. Three groups with six methods have participated in this track and the retrieval performance was evaluated using six commonly-used metrics.