Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks

In this paper, we propose a generalization of convolutional neural networks (CNN) to non‐Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform to manifolds) that is used to extract the lo...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 34; no. 5; pp. 13 - 23
Main Authors: Boscaini, D., Masci, J., Melzi, S., Bronstein, M. M., Castellani, U., Vandergheynst, P.
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.08.2015
Subjects:
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this paper, we propose a generalization of convolutional neural networks (CNN) to non‐Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform to manifolds) that is used to extract the local behavior of some dense intrinsic descriptor, roughly acting as an analogy to patches in images. The resulting local frequency representations are then passed through a bank of filters whose coefficient are determined by a learning procedure minimizing a task‐specific cost. Our approach generalizes several previous methods such as HKS, WKS, spectral CNN, and GPS embeddings. Experimental results show that the proposed approach allows learning class‐specific shape descriptors significantly outperforming recent state‐of‐the‐art methods on standard benchmarks.
AbstractList In this paper, we propose a generalization of convolutional neural networks (CNN) to non‐Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform to manifolds) that is used to extract the local behavior of some dense intrinsic descriptor, roughly acting as an analogy to patches in images. The resulting local frequency representations are then passed through a bank of filters whose coefficient are determined by a learning procedure minimizing a task‐specific cost. Our approach generalizes several previous methods such as HKS, WKS, spectral CNN, and GPS embeddings. Experimental results show that the proposed approach allows learning class‐specific shape descriptors significantly outperforming recent state‐of‐the‐art methods on standard benchmarks.
Author Bronstein, M. M.
Vandergheynst, P.
Boscaini, D.
Masci, J.
Melzi, S.
Castellani, U.
Author_xml – sequence: 1
  givenname: D.
  surname: Boscaini
  fullname: Boscaini, D.
  organization: Institute of Computational Science, Faculty of Informatics, University of Lugano (USI), Switzerland
– sequence: 2
  givenname: J.
  surname: Masci
  fullname: Masci, J.
  organization: Institute of Computational Science, Faculty of Informatics, University of Lugano (USI), Switzerland
– sequence: 3
  givenname: S.
  surname: Melzi
  fullname: Melzi, S.
  organization: Department of Informatics, University of Verona, Italy
– sequence: 4
  givenname: M. M.
  surname: Bronstein
  fullname: Bronstein, M. M.
  organization: Institute of Computational Science, Faculty of Informatics, University of Lugano (USI), Switzerland
– sequence: 5
  givenname: U.
  surname: Castellani
  fullname: Castellani, U.
  organization: Department of Informatics, University of Verona, Italy
– sequence: 6
  givenname: P.
  surname: Vandergheynst
  fullname: Vandergheynst, P.
  organization: Department of Electrical Engineering, EPFL, Lausanne, Switzerland
BookMark eNp1kE1v1DAQhi1UJLYLB_5BJC5wSGuvYzs5oohdPlYgQRFHy5nYxa03Dp6EUn49Dls4VOCD7ZGeZzTznpKTIQ6WkKeMnrF8zuHSnbGNbPgDsmKVVGUtRXNCVpTlv6JCPCKniFeU0kpJsSJ-b00a_HBZQDCIJY4WvPNQ9BYh-XGKCQsXU67zfTBdsAV-NaPFYsZFCxFM8D9tXyzqlEwoIA7fY5gnH4dcDXa6iekaH5OHzgS0T-7eNfm8fXXRvi73H3Zv2pf7EgRveGlUZ9nG5VFNY5hlBlgFler6DvqKcaqc6GrWdapxQGsLjZCypgCVdLUQpudr8vzYd0zx22xx0gePYEMwg40zaqZUTSsuckZr8uweehXnlIdeKLqRUqlKZOr8SEGKiMk6DX4yy3Z5Wx80o3qJXufo9e_os_HinjEmfzDp9p_sXfcbH-zt_0Hd7rZ_jPJoeJzsj7-GSddaKq6E_vJ-py9a_nHbvnurP_FflYmmng
CitedBy_id crossref_primary_10_1111_cgf_14094
crossref_primary_10_1145_3476576_3476751
crossref_primary_10_1111_cgf_14371
crossref_primary_10_1145_3144454
crossref_primary_10_1109_ACCESS_2020_2973190
crossref_primary_10_1109_TGRS_2023_3266273
crossref_primary_10_1109_TVCG_2024_3368083
crossref_primary_10_1007_s11263_020_01359_2
crossref_primary_10_1111_cgf_14012
crossref_primary_10_1016_j_aei_2024_102439
crossref_primary_10_1111_cgf_12866
crossref_primary_10_1007_s11548_019_02013_0
crossref_primary_10_1007_s00371_023_02935_6
crossref_primary_10_1109_MSP_2017_2693418
crossref_primary_10_1016_j_cag_2023_04_010
crossref_primary_10_1016_j_cagd_2024_102304
crossref_primary_10_1007_s00170_023_10834_2
crossref_primary_10_1109_TIP_2021_3116786
crossref_primary_10_1109_TMM_2019_2918729
crossref_primary_10_1109_TIP_2016_2605920
crossref_primary_10_1016_j_cag_2019_05_010
crossref_primary_10_1016_j_patcog_2019_06_012
crossref_primary_10_1145_3272127_3275050
crossref_primary_10_1007_s00521_021_06006_6
crossref_primary_10_1145_3072959_3073608
crossref_primary_10_1109_ACCESS_2021_3060173
crossref_primary_10_1109_JPROC_2018_2820126
crossref_primary_10_1109_TIP_2018_2868426
crossref_primary_10_1111_cgf_13496
crossref_primary_10_1111_cgf_12734
crossref_primary_10_1017_ATSIP_2016_13
crossref_primary_10_1007_s41095_020_0163_y
crossref_primary_10_1111_cgf_14502
crossref_primary_10_1016_j_cagd_2017_03_004
crossref_primary_10_1111_cgf_13536
crossref_primary_10_1109_TVCG_2020_2968062
crossref_primary_10_1007_s11263_019_01278_x
crossref_primary_10_1145_3450626_3459797
crossref_primary_10_1007_s11263_023_01750_9
crossref_primary_10_3390_app10041342
crossref_primary_10_1007_s10915_025_02856_7
crossref_primary_10_1109_TVCG_2018_2848628
crossref_primary_10_1016_j_jsg_2021_104302
crossref_primary_10_1145_3495208
crossref_primary_10_1016_j_cagd_2020_101901
crossref_primary_10_1111_cgf_12844
crossref_primary_10_1007_s41095_020_0174_8
crossref_primary_10_1109_TMM_2019_2952983
crossref_primary_10_1111_cgf_13309
crossref_primary_10_1109_TSP_2018_2879624
crossref_primary_10_1109_TVCG_2020_2994013
crossref_primary_10_1109_LRA_2018_2850061
crossref_primary_10_1109_TITS_2020_3023541
crossref_primary_10_1145_3386569_3392443
crossref_primary_10_1109_ACCESS_2020_2975067
crossref_primary_10_1109_JSTSP_2017_2726981
crossref_primary_10_3390_a12080171
crossref_primary_10_1007_s11042_022_12683_9
crossref_primary_10_1109_ACCESS_2020_2982196
crossref_primary_10_1109_TVCG_2018_2887262
crossref_primary_10_1109_TPAMI_2016_2596722
crossref_primary_10_1007_s11042_018_6052_z
crossref_primary_10_1016_j_patcog_2019_04_004
crossref_primary_10_1016_j_imavis_2023_104768
crossref_primary_10_1007_s13042_021_01328_2
crossref_primary_10_1111_cgf_14120
crossref_primary_10_1109_TCSVT_2020_2984241
crossref_primary_10_3390_math12182946
crossref_primary_10_1016_j_neucom_2020_12_097
crossref_primary_10_1007_s00371_023_03254_6
crossref_primary_10_1109_TVCG_2019_2896310
crossref_primary_10_1109_ACCESS_2019_2950279
crossref_primary_10_1016_j_jmgm_2021_108103
crossref_primary_10_1007_s40304_021_00246_7
crossref_primary_10_1016_j_cag_2025_104320
crossref_primary_10_3390_s19122809
crossref_primary_10_1109_ACCESS_2019_2955487
crossref_primary_10_1007_s10915_023_02274_7
crossref_primary_10_1111_cgf_12790
crossref_primary_10_1016_j_asoc_2022_109500
crossref_primary_10_1109_TIP_2019_2904460
crossref_primary_10_1109_TVCG_2023_3259044
crossref_primary_10_1016_j_cagd_2018_03_002
crossref_primary_10_1016_j_gmod_2021_101121
Cites_doi 10.1109/CVPR.2014.532
10.1109/TPAMI.2013.148
10.1109/34.765655
10.1109/ICCVW.2011.6130444
10.1109/TPAMI.2006.208
10.1145/571647.571648
10.1007/s00371-011-0610-y
10.1016/j.cad.2005.10.011
10.1145/1073204.1073207
10.1111/j.1467-8659.2009.01517.x
10.1111/cgf.12438
10.1007/978-3-540-39966-7_36
10.1007/BF01896401
10.1111/1467-8659.00675
10.1109/CVPR.2008.4587538
10.1109/CVPR.2014.491
10.1007/978-3-662-05105-4_2
10.1162/neco.1989.1.4.541
10.1111/cgf.12429
10.1109/CVPR.2012.6247671
10.1111/j.1467-8659.2010.01764.x
10.1016/j.acha.2006.04.006
10.1016/j.patcog.2012.07.014
10.1145/2508363.2508364
10.1109/TPAMI.2003.1233902
10.1023/B:VISI.0000029664.99615.94
10.1111/j.1467-8659.2009.01515.x
10.25080/Majora-92bf1922-003
10.1145/2010324.1964974
10.1080/10586458.1993.10504266
ContentType Journal Article
Copyright 2015 The Author(s) Computer Graphics Forum © 2015 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
2015 The Eurographics Association and John Wiley & Sons Ltd.
Copyright_xml – notice: 2015 The Author(s) Computer Graphics Forum © 2015 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
– notice: 2015 The Eurographics Association and John Wiley & Sons Ltd.
DBID BSCLL
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
F28
FR3
DOI 10.1111/cgf.12693
DatabaseName Istex
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
Engineering Research Database
ANTE: Abstracts in New Technology & Engineering
DatabaseTitleList
Computer and Information Systems Abstracts
Technology Research Database
CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1467-8659
EndPage 23
ExternalDocumentID 3772907451
10_1111_cgf_12693
CGF12693
ark_67375_WNG_TC3RFCKJ_S
Genre article
Feature
GroupedDBID .3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
15B
1OB
1OC
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8VB
930
A03
AAESR
AAEVG
AAHQN
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABDPE
ABEML
ABPVW
ACAHQ
ACBWZ
ACCZN
ACFBH
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AEIMD
AEMOZ
AENEX
AEUYR
AEYWJ
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AHEFC
AHQJS
AIDQK
AIDYY
AIQQE
AITYG
AIURR
AJXKR
AKVCP
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BSCLL
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EAD
EAP
EBA
EBO
EBR
EBS
EBU
EDO
EJD
EMK
EST
ESX
F00
F01
F04
F5P
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K1G
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QWB
R.K
RDJ
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
TH9
TN5
TUS
UB1
V8K
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WXSBR
WYISQ
WZISG
XG1
ZL0
ZZTAW
~IA
~IF
~WT
ALUQN
AAYXX
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
F28
FR3
ID FETCH-LOGICAL-c5393-a7be12f705a9a1e1ac14c47bdbcd41307f5b81bb79fc08ec956680cc46f855ad3
IEDL.DBID DRFUL
ISICitedReferencesCount 151
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000362293300003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-7055
IngestDate Thu Oct 02 11:35:56 EDT 2025
Fri Jul 25 23:47:11 EDT 2025
Tue Nov 18 22:36:11 EST 2025
Sat Nov 29 03:41:12 EST 2025
Sun Sep 21 06:26:22 EDT 2025
Tue Nov 11 03:32:33 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c5393-a7be12f705a9a1e1ac14c47bdbcd41307f5b81bb79fc08ec956680cc46f855ad3
Notes istex:A9D816B10CB68EF9EA6AD9D2E557CB4334DA3231
ark:/67375/WNG-TC3RFCKJ-S
ArticleID:CGF12693
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
OpenAccessLink http://infoscience.epfl.ch/record/213888
PQID 1702667745
PQPubID 30877
PageCount 11
ParticipantIDs proquest_miscellaneous_1778043569
proquest_journals_1702667745
crossref_citationtrail_10_1111_cgf_12693
crossref_primary_10_1111_cgf_12693
wiley_primary_10_1111_cgf_12693_CGF12693
istex_primary_ark_67375_WNG_TC3RFCKJ_S
PublicationCentury 2000
PublicationDate August 2015
PublicationDateYYYYMMDD 2015-08-01
PublicationDate_xml – month: 08
  year: 2015
  text: August 2015
PublicationDecade 2010
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Computer graphics forum
PublicationTitleAlternate Computer Graphics Forum
PublicationYear 2015
Publisher Blackwell Publishing Ltd
Publisher_xml – name: Blackwell Publishing Ltd
References Anguelov D., et al.: SCAPE: Shape completion and animation of people. TOG 24, 3 (2005), 408-416. 7
Bérard P., Besson G., Gallot S.: Embedding riemannian manifolds by their heat kernel. Geometric & Functional Analysis 4, 4 (1994), 373-398. 1, 3
Johnson A.E., Hebert M.: Using spin images for efficient object recognition in cluttered 3D scenes. PAMI 21, 5 (1999), 433-449. 1
Lowe D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 2 (2004), 91-110. 1
Pauly M., Keiser R., Gross M.: Multi-scale feature extraction on point-sampled surfaces. CGF 22, 3 (2003), 281-289. 1
LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation 1, 4 (1989), 541-551. 2, 5
Lian Z., et al.: A comparison of methods for non-rigid 3D shape retrieval. Pattern Recognition 46, 1 (2013), 449-461. 1
Osada R., Funkhouser T., Chazelle B., Dobkin D.: Shape distributions. TOG 21, 4 (2002), 807-832. 1
Litman R., Bronstein A.M.: Learning spectral descriptors for deformable shape correspondence. PAMI 36, 1 (2014), 170-180. 2, 3, 6, 7, 8
Sun J., Ovsjanikov M., Guibas L.J.: A concise and provably informative multi-scale signature based on heat diffusion. CGF 28, 5 (2009), 1383-1392. 1, 3, 7
Gebal K., Bærentzen J. A., Anæs H., Larsen R.: Shape analysis using the auto diffusion function. CGF 28, 5 (2009), 1405-1413. 1, 3
Pinkall U., Polthier K.: Computing discrete minimal surfaces and their conjugates. Experimental Mathematics 2, 1 (1993), 15-36. 5
Kalogerakis E., Hertzmann A., Singh K.: Learning 3D mesh segmentation and labeling. TOG 29, 3 (2010). 1
Sipiran I., Bustos B.: Harris 3D: a robust extension of the harris operator for interest point detection on 3D meshes. Visual Computer 27, 11 (2011), 963-976. 1
Elad A., Kimmel R.: On bending invariant signatures for surfaces. PAMI 25, 10 (2003), 1285-1295. 1
Manay S., Cremers D., Hong B.-W., Yezzi A.J., Soatto S.: Integral invariants for shape matching. PAMI 28, 10 (2006), 1602-1618. 1
Neumann T., Varanasi K., Theobalt C., Magnor M., Wacker M.: Compressed manifold modes for mesh processing. In Computer Graphics Forum (2014), vol. 33, pp. 35-44. 4
Reuter M., Wolter F.-E., Peinecke N.: Laplace-beltrami spectra as 'shape-dna' of surfaces and solids. Computer-Aided Design 38, 4 (2006), 342-366. 1
Coifman R.R., Lafon S.: Diffusion maps. Applied and Computational Harmonic Analysis 21, 1 (2006), 5-30. 1, 3, 4
Litman R., Bronstein A., Bronstein M., Castellani U.: Supervised learning of bag-of-features shape descriptors using sparse coding. CGF 33, 5 (2014), 127-136. 1, 2
Ovsjanikov M., Mérigot Q., Mémoli F., Guibas L.: One point isometric matching with the heat kernel. Computer Graphics Forum 29, 5 (2010), 1555-1564. 1
Kim V.G., Lipman Y., Funkhouser T.: Blended intrinsic maps. TOG 30, 4 (2011), 1-12. 8
Wu Z., Song S., Khosla A., Yu F., Zhang L., Tang X., Xiao J.: 3d shapenets: A deep representation for volumetric shape modeling. In Proc. CVPR (2015), vol. 1, p. 3. 2
2015; 1
1989; 1
2004; 60
2012
2011
2010
2013; 46
2006; 38
2008
2011; 30
2007
1999; 21
2006
2003
1993; 2
2005; 24
2009; 28
2000
2006; 21
2010; 29
2006; 28
2002; 21
2003; 25
2014; 36
2015
2014
2013
2011; 27
1994; 4
2014; 33
2003; 22
e_1_2_9_30_2
e_1_2_9_10_2
e_1_2_9_33_2
e_1_2_9_34_2
e_1_2_9_12_2
e_1_2_9_31_2
e_1_2_9_11_2
e_1_2_9_32_2
Kalogerakis E. (e_1_2_9_18_2) 2010; 29
e_1_2_9_14_2
e_1_2_9_37_2
e_1_2_9_13_2
e_1_2_9_38_2
e_1_2_9_16_2
e_1_2_9_35_2
e_1_2_9_15_2
e_1_2_9_36_2
e_1_2_9_17_2
e_1_2_9_39_2
e_1_2_9_19_2
Wu Z. (e_1_2_9_41_2) 2015; 1
e_1_2_9_40_2
e_1_2_9_21_2
e_1_2_9_20_2
e_1_2_9_23_2
e_1_2_9_42_2
e_1_2_9_22_2
e_1_2_9_7_2
e_1_2_9_6_2
e_1_2_9_5_2
e_1_2_9_4_2
e_1_2_9_3_2
e_1_2_9_2_2
e_1_2_9_9_2
e_1_2_9_8_2
e_1_2_9_25_2
e_1_2_9_24_2
e_1_2_9_27_2
e_1_2_9_26_2
e_1_2_9_29_2
e_1_2_9_28_2
References_xml – reference: Elad A., Kimmel R.: On bending invariant signatures for surfaces. PAMI 25, 10 (2003), 1285-1295. 1
– reference: Coifman R.R., Lafon S.: Diffusion maps. Applied and Computational Harmonic Analysis 21, 1 (2006), 5-30. 1, 3, 4
– reference: Lian Z., et al.: A comparison of methods for non-rigid 3D shape retrieval. Pattern Recognition 46, 1 (2013), 449-461. 1
– reference: Reuter M., Wolter F.-E., Peinecke N.: Laplace-beltrami spectra as 'shape-dna' of surfaces and solids. Computer-Aided Design 38, 4 (2006), 342-366. 1
– reference: Litman R., Bronstein A., Bronstein M., Castellani U.: Supervised learning of bag-of-features shape descriptors using sparse coding. CGF 33, 5 (2014), 127-136. 1, 2
– reference: Sun J., Ovsjanikov M., Guibas L.J.: A concise and provably informative multi-scale signature based on heat diffusion. CGF 28, 5 (2009), 1383-1392. 1, 3, 7
– reference: Kim V.G., Lipman Y., Funkhouser T.: Blended intrinsic maps. TOG 30, 4 (2011), 1-12. 8
– reference: Osada R., Funkhouser T., Chazelle B., Dobkin D.: Shape distributions. TOG 21, 4 (2002), 807-832. 1
– reference: Anguelov D., et al.: SCAPE: Shape completion and animation of people. TOG 24, 3 (2005), 408-416. 7
– reference: Sipiran I., Bustos B.: Harris 3D: a robust extension of the harris operator for interest point detection on 3D meshes. Visual Computer 27, 11 (2011), 963-976. 1
– reference: Neumann T., Varanasi K., Theobalt C., Magnor M., Wacker M.: Compressed manifold modes for mesh processing. In Computer Graphics Forum (2014), vol. 33, pp. 35-44. 4
– reference: Lowe D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 2 (2004), 91-110. 1
– reference: Kalogerakis E., Hertzmann A., Singh K.: Learning 3D mesh segmentation and labeling. TOG 29, 3 (2010). 1
– reference: Pauly M., Keiser R., Gross M.: Multi-scale feature extraction on point-sampled surfaces. CGF 22, 3 (2003), 281-289. 1
– reference: Litman R., Bronstein A.M.: Learning spectral descriptors for deformable shape correspondence. PAMI 36, 1 (2014), 170-180. 2, 3, 6, 7, 8
– reference: LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation 1, 4 (1989), 541-551. 2, 5
– reference: Gebal K., Bærentzen J. A., Anæs H., Larsen R.: Shape analysis using the auto diffusion function. CGF 28, 5 (2009), 1405-1413. 1, 3
– reference: Ovsjanikov M., Mérigot Q., Mémoli F., Guibas L.: One point isometric matching with the heat kernel. Computer Graphics Forum 29, 5 (2010), 1555-1564. 1
– reference: Bérard P., Besson G., Gallot S.: Embedding riemannian manifolds by their heat kernel. Geometric & Functional Analysis 4, 4 (1994), 373-398. 1, 3
– reference: Wu Z., Song S., Khosla A., Yu F., Zhang L., Tang X., Xiao J.: 3d shapenets: A deep representation for volumetric shape modeling. In Proc. CVPR (2015), vol. 1, p. 3. 2
– reference: Pinkall U., Polthier K.: Computing discrete minimal surfaces and their conjugates. Experimental Mathematics 2, 1 (1993), 15-36. 5
– reference: Johnson A.E., Hebert M.: Using spin images for efficient object recognition in cluttered 3D scenes. PAMI 21, 5 (1999), 433-449. 1
– reference: Manay S., Cremers D., Hong B.-W., Yezzi A.J., Soatto S.: Integral invariants for shape matching. PAMI 28, 10 (2006), 1602-1618. 1
– year: 2011
– volume: 29
  issue: 3
  year: 2010
  article-title: Learning 3D mesh segmentation and labeling
  publication-title: TOG
– volume: 28
  start-page: 1405
  issue: 5
  year: 2009
  end-page: 1413
  article-title: Shape analysis using the auto diffusion function
  publication-title: CGF
– volume: 21
  start-page: 807
  issue: 4
  year: 2002
  end-page: 832
  article-title: Shape distributions
  publication-title: TOG
– volume: 33
  start-page: 127
  issue: 5
  year: 2014
  end-page: 136
  article-title: Supervised learning of bag‐of‐features shape descriptors using sparse coding
  publication-title: CGF
– volume: 30
  start-page: 1
  issue: 4
  year: 2011
  end-page: 12
  article-title: Blended intrinsic maps
  publication-title: TOG
– volume: 24
  start-page: 408
  issue: 3
  year: 2005
  end-page: 416
  article-title: SCAPE: Shape completion and animation of people
  publication-title: TOG
– volume: 46
  start-page: 449
  issue: 1
  year: 2013
  end-page: 461
  article-title: A comparison of methods for non‐rigid 3D shape retrieval
  publication-title: Pattern Recognition
– volume: 28
  start-page: 1383
  issue: 5
  year: 2009
  end-page: 1392
  article-title: A concise and provably informative multi‐scale signature based on heat diffusion
  publication-title: CGF
– year: 2007
– volume: 33
  start-page: 35
  year: 2014
  end-page: 44
  article-title: Compressed manifold modes for mesh processing
  publication-title: Computer Graphics Forum
– year: 2003
– year: 2000
– volume: 21
  start-page: 433
  issue: 5
  year: 1999
  end-page: 449
  article-title: Using spin images for efficient object recognition in cluttered 3D scenes
  publication-title: PAMI
– volume: 38
  start-page: 342
  issue: 4
  year: 2006
  end-page: 366
  article-title: Laplace–beltrami spectra as ‘shape‐dna’ of surfaces and solids
  publication-title: Computer‐Aided Design
– volume: 25
  start-page: 1285
  issue: 10
  year: 2003
  end-page: 1295
  article-title: On bending invariant signatures for surfaces
  publication-title: PAMI
– year: 2014
– volume: 29
  start-page: 1555
  issue: 5
  year: 2010
  end-page: 1564
  article-title: One point isometric matching with the heat kernel
  publication-title: Computer Graphics Forum
– volume: 21
  start-page: 5
  issue: 1
  year: 2006
  end-page: 30
  article-title: Diffusion maps
  publication-title: Applied and Computational Harmonic Analysis
– volume: 22
  start-page: 281
  issue: 3
  year: 2003
  end-page: 289
  article-title: Multi‐scale feature extraction on point‐sampled surfaces
  publication-title: CGF
– year: 2010
– start-page: 35
  year: 2003
  end-page: 57
– year: 2012
– volume: 27
  start-page: 963
  issue: 11
  year: 2011
  end-page: 976
  article-title: Harris 3D: a robust extension of the harris operator for interest point detection on 3D meshes
  publication-title: Visual Computer
– year: 2008
– volume: 36
  start-page: 170
  issue: 1
  year: 2014
  end-page: 180
  article-title: Learning spectral descriptors for deformable shape correspondence
  publication-title: PAMI
– year: 2006
– volume: 1
  start-page: 541
  issue: 4
  year: 1989
  end-page: 551
  article-title: Backpropagation applied to handwritten zip code recognition
  publication-title: Neural Computation
– volume: 60
  start-page: 91
  issue: 2
  year: 2004
  end-page: 110
  article-title: Distinctive image features from scale‐invariant keypoints
  publication-title: IJCV
– volume: 28
  start-page: 1602
  issue: 10
  year: 2006
  end-page: 1618
  article-title: Integral invariants for shape matching
  publication-title: PAMI
– volume: 2
  start-page: 15
  issue: 1
  year: 1993
  end-page: 36
  article-title: Computing discrete minimal surfaces and their conjugates
  publication-title: Experimental Mathematics
– volume: 1
  start-page: 3
  year: 2015
  article-title: 3d shapenets: A deep representation for volumetric shape modeling
  publication-title: Proc. CVPR
– year: 2015
– volume: 4
  start-page: 373
  issue: 4
  year: 1994
  end-page: 398
  article-title: Embedding riemannian manifolds by their heat kernel
  publication-title: Geometric & Functional Analysis
– year: 2013
– ident: e_1_2_9_35_2
  doi: 10.1109/CVPR.2014.532
– ident: e_1_2_9_24_2
– ident: e_1_2_9_21_2
  doi: 10.1109/TPAMI.2013.148
– ident: e_1_2_9_16_2
  doi: 10.1109/34.765655
– ident: e_1_2_9_3_2
  doi: 10.1109/ICCVW.2011.6130444
– ident: e_1_2_9_27_2
  doi: 10.1109/TPAMI.2006.208
– ident: e_1_2_9_31_2
  doi: 10.1145/571647.571648
– ident: e_1_2_9_38_2
  doi: 10.1007/s00371-011-0610-y
– ident: e_1_2_9_37_2
  doi: 10.1016/j.cad.2005.10.011
– ident: e_1_2_9_2_2
  doi: 10.1145/1073204.1073207
– ident: e_1_2_9_13_2
  doi: 10.1111/j.1467-8659.2009.01517.x
– ident: e_1_2_9_26_2
– ident: e_1_2_9_22_2
  doi: 10.1111/cgf.12438
– ident: e_1_2_9_14_2
  doi: 10.1007/978-3-540-39966-7_36
– ident: e_1_2_9_5_2
  doi: 10.1007/BF01896401
– ident: e_1_2_9_33_2
  doi: 10.1111/1467-8659.00675
– ident: e_1_2_9_29_2
  doi: 10.1109/CVPR.2008.4587538
– ident: e_1_2_9_8_2
  doi: 10.1109/CVPR.2014.491
– ident: e_1_2_9_28_2
  doi: 10.1007/978-3-662-05105-4_2
– ident: e_1_2_9_42_2
– ident: e_1_2_9_9_2
– ident: e_1_2_9_11_2
– ident: e_1_2_9_6_2
– volume: 29
  issue: 3
  year: 2010
  ident: e_1_2_9_18_2
  article-title: Learning 3D mesh segmentation and labeling
  publication-title: TOG
– ident: e_1_2_9_23_2
  doi: 10.1162/neco.1989.1.4.541
– ident: e_1_2_9_30_2
  doi: 10.1111/cgf.12429
– ident: e_1_2_9_17_2
  doi: 10.1109/CVPR.2012.6247671
– volume: 1
  start-page: 3
  year: 2015
  ident: e_1_2_9_41_2
  article-title: 3d shapenets: A deep representation for volumetric shape modeling
  publication-title: Proc. CVPR
– ident: e_1_2_9_32_2
  doi: 10.1111/j.1467-8659.2010.01764.x
– ident: e_1_2_9_10_2
  doi: 10.1016/j.acha.2006.04.006
– ident: e_1_2_9_7_2
– ident: e_1_2_9_20_2
  doi: 10.1016/j.patcog.2012.07.014
– ident: e_1_2_9_15_2
  doi: 10.1145/2508363.2508364
– ident: e_1_2_9_12_2
  doi: 10.1109/TPAMI.2003.1233902
– ident: e_1_2_9_36_2
– ident: e_1_2_9_25_2
  doi: 10.1023/B:VISI.0000029664.99615.94
– ident: e_1_2_9_39_2
  doi: 10.1111/j.1467-8659.2009.01515.x
– ident: e_1_2_9_4_2
  doi: 10.25080/Majora-92bf1922-003
– ident: e_1_2_9_19_2
  doi: 10.1145/2010324.1964974
– ident: e_1_2_9_34_2
  doi: 10.1080/10586458.1993.10504266
– ident: e_1_2_9_40_2
SSID ssj0004765
Score 2.559995
Snippet In this paper, we propose a generalization of convolutional neural networks (CNN) to non‐Euclidean domains for the analysis of deformable shapes. Our...
In this paper, we propose a generalization of convolutional neural networks (CNN) to non-Euclidean domains for the analysis of deformable shapes. Our...
SourceID proquest
crossref
wiley
istex
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 13
SubjectTerms Analysis
Categories and Subject Descriptors (according to ACM CCS)
Computational Geometry and Object Modeling [I.3.5]
Computer graphics
Cost engineering
Deformation
Feature Measurement [I.4.7]
Formability
Fourier transforms
Learning
Learning [I.2.6]
Networks
Neural networks
Spectra
State of the art
Studies
Topological manifolds
Title Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks
URI https://api.istex.fr/ark:/67375/WNG-TC3RFCKJ-S/fulltext.pdf
https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.12693
https://www.proquest.com/docview/1702667745
https://www.proquest.com/docview/1778043569
Volume 34
WOSCitedRecordID wos000362293300003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1467-8659
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004765
  issn: 0167-7055
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bT9RAFD7BXR_0AUUlroAZjDG-1LTbmV7Ck1koRsnGIChvk5npdCWQLmmBGJ_4CfxGfgnnTC8siSYmvnXS03RyLj3f6Zz5BuAt1z63CgPJhFHh8bSwnk7CwMNiiwtltOVu9fz7XjydJkdH6dcl2Or2wjT8EP0PN4oM972mAFe6XghyMys-BOMoDR_AcIx-ywcw3N7PDvfutkXGkeiovYk0piUWokae_uF76WhImv11D2suIlaXcrIn_zXZp7DcIk32sXGNFViy5TN4vMA_-BxOWnbVGTMEom-urmnjJTUPsdw235N5VTPEtTh26FafWlb_VGe2ZtQxP2MuFx7_tjlzezYrfCM1srcOjaOy6TOvX8BhtnMw-eS1py94RoRp6KlY22BcoOJUqgIbKBNww2Oda5NT5osLoRHz6jgtjJ9Yg4VWlPjG8KhIhFB5uAqDcl7al8AKhcAqUWOliG3PF1oo7ds0T7A841hzjuB9ZwRpWmpyOiHjVHYlCupPOv2N4E0vetbwcfxJ6J2zZC-hqhNqYIuF_DHdlQeTcD-bfPksv41gvTO1bGO3lkGMdWmEsFiMYLO_jVFHSymqtPMLkiHiplBEKc7dGf7vs5GT3cxdvPp30TV4hMhMNJ2G6zA4ry7sBjw0l-fHdfW6dfRbV-YDrQ
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6VXSTgUN5ioYBBCHEJSjZ2HlIvaCEtdFmhsqW9WbbjLFWrbJW0CHHqT-hv5Jcw4zzYSiAhcYuViWKNZzzf2OPPAC-49rlV6EgmjAqPp4X1dBIGHiZbXCijLXe751-m8WyWHBykn9ZgszsL0_BD9Atu5BluviYHpwXpFS83i-J1MI7S8AoMOZqRGMDw7W62N_19LjKORMftTawxLbMQVfL0H1-KR0NS7fdLYHMVsrqYk938v97egvUWa7I3jXHchjVb3oEbKwyEd-Go5VddMEMw-uf5BR29pPIhlttmRllWNUNki22Hb_WxZfVXdWJrRjXzC-ai4eEPmzN3arPCP1Ipe2vS2CqbSvP6Huxl7-aTba-9f8EzIkxDT8XaBuMCNadSFdhAmYAbHutcm5xiX1wIjahXx2lh_MQaTLWixDeGR0UihMrD-zAol6V9AKxQCK0SNVaK-PZ8oYXSvk3zBBM0jlnnCF51oyBNS05Od2Qcyy5JQf1Jp78RPO9FTxpGjj8JvXRD2Uuo6ohK2GIh92dbcj4Jd7PJzgf5eQQb3VjL1ntrGcSYmUYIjMUInvWv0e9oM0WVdnlGMkTdFIooxb67kf97b-RkK3MPD_9d9Clc255_nMrp-9nOI7iOOE00dYcbMDitzuxjuGq-nR7W1ZPW6n8B1jgHnQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NbtQwEB6VLkL0UP7VpQUMQohLqmRjJ7HEBW1Jga5WVWmhN8t27KVqlV0lLUKc-gh9Rp6EsfPDVgIJiVusTBRrxpP5Jp75DPCSqpAaiY6k48QGlFsTqCyOAky2KJNaGep3zz9P0uk0Oz7m-yvwpuuFafgh-h9uzjP899o5uFkUdsnL9cxuR6OExzdgQBlP0C0HOwf50eR3X2SasI7b27HGtMxCrpKnf_haPBo41X6_BjaXIauPOfmd_5vtXVhvsSZ52yyOe7BiyvuwtsRA-ABOW37VGdEORv-8vHKtl658iBSm-aLMq5ogssWxx7fqzJD6q1yYmria-Rnx0fDkhymI79qs8I2ulL1d0jgqm0rz-iEc5e8Ox--D9vyFQLOYx4FMlYlGFjUnuYxMJHVENU1VoXThYl9qmULUq1JudZgZjalWkoVa08RmjMkifgSr5bw0G0CsRGiVyZGUjm8vZIpJFRpeZJigUcw6h_C6s4LQLTm5OyPjTHRJCupPeP0N4UUvumgYOf4k9MqbspeQ1akrYUuZ-DLdFYfj-CAf730Un4aw1dlatN5biyjFzDRBYMyG8Ly_jX7nNlNkaeYXTsZRN8Us4Th3b_m_z0aMd3N_8fjfRZ_Brf2dXEw-TPc24TbCNNaUHW7B6nl1YZ7ATf3t_KSunraL_hdXsgcY
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Learning+class-specific+descriptors+for+deformable+shapes+using+localized+spectral+convolutional+networks&rft.jtitle=Computer+graphics+forum&rft.au=Boscaini%2C+D&rft.au=Masci%2C+J&rft.au=Melzi%2C+S&rft.au=Bronstein%2C+M+M&rft.date=2015-08-01&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=34&rft.issue=5&rft.spage=13&rft.epage=23&rft_id=info:doi/10.1111%2Fcgf.12693&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon