Stochastic human motion prediction using a quantized conditional diffusion model

Human motion prediction is a fundamental task in computer vision, aiming to forecast future human poses based on observed motion sequences. Existing deterministic methods generate a single future motion sequence, neglecting the inherent stochasticity and diversity of human behaviors. To address this...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Knowledge-based systems Jg. 309; S. 112823
Hauptverfasser: Huang, Biaozhang, Li, Xinde, Hu, Chuanfei, Li, Heqing
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 30.01.2025
Schlagworte:
ISSN:0950-7051
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Human motion prediction is a fundamental task in computer vision, aiming to forecast future human poses based on observed motion sequences. Existing deterministic methods generate a single future motion sequence, neglecting the inherent stochasticity and diversity of human behaviors. To address this limitation, we propose a novel two-stage stochastic human motion prediction framework, termed the Quantized Conditional Diffusion Model (QCDM), which combines a Discrete Motion Quantization Module and a Conditional Motion Generation Module. Specifically, we first design a discrete motion quantization module that leverages Graph Convolutional Networks (GCNs) and one-dimensional temporal convolutions to encode motion sequences into continuous latent representations. These representations are then quantized into discrete latent variables using a learnable codebook. A decoder reconstructs the motion sequence from these discrete variables, preserving key motion patterns while eliminating redundancies. Next, we develop a conditional motion generation module that integrates GCNs and Transformers for denoising spatio-temporal features. The diffusion process iteratively refines noisy motion data by reversing a gradual noising procedure, modeling the distribution of plausible future motions. Action category information and observed historical motion segments are incorporated as conditions into the denoising process, enabling controllable generation of specific motions. Additionally, we introduce a diversity enhancement strategy by penalizing overly similar samples. This encourages the model to explore a wider range of plausible motions and thereby improving the diversity and richness of the prediction results. Extensive experiments demonstrate that the QCDM framework outperforms state-of-the-art methods in stochastic human motion prediction tasks, offering both accuracy and diversity in generated motion sequences. •Combines motion quantization with conditional diffusion model for motion prediction.•Utilizes GCNs and temporal convolutions for efficient motion feature extraction.•Integrates action category info for controllable, diverse motion generation.•Implements diversity enhancement to reduce similarity in prediction samples.
AbstractList Human motion prediction is a fundamental task in computer vision, aiming to forecast future human poses based on observed motion sequences. Existing deterministic methods generate a single future motion sequence, neglecting the inherent stochasticity and diversity of human behaviors. To address this limitation, we propose a novel two-stage stochastic human motion prediction framework, termed the Quantized Conditional Diffusion Model (QCDM), which combines a Discrete Motion Quantization Module and a Conditional Motion Generation Module. Specifically, we first design a discrete motion quantization module that leverages Graph Convolutional Networks (GCNs) and one-dimensional temporal convolutions to encode motion sequences into continuous latent representations. These representations are then quantized into discrete latent variables using a learnable codebook. A decoder reconstructs the motion sequence from these discrete variables, preserving key motion patterns while eliminating redundancies. Next, we develop a conditional motion generation module that integrates GCNs and Transformers for denoising spatio-temporal features. The diffusion process iteratively refines noisy motion data by reversing a gradual noising procedure, modeling the distribution of plausible future motions. Action category information and observed historical motion segments are incorporated as conditions into the denoising process, enabling controllable generation of specific motions. Additionally, we introduce a diversity enhancement strategy by penalizing overly similar samples. This encourages the model to explore a wider range of plausible motions and thereby improving the diversity and richness of the prediction results. Extensive experiments demonstrate that the QCDM framework outperforms state-of-the-art methods in stochastic human motion prediction tasks, offering both accuracy and diversity in generated motion sequences. •Combines motion quantization with conditional diffusion model for motion prediction.•Utilizes GCNs and temporal convolutions for efficient motion feature extraction.•Integrates action category info for controllable, diverse motion generation.•Implements diversity enhancement to reduce similarity in prediction samples.
ArticleNumber 112823
Author Li, Heqing
Huang, Biaozhang
Li, Xinde
Hu, Chuanfei
Author_xml – sequence: 1
  givenname: Biaozhang
  orcidid: 0009-0009-8628-5839
  surname: Huang
  fullname: Huang, Biaozhang
  organization: Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation, Southeast University, Nanjing, 210096, China
– sequence: 2
  givenname: Xinde
  surname: Li
  fullname: Li, Xinde
  email: xindeli@seu.edu.cn
  organization: Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation, Southeast University, Nanjing, 210096, China
– sequence: 3
  givenname: Chuanfei
  surname: Hu
  fullname: Hu, Chuanfei
  organization: Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation, Southeast University, Nanjing, 210096, China
– sequence: 4
  givenname: Heqing
  surname: Li
  fullname: Li, Heqing
  organization: Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation, Southeast University, Nanjing, 210096, China
BookMark eNqFkE1LAzEQhnOoYFv9Bx72D-yar-6HB0GKX1BQUM8hnUxs6japm1Sov95d68mDnmZg5nmZeSZk5INHQs4YLRhl5fm6ePMh7mPBKZcFY7zmYkTGtJnRvKIzdkwmMa4ppZyzekwen1KAlY7JQbbabbTPNiG54LNth8bBd7uLzr9mOnvfaZ_cJ5oMgjdumOk2M87afiMMpMH2hBxZ3UY8_alT8nJz_Ty_yxcPt_fzq0UOgpYpR1ouRW2EBGnRLhlIJrBhFWrZWN0ALoGVNXJugDHNZSnMzJrKSl4JBlCJKbk45EIXYuzQKnBJDzelTrtWMaoGH2qtDj7U4EMdfPSw_AVvO7fR3f4_7PKAYf_Yh8NORXDooTfVISRlgvs74AuI04NM
CitedBy_id crossref_primary_10_1016_j_eswa_2025_129140
Cites_doi 10.1109/ICCV51070.2023.01816
10.1109/TCSVT.2023.3239322
10.1109/CVPR52688.2022.00799
10.1145/3550454.3555435
10.1109/CVPRW.2018.00191
10.1109/LRA.2024.3401116
10.1109/TPAMI.2013.248
10.1109/TII.2022.3182780
10.1109/CVPR52688.2022.00635
10.1109/CVPR52729.2023.01415
10.1109/CVPR42600.2020.00527
10.1016/j.knosys.2022.108304
10.1109/CVPR52688.2022.01043
10.1007/s11263-009-0273-6
10.1109/ICCV.2017.361
10.1109/ICCV51070.2023.00875
10.1016/j.patcog.2021.107868
10.1109/ICCV48922.2021.01114
10.1109/ICCV48922.2021.01118
10.1109/JSEN.2023.3266609
10.1007/978-3-030-01228-1_17
10.1109/ICCV.2019.00723
10.1109/CVPR46437.2021.01268
10.1109/ICCV51070.2023.00220
10.1214/aoms/1177704261
10.1145/3386569.3392422
10.1016/j.knosys.2023.111283
10.1007/978-3-030-58545-7_20
10.1109/TFUZZ.2021.3079495
10.1109/CVPR.2017.525
ContentType Journal Article
Copyright 2024 Elsevier B.V.
Copyright_xml – notice: 2024 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.knosys.2024.112823
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
ExternalDocumentID 10_1016_j_knosys_2024_112823
S0950705124014576
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
77K
8P~
9JN
AACTN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXKI
AAXUO
AAYFN
ABAOU
ABBOA
ABIVO
ABJNI
ABMAC
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AFJKZ
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSW
SSZ
T5K
WH7
XPP
ZMT
~02
~G-
29L
77I
9DU
AAQXK
AATTM
AAYWO
AAYXX
ABDPE
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEUPX
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EFLBG
EJD
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
R2-
SBC
SET
UHS
WUQ
~HD
ID FETCH-LOGICAL-c306t-e06b38d34c4fefb1c413e917ea49fa9cebc168e22dc11a2463d5fd7f42731cc73
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001385489600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0950-7051
IngestDate Sat Nov 29 01:33:43 EST 2025
Tue Nov 18 22:36:15 EST 2025
Sat Feb 01 16:08:16 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Conditional diffusion model
Human motion prediction
Vector quantized variational autoencoder
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-e06b38d34c4fefb1c413e917ea49fa9cebc168e22dc11a2463d5fd7f42731cc73
ORCID 0009-0009-8628-5839
ParticipantIDs crossref_citationtrail_10_1016_j_knosys_2024_112823
crossref_primary_10_1016_j_knosys_2024_112823
elsevier_sciencedirect_doi_10_1016_j_knosys_2024_112823
PublicationCentury 2000
PublicationDate 2025-01-30
PublicationDateYYYYMMDD 2025-01-30
PublicationDate_xml – month: 01
  year: 2025
  text: 2025-01-30
  day: 30
PublicationDecade 2020
PublicationTitle Knowledge-based systems
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References G. Tevet, S. Raab, B. Gordon, Y. Shafir, D. Cohen-or, A.H. Bermano, Human Motion Diffusion Model, in: The Eleventh International Conference on Learning Representations, 2022.
M. Hassan, D. Ceylan, R. Villegas, J. Saito, J. Yang, Y. Zhou, M.J. Black, Stochastic Scene-Aware Motion Prediction, in: IEEE International Conference on Computer Vision, ICCV, 2021.
Dong, Li, Dezert, Zhou, Zhu, Cao, Khyam, Ge (b7) 2022; 19
Y. Yuan, K. Kitani, DLOW: Diversifying Latent Flows for Diverse Human Motion Prediction, in: European Conference on Computer Vision, ECCV, 2020, pp. 265–281.
J. Zhang, Y. Zhang, X. Cun, Y. Zhang, H. Zhao, H. Lu, X. Shen, Y. Shan, Generating human motion from textual descriptions with discrete representations, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14730–14740.
Li, Chen, Zhao, Zhang, Wang, Tian (b59) 2020
Ramesh, Pavlov, Goh, Gray, Voss, Radford, Chen, Sutskever (b42) 2021
S. Aliakbarian, F.S. Saleh, M. Salzmann, L. Petersson, S. Gould, A stochastic conditioning scheme for diverse human motion prediction, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 5223–5232.
Liu, Lyu, Wu, Chen, Hao, Ji (b16) 2021; vol. 35
Arjovsky, Bottou (b20) 2017
Tang, Zhang, Ding, Gu, Yin (b62) 2023
Tian, Zheng, Liang (b58) 2024
Sigal, Balan, Black (b51) 2010
Mao, Liu, Salzmann, Li (b3) 2019
A. Hernandez, J. Gall, F. Moreno-Noguer, Human motion prediction via spatio-temporal inpainting, in: The IEEE International Conference on Computer Vision, ICCV, 2019, pp. 9622–9631.
Wang, Yu, Zhao, Zhang, Zhou, Yuan, Chen (b17) 2020; vol. 34
Liu, Zhou, Mao, Bao, Li, Shi, Chen, Shen, Huang (b30) 2024; 284
Dong, Li, Dezert, Zhou, Zuo, Ge (b1) 2023
Ionescu, Papava, Olaru, Sminchisescu (b50) 2014; 36
L.-H. Chen, J. Zhang, Y. Li, Y. Pang, X. Xia, T. Liu, HumanMAC: Masked Motion Completion for Human Motion Prediction, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV, 2023, pp. 9544–9555.
Wei, Sun, Li, Lu, Li, Sun, Hu (b26) 2023
Dhariwal, Jun, Payne, Kim, Radford, Sutskever (b44) 2020
Ling, Zinno, Cheng, Van De Panne (b19) 2020; 39
Kingma, Welling (b33) 2014; 1050
G. Barquero, S. Escalera, C. Palmero, Belfusion: Latent diffusion for behavior-driven human motion prediction, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 2317–2327.
Y.J. Ma, J.P. Inala, D. Jayaraman, O. Bastani, Likelihood-based diverse sampling for trajectory forecasting, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 13279–13288.
V. Nair, G.E. Hinton, Rectified linear units improve restricted boltzmann machines, in: Proceedings of the 27th International Conference on Machine Learning, ICML-10, 2010, pp. 807–814.
H. Ma, J. Li, R. Hosseini, M. Tomizuka, C. Choi, Multi-objective diverse human motion prediction with knowledge distillation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8161–8171.
Fragkiadaki, Levine, Felsen, Malik (b54) 2015
Li, Zhang, Lee, Lee (b55) 2018
X. Yan, A. Rastogi, R. Villegas, K. Sunkavalli, E. Shechtman, S. Hadap, E. Yumer, H. Lee, Mt-vae: Learning motion transformations to generate multimodal human dynamics, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 265–281.
Martinez, Black, Romero (b52) 2017
P. Esser, R. Rombach, B. Ommer, Taming transformers for high-resolution image synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12873–12883.
Sheng, Li (b8) 2021; 114
Zhang, Cai, Pan, Hong, Guo, Yang, Liu (b25) 2024
Van Den Oord, Vinyals (b28) 2017; vol. 30
Fu, Yang, Dang, Liu, Yin (b6) 2023
T.N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, in: International Conference on Learning Representations, 2017.
S. Aliakbarian, F. Saleh, L. Petersson, S. Gould, M. Salzmann, Contextually plausible and diverse 3d human motion prediction, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 11333–11342.
Dang, Nie, Long, Zhang, Li (b60) 2021
Williams, Ringer, Ash, MacLeod, Dougherty, Hughes (b41) 2020; 33
Dieleman, Van Den Oord, Simonyan (b45) 2018; vol. 31
J. Walker, K. Marino, A. Gupta, M. Hebert, The pose knows: Video forecasting by generating pose futures, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 3332–3341.
Ao, Gao, Lou, Chen, Liu (b43) 2022; 41
Zhong, Hu, Zhang, Ye, Xia (b5) 2022
Goodfellow, Bengio, Courville (b34) 2016
S. Gu, D. Chen, J. Bao, F. Wen, B. Zhang, D. Chen, L. Yuan, B. Guo, Vector quantized diffusion model for text-to-image synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10696–10706.
Ho, Jain, Abbeel (b23) 2020
E. Barsoum, J. Kender, Z. Liu, Hp-gan: Probabilistic 3d human motion prediction via gan, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018, pp. 1418–1427.
S. Gurumurthy, R.K. Sarvadevabhatla, R.V. Babu, Deligan: Generative Adversarial Networks for Diverse and Limited Data, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 166–174.
I. Loshchilov, F. Hutter, Decoupled Weight Decay Regularization, in: International Conference on Learning Representations, 2018.
Guo, Zuo, Wang, Cheng (b38) 2022
Aksan, Cao, Kaufmann, Hilliges (b4) 2021
Ahn, Mascaro, Lee (b37) 2023
S. Chen, P. Sun, Y. Song, P. Luo, Diffusiondet: Diffusion model for object detection, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 19830–19843.
Wu, Wu, Shen, Du, Telikani, Fahmideh, Liang (b9) 2022; 241
T. Salzmann, M. Pavone, M. Ryll, Motron: Multimodal probabilistic human motion forecasting, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 6457–6466.
Zuo, Li, Dong, Dezert, Ge (b2) 2023; 23
Dong, Li, Dezert, Zhou, Zhu, Wei, Ge (b10) 2021; 29
Ma, Nie, Long, Zhang, Li (b61) 2022
Hachigian (b48) 1963; 34
Kundu, Gor, Babu (b31) 2019; vol. 33
Sohl-Dickstein, Weiss, Maheswaranathan, Ganguli (b35) 2015
Ho (10.1016/j.knosys.2024.112823_b23) 2020
10.1016/j.knosys.2024.112823_b39
Zhang (10.1016/j.knosys.2024.112823_b25) 2024
Dong (10.1016/j.knosys.2024.112823_b7) 2022; 19
10.1016/j.knosys.2024.112823_b36
Dong (10.1016/j.knosys.2024.112823_b1) 2023
Ramesh (10.1016/j.knosys.2024.112823_b42) 2021
Arjovsky (10.1016/j.knosys.2024.112823_b20) 2017
10.1016/j.knosys.2024.112823_b32
Tian (10.1016/j.knosys.2024.112823_b58) 2024
Sheng (10.1016/j.knosys.2024.112823_b8) 2021; 114
Ao (10.1016/j.knosys.2024.112823_b43) 2022; 41
Hachigian (10.1016/j.knosys.2024.112823_b48) 1963; 34
Tang (10.1016/j.knosys.2024.112823_b62) 2023
10.1016/j.knosys.2024.112823_b27
10.1016/j.knosys.2024.112823_b29
10.1016/j.knosys.2024.112823_b24
Sigal (10.1016/j.knosys.2024.112823_b51) 2010
Zhong (10.1016/j.knosys.2024.112823_b5) 2022
Sohl-Dickstein (10.1016/j.knosys.2024.112823_b35) 2015
10.1016/j.knosys.2024.112823_b63
10.1016/j.knosys.2024.112823_b21
Fu (10.1016/j.knosys.2024.112823_b6) 2023
10.1016/j.knosys.2024.112823_b22
Fragkiadaki (10.1016/j.knosys.2024.112823_b54) 2015
Kingma (10.1016/j.knosys.2024.112823_b33) 2014; 1050
Ionescu (10.1016/j.knosys.2024.112823_b50) 2014; 36
Martinez (10.1016/j.knosys.2024.112823_b52) 2017
Li (10.1016/j.knosys.2024.112823_b55) 2018
Mao (10.1016/j.knosys.2024.112823_b3) 2019
10.1016/j.knosys.2024.112823_b18
Li (10.1016/j.knosys.2024.112823_b59) 2020
Dang (10.1016/j.knosys.2024.112823_b60) 2021
10.1016/j.knosys.2024.112823_b12
Kundu (10.1016/j.knosys.2024.112823_b31) 2019; vol. 33
10.1016/j.knosys.2024.112823_b56
10.1016/j.knosys.2024.112823_b13
10.1016/j.knosys.2024.112823_b57
Dong (10.1016/j.knosys.2024.112823_b10) 2021; 29
10.1016/j.knosys.2024.112823_b14
10.1016/j.knosys.2024.112823_b15
Dieleman (10.1016/j.knosys.2024.112823_b45) 2018; vol. 31
10.1016/j.knosys.2024.112823_b53
Ling (10.1016/j.knosys.2024.112823_b19) 2020; 39
10.1016/j.knosys.2024.112823_b11
Wei (10.1016/j.knosys.2024.112823_b26) 2023
Van Den Oord (10.1016/j.knosys.2024.112823_b28) 2017; vol. 30
Goodfellow (10.1016/j.knosys.2024.112823_b34) 2016
Liu (10.1016/j.knosys.2024.112823_b16) 2021; vol. 35
Aksan (10.1016/j.knosys.2024.112823_b4) 2021
Liu (10.1016/j.knosys.2024.112823_b30) 2024; 284
Zuo (10.1016/j.knosys.2024.112823_b2) 2023; 23
10.1016/j.knosys.2024.112823_b49
Ma (10.1016/j.knosys.2024.112823_b61) 2022
Williams (10.1016/j.knosys.2024.112823_b41) 2020; 33
10.1016/j.knosys.2024.112823_b46
10.1016/j.knosys.2024.112823_b47
Guo (10.1016/j.knosys.2024.112823_b38) 2022
Wu (10.1016/j.knosys.2024.112823_b9) 2022; 241
Dhariwal (10.1016/j.knosys.2024.112823_b44) 2020
10.1016/j.knosys.2024.112823_b40
Wang (10.1016/j.knosys.2024.112823_b17) 2020; vol. 34
Ahn (10.1016/j.knosys.2024.112823_b37) 2023
References_xml – volume: 36
  start-page: 1325
  year: 2014
  end-page: 1339
  ident: b50
  article-title: Human3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– reference: E. Barsoum, J. Kender, Z. Liu, Hp-gan: Probabilistic 3d human motion prediction via gan, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018, pp. 1418–1427.
– reference: P. Esser, R. Rombach, B. Ommer, Taming transformers for high-resolution image synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12873–12883.
– volume: vol. 35
  start-page: 2225
  year: 2021
  end-page: 2232
  ident: b16
  article-title: Aggregated multi-gans for controlled 3d human motion prediction
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– year: 2024
  ident: b58
  article-title: TransFusion: A practical and effective transformer-based diffusion model for 3d human motion prediction
  publication-title: IEEE Robot. Autom. Lett.
– year: 2010
  ident: b51
  article-title: HumanEva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion
  publication-title: Int. J. Comput. Vis. (IJCV)
– reference: M. Hassan, D. Ceylan, R. Villegas, J. Saito, J. Yang, Y. Zhou, M.J. Black, Stochastic Scene-Aware Motion Prediction, in: IEEE International Conference on Computer Vision, ICCV, 2021.
– reference: G. Tevet, S. Raab, B. Gordon, Y. Shafir, D. Cohen-or, A.H. Bermano, Human Motion Diffusion Model, in: The Eleventh International Conference on Learning Representations, 2022.
– volume: 23
  start-page: 12309
  year: 2023
  end-page: 12319
  ident: b2
  article-title: Combination of different-granularity beliefs for sensor-based human activity recognition
  publication-title: IEEE Sens. J.
– year: 2022
  ident: b61
  article-title: Progressively generating better initial guesses towards next stages for high-quality human motion prediction
  publication-title: Proceedings of the Conference on Computer Vision and Pattern Recognition
– volume: vol. 30
  year: 2017
  ident: b28
  article-title: Neural discrete representation learning
  publication-title: Advances in Neural Information Processing Systems
– reference: X. Yan, A. Rastogi, R. Villegas, K. Sunkavalli, E. Shechtman, S. Hadap, E. Yumer, H. Lee, Mt-vae: Learning motion transformations to generate multimodal human dynamics, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 265–281.
– reference: I. Loshchilov, F. Hutter, Decoupled Weight Decay Regularization, in: International Conference on Learning Representations, 2018.
– reference: A. Hernandez, J. Gall, F. Moreno-Noguer, Human motion prediction via spatio-temporal inpainting, in: The IEEE International Conference on Computer Vision, ICCV, 2019, pp. 9622–9631.
– volume: vol. 34
  start-page: 12281
  year: 2020
  end-page: 12288
  ident: b17
  article-title: Learning diverse stochastic human-action generators by learning smooth latent transitions
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– start-page: 4346
  year: 2015
  end-page: 4354
  ident: b54
  article-title: Recurrent network models for human dynamics
  publication-title: Proceedings of the 2015 IEEE International Conference on Computer Vision
– year: 2023
  ident: b1
  article-title: Graph-structure-based multigranular belief fusion for human activity recognition
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: vol. 33
  start-page: 8553
  year: 2019
  end-page: 8560
  ident: b31
  article-title: Bihmp-gan: Bidirectional 3d human motion prediction gan
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– reference: S. Aliakbarian, F. Saleh, L. Petersson, S. Gould, M. Salzmann, Contextually plausible and diverse 3d human motion prediction, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 11333–11342.
– start-page: 6840
  year: 2020
  end-page: 6851
  ident: b23
  article-title: Denoising diffusion probabilistic models
  publication-title: Advances in Neural Information Processing Systems
– volume: 34
  start-page: 233
  year: 1963
  end-page: 237
  ident: b48
  article-title: Collapsed Markov chains and the Chapman-Kolmogorov equation
  publication-title: Ann. Math. Stat.
– start-page: 4317
  year: 2019
  end-page: 4326
  ident: b3
  article-title: Learning trajectory dependencies for human motion prediction
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– volume: 29
  start-page: 3607
  year: 2021
  end-page: 3619
  ident: b10
  article-title: Evidential reasoning with hesitant fuzzy belief structures for human activity recognition
  publication-title: IEEE Trans. Fuzzy Syst.
– reference: T. Salzmann, M. Pavone, M. Ryll, Motron: Multimodal probabilistic human motion forecasting, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 6457–6466.
– volume: 1050
  start-page: 1
  year: 2014
  ident: b33
  article-title: Auto-encoding variational Bayes
  publication-title: Stat
– reference: T.N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, in: International Conference on Learning Representations, 2017.
– start-page: 6447
  year: 2022
  end-page: 6456
  ident: b5
  article-title: Spatio-temporal gating-adjacency GCN for human motion prediction
  publication-title: Proceedings of the Conference on Computer Vision and Pattern Recognition
– start-page: 2256
  year: 2015
  end-page: 2265
  ident: b35
  article-title: Deep unsupervised learning using nonequilibrium thermodynamics
  publication-title: International Conference on Machine Learning
– year: 2023
  ident: b26
  article-title: Human joint kinematics diffusion-refinement for stochastic motion prediction
  publication-title: Association for the Advancement of Artificial Intelligence
– year: 2023
  ident: b6
  article-title: Learning constrained dynamic correlations in spatiotemporal graphs for motion prediction
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 19
  start-page: 5530
  year: 2022
  end-page: 5542
  ident: b7
  article-title: Multisource weighted domain adaptation with evidential reasoning for activity recognition
  publication-title: IEEE Trans. Ind. Inform.
– volume: 114
  year: 2021
  ident: b8
  article-title: Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network
  publication-title: Pattern Recognit.
– reference: S. Chen, P. Sun, Y. Song, P. Luo, Diffusiondet: Diffusion model for object detection, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 19830–19843.
– year: 2016
  ident: b34
  article-title: Deep Learning
– reference: G. Barquero, S. Escalera, C. Palmero, Belfusion: Latent diffusion for behavior-driven human motion prediction, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 2317–2327.
– reference: J. Zhang, Y. Zhang, X. Cun, Y. Zhang, H. Zhao, H. Lu, X. Shen, Y. Shan, Generating human motion from textual descriptions with discrete representations, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14730–14740.
– start-page: 2275
  year: 2018
  end-page: 2284
  ident: b55
  article-title: Convolutional sequence to sequence model for human dynamics
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– reference: V. Nair, G.E. Hinton, Rectified linear units improve restricted boltzmann machines, in: Proceedings of the 27th International Conference on Machine Learning, ICML-10, 2010, pp. 807–814.
– volume: vol. 31
  year: 2018
  ident: b45
  article-title: The challenge of realistic music generation: modelling raw audio at scale
  publication-title: Advances in Neural Information Processing Systems
– year: 2024
  ident: b25
  article-title: Motiondiffuse: Text-driven human motion generation with diffusion model
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– year: 2020
  ident: b44
  article-title: Jukebox: A generative model for music
– reference: S. Aliakbarian, F.S. Saleh, M. Salzmann, L. Petersson, S. Gould, A stochastic conditioning scheme for diverse human motion prediction, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 5223–5232.
– volume: 39
  year: 2020
  ident: b19
  article-title: Character controllers using motion vaes
  publication-title: ACM Trans. Graph.
– volume: 33
  start-page: 4524
  year: 2020
  end-page: 4535
  ident: b41
  article-title: Hierarchical quantized autoencoders
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 214
  year: 2020
  end-page: 223
  ident: b59
  article-title: Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– reference: Y. Yuan, K. Kitani, DLOW: Diversifying Latent Flows for Diverse Human Motion Prediction, in: European Conference on Computer Vision, ECCV, 2020, pp. 265–281.
– start-page: 580
  year: 2022
  end-page: 597
  ident: b38
  article-title: Tm2t: Stochastic and tokenized modeling for the reciprocal generation of 3d human motions and texts
  publication-title: European Conference on Computer Vision
– reference: J. Walker, K. Marino, A. Gupta, M. Hebert, The pose knows: Video forecasting by generating pose futures, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 3332–3341.
– volume: 41
  start-page: 1
  year: 2022
  end-page: 19
  ident: b43
  article-title: Rhythmic gesticulator: Rhythm-aware co-speech gesture synthesis with hierarchical neural embeddings
  publication-title: ACM Trans. Graph.
– year: 2023
  ident: b62
  article-title: Collaborative multi-dynamic pattern modeling for human motion prediction
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– reference: S. Gurumurthy, R.K. Sarvadevabhatla, R.V. Babu, Deligan: Generative Adversarial Networks for Diverse and Limited Data, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 166–174.
– reference: Y.J. Ma, J.P. Inala, D. Jayaraman, O. Bastani, Likelihood-based diverse sampling for trajectory forecasting, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 13279–13288.
– volume: 241
  year: 2022
  ident: b9
  article-title: Distributed agent-based deep reinforcement learning for large scale traffic signal control
  publication-title: Knowl.-Based Syst.
– reference: H. Ma, J. Li, R. Hosseini, M. Tomizuka, C. Choi, Multi-objective diverse human motion prediction with knowledge distillation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8161–8171.
– volume: 284
  year: 2024
  ident: b30
  article-title: Global disentangled graph convolutional neural network based on a graph topological metric
  publication-title: Knowl.-Based Syst.
– start-page: 11467
  year: 2021
  end-page: 11476
  ident: b60
  article-title: MSR-gcn: Multi-scale residual graph convolution networks for human motion prediction
  publication-title: Proceedings of the International Conference on Computer Vision
– reference: L.-H. Chen, J. Zhang, Y. Li, Y. Pang, X. Xia, T. Liu, HumanMAC: Masked Motion Completion for Human Motion Prediction, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV, 2023, pp. 9544–9555.
– start-page: 8821
  year: 2021
  end-page: 8831
  ident: b42
  article-title: Zero-shot text-to-image generation
  publication-title: International Conference on Machine Learning
– reference: S. Gu, D. Chen, J. Bao, F. Wen, B. Zhang, D. Chen, L. Yuan, B. Guo, Vector quantized diffusion model for text-to-image synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10696–10706.
– start-page: 565
  year: 2021
  end-page: 574
  ident: b4
  article-title: A spatio-temporal transformer for 3d human motion prediction
  publication-title: Proceedings of the 2021 International Conference on 3D Vision
– year: 2017
  ident: b20
  article-title: Towards principled methods for training generative adversarial networks
– start-page: 9837
  year: 2023
  end-page: 9843
  ident: b37
  article-title: Can we use diffusion probabilistic models for 3d motion prediction?
  publication-title: 2023 IEEE International Conference on Robotics and Automation
– start-page: 2891
  year: 2017
  end-page: 2900
  ident: b52
  article-title: On human motion prediction using recurrent neural networks
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: vol. 35
  start-page: 2225
  year: 2021
  ident: 10.1016/j.knosys.2024.112823_b16
  article-title: Aggregated multi-gans for controlled 3d human motion prediction
– ident: 10.1016/j.knosys.2024.112823_b22
  doi: 10.1109/ICCV51070.2023.01816
– year: 2023
  ident: 10.1016/j.knosys.2024.112823_b62
  article-title: Collaborative multi-dynamic pattern modeling for human motion prediction
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2023.3239322
– ident: 10.1016/j.knosys.2024.112823_b57
  doi: 10.1109/CVPR52688.2022.00799
– start-page: 6840
  year: 2020
  ident: 10.1016/j.knosys.2024.112823_b23
  article-title: Denoising diffusion probabilistic models
– year: 2023
  ident: 10.1016/j.knosys.2024.112823_b6
  article-title: Learning constrained dynamic correlations in spatiotemporal graphs for motion prediction
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: vol. 30
  year: 2017
  ident: 10.1016/j.knosys.2024.112823_b28
  article-title: Neural discrete representation learning
– volume: 41
  start-page: 1
  issue: 6
  year: 2022
  ident: 10.1016/j.knosys.2024.112823_b43
  article-title: Rhythmic gesticulator: Rhythm-aware co-speech gesture synthesis with hierarchical neural embeddings
  publication-title: ACM Trans. Graph.
  doi: 10.1145/3550454.3555435
– start-page: 214
  year: 2020
  ident: 10.1016/j.knosys.2024.112823_b59
  article-title: Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction
– start-page: 4346
  year: 2015
  ident: 10.1016/j.knosys.2024.112823_b54
  article-title: Recurrent network models for human dynamics
– year: 2022
  ident: 10.1016/j.knosys.2024.112823_b61
  article-title: Progressively generating better initial guesses towards next stages for high-quality human motion prediction
– ident: 10.1016/j.knosys.2024.112823_b24
– ident: 10.1016/j.knosys.2024.112823_b15
  doi: 10.1109/CVPRW.2018.00191
– year: 2017
  ident: 10.1016/j.knosys.2024.112823_b20
– year: 2024
  ident: 10.1016/j.knosys.2024.112823_b58
  article-title: TransFusion: A practical and effective transformer-based diffusion model for 3d human motion prediction
  publication-title: IEEE Robot. Autom. Lett.
  doi: 10.1109/LRA.2024.3401116
– volume: 36
  start-page: 1325
  issue: 7
  year: 2014
  ident: 10.1016/j.knosys.2024.112823_b50
  article-title: Human3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2013.248
– year: 2020
  ident: 10.1016/j.knosys.2024.112823_b44
– volume: 19
  start-page: 5530
  issue: 4
  year: 2022
  ident: 10.1016/j.knosys.2024.112823_b7
  article-title: Multisource weighted domain adaptation with evidential reasoning for activity recognition
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2022.3182780
– start-page: 2891
  year: 2017
  ident: 10.1016/j.knosys.2024.112823_b52
  article-title: On human motion prediction using recurrent neural networks
– year: 2016
  ident: 10.1016/j.knosys.2024.112823_b34
– start-page: 9837
  year: 2023
  ident: 10.1016/j.knosys.2024.112823_b37
  article-title: Can we use diffusion probabilistic models for 3d motion prediction?
– ident: 10.1016/j.knosys.2024.112823_b63
  doi: 10.1109/CVPR52688.2022.00635
– start-page: 6447
  year: 2022
  ident: 10.1016/j.knosys.2024.112823_b5
  article-title: Spatio-temporal gating-adjacency GCN for human motion prediction
– ident: 10.1016/j.knosys.2024.112823_b39
  doi: 10.1109/CVPR52729.2023.01415
– ident: 10.1016/j.knosys.2024.112823_b12
  doi: 10.1109/CVPR42600.2020.00527
– volume: 33
  start-page: 4524
  year: 2020
  ident: 10.1016/j.knosys.2024.112823_b41
  article-title: Hierarchical quantized autoencoders
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 241
  year: 2022
  ident: 10.1016/j.knosys.2024.112823_b9
  article-title: Distributed agent-based deep reinforcement learning for large scale traffic signal control
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2022.108304
– start-page: 580
  year: 2022
  ident: 10.1016/j.knosys.2024.112823_b38
  article-title: Tm2t: Stochastic and tokenized modeling for the reciprocal generation of 3d human motions and texts
– start-page: 4317
  year: 2019
  ident: 10.1016/j.knosys.2024.112823_b3
  article-title: Learning trajectory dependencies for human motion prediction
– ident: 10.1016/j.knosys.2024.112823_b47
  doi: 10.1109/CVPR52688.2022.01043
– start-page: 2275
  year: 2018
  ident: 10.1016/j.knosys.2024.112823_b55
  article-title: Convolutional sequence to sequence model for human dynamics
– start-page: 565
  year: 2021
  ident: 10.1016/j.knosys.2024.112823_b4
  article-title: A spatio-temporal transformer for 3d human motion prediction
– year: 2010
  ident: 10.1016/j.knosys.2024.112823_b51
  article-title: HumanEva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion
  publication-title: Int. J. Comput. Vis. (IJCV)
  doi: 10.1007/s11263-009-0273-6
– ident: 10.1016/j.knosys.2024.112823_b29
– start-page: 2256
  year: 2015
  ident: 10.1016/j.knosys.2024.112823_b35
  article-title: Deep unsupervised learning using nonequilibrium thermodynamics
– ident: 10.1016/j.knosys.2024.112823_b32
  doi: 10.1109/ICCV.2017.361
– ident: 10.1016/j.knosys.2024.112823_b36
  doi: 10.1109/ICCV51070.2023.00875
– volume: 114
  year: 2021
  ident: 10.1016/j.knosys.2024.112823_b8
  article-title: Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2021.107868
– ident: 10.1016/j.knosys.2024.112823_b11
  doi: 10.1109/ICCV48922.2021.01114
– ident: 10.1016/j.knosys.2024.112823_b13
  doi: 10.1109/ICCV48922.2021.01118
– volume: 23
  start-page: 12309
  issue: 11
  year: 2023
  ident: 10.1016/j.knosys.2024.112823_b2
  article-title: Combination of different-granularity beliefs for sensor-based human activity recognition
  publication-title: IEEE Sens. J.
  doi: 10.1109/JSEN.2023.3266609
– start-page: 8821
  year: 2021
  ident: 10.1016/j.knosys.2024.112823_b42
  article-title: Zero-shot text-to-image generation
– volume: vol. 31
  year: 2018
  ident: 10.1016/j.knosys.2024.112823_b45
  article-title: The challenge of realistic music generation: modelling raw audio at scale
– ident: 10.1016/j.knosys.2024.112823_b14
  doi: 10.1007/978-3-030-01228-1_17
– ident: 10.1016/j.knosys.2024.112823_b18
  doi: 10.1109/ICCV.2019.00723
– year: 2023
  ident: 10.1016/j.knosys.2024.112823_b26
  article-title: Human joint kinematics diffusion-refinement for stochastic motion prediction
– volume: vol. 33
  start-page: 8553
  year: 2019
  ident: 10.1016/j.knosys.2024.112823_b31
  article-title: Bihmp-gan: Bidirectional 3d human motion prediction gan
– ident: 10.1016/j.knosys.2024.112823_b40
  doi: 10.1109/CVPR46437.2021.01268
– ident: 10.1016/j.knosys.2024.112823_b53
– ident: 10.1016/j.knosys.2024.112823_b49
– ident: 10.1016/j.knosys.2024.112823_b21
  doi: 10.1109/ICCV51070.2023.00220
– volume: 34
  start-page: 233
  issue: 1
  year: 1963
  ident: 10.1016/j.knosys.2024.112823_b48
  article-title: Collapsed Markov chains and the Chapman-Kolmogorov equation
  publication-title: Ann. Math. Stat.
  doi: 10.1214/aoms/1177704261
– volume: 39
  issue: 4
  year: 2020
  ident: 10.1016/j.knosys.2024.112823_b19
  article-title: Character controllers using motion vaes
  publication-title: ACM Trans. Graph.
  doi: 10.1145/3386569.3392422
– volume: vol. 34
  start-page: 12281
  year: 2020
  ident: 10.1016/j.knosys.2024.112823_b17
  article-title: Learning diverse stochastic human-action generators by learning smooth latent transitions
– volume: 284
  year: 2024
  ident: 10.1016/j.knosys.2024.112823_b30
  article-title: Global disentangled graph convolutional neural network based on a graph topological metric
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2023.111283
– ident: 10.1016/j.knosys.2024.112823_b27
  doi: 10.1007/978-3-030-58545-7_20
– year: 2023
  ident: 10.1016/j.knosys.2024.112823_b1
  article-title: Graph-structure-based multigranular belief fusion for human activity recognition
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 1050
  start-page: 1
  year: 2014
  ident: 10.1016/j.knosys.2024.112823_b33
  article-title: Auto-encoding variational Bayes
  publication-title: Stat
– volume: 29
  start-page: 3607
  issue: 12
  year: 2021
  ident: 10.1016/j.knosys.2024.112823_b10
  article-title: Evidential reasoning with hesitant fuzzy belief structures for human activity recognition
  publication-title: IEEE Trans. Fuzzy Syst.
  doi: 10.1109/TFUZZ.2021.3079495
– year: 2024
  ident: 10.1016/j.knosys.2024.112823_b25
  article-title: Motiondiffuse: Text-driven human motion generation with diffusion model
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 11467
  year: 2021
  ident: 10.1016/j.knosys.2024.112823_b60
  article-title: MSR-gcn: Multi-scale residual graph convolution networks for human motion prediction
– ident: 10.1016/j.knosys.2024.112823_b46
– ident: 10.1016/j.knosys.2024.112823_b56
  doi: 10.1109/CVPR.2017.525
SSID ssj0002218
Score 2.4270732
Snippet Human motion prediction is a fundamental task in computer vision, aiming to forecast future human poses based on observed motion sequences. Existing...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 112823
SubjectTerms Conditional diffusion model
Human motion prediction
Vector quantized variational autoencoder
Title Stochastic human motion prediction using a quantized conditional diffusion model
URI https://dx.doi.org/10.1016/j.knosys.2024.112823
Volume 309
WOSCitedRecordID wos001385489600001&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: PRVESC
  databaseName: ScienceDirect Freedom Collection 2021
  issn: 0950-7051
  databaseCode: AIEXJ
  dateStart: 19950201
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0002218
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELbahUMvfUBRoQ_50KvRxnbW9pFWVLSVEFJB2lvktR0RirKUzVaIX8_4lSwF0XLoJYoi23nMl_F4PDMfQh-VY7wsWUlAKwrCtXREFjWcFZYBPCToTRvIJsThoZxO1VEKCVoEOgHRtvLqSl38V1HDNRC2T519hLj7QeECnIPQ4Qhih-M_Cf5HNzen2pdfTgR8kajHVwOwTSQGXwYHgfYZlW3XXDuf2ea3rqNb0HOmLL0TLdLkrJqv37MHjvjZz6Y60IsBG8n7_KnR82vviu7jfULQwNTXZhwax-1-6FO75nbDA_crT6nJI0F98F_eXMmuxTER41RINmlZNlYrehKsPBnzjO-o8OhNONv92c7hJWAFT_nu0Px2xew_ZrI-vjCHrp1VcZTKj1LFUZ6iNSpKJUdobe_r_vRbP29TGrzB_dPnRMsQDXj3ae43ZFaMk-OX6HlaVeC9iIZX6IlrN9CLzNiBkwLfREcDOHAAB47gwAM4cAAH1rgHB14BB-7BgQM4XqOTL_vHnw9I4tQgBhaHHXHjyYxJy7jhtatnhYGf0cGS3Wmuaq2Mm5liIh2l1hSFpnzCbFlbUXMwcwtjBNtCo3beujcIG1iplmDb0NLOuFXOJzFrW9RWaSmoVtuI5Q9UmVRw3vOenFcPiWcbkb7XRSy48pf2In_7KhmN0RisAFAP9tx55J3eomcD2t-hUXe5dO_RuvndNYvLDwlNN6H-kg4
linkProvider Elsevier
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=Stochastic+human+motion+prediction+using+a+quantized+conditional+diffusion+model&rft.jtitle=Knowledge-based+systems&rft.au=Huang%2C+Biaozhang&rft.au=Li%2C+Xinde&rft.au=Hu%2C+Chuanfei&rft.au=Li%2C+Heqing&rft.date=2025-01-30&rft.issn=0950-7051&rft.volume=309&rft.spage=112823&rft_id=info:doi/10.1016%2Fj.knosys.2024.112823&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_knosys_2024_112823
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon