CSR: Cascade Conditional Variational Auto Encoder with Socially-aware Regression for Pedestrian Trajectory Prediction

•The proposed trajectory prediction method consists of a cascaded CVAE module and a socially aware regression module.•The cascaded CVAE module decouples and balances the loss function with respect to time steps and minimizes the losses at every time steps independently.•The socially aware regression...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Pattern recognition Jg. 133; S. 109030
Hauptverfasser: Zhou, Hao, Ren, Dongchun, Yang, Xu, Fan, Mingyu, Huang, Hai
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.01.2023
Schlagworte:
ISSN:0031-3203, 1873-5142
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •The proposed trajectory prediction method consists of a cascaded CVAE module and a socially aware regression module.•The cascaded CVAE module decouples and balances the loss function with respect to time steps and minimizes the losses at every time steps independently.•The socially aware regression module corrects the predictions by checking the compatibility between the interaction coding and the crude predicted trajectories. Pedestrian trajectory prediction is a key technology in many real applications such as video surveillance, social robot navigation, and autonomous driving, and significant progress has been made in this research topic. However, there remain two limitations of previous studies. First, the losses of the last time steps are heavier weighted than that of the beginning time steps in the objective function at the learning stage, causing the prediction errors generated at the beginning to accumulate to large errors at the last time steps at the inference stage. Second, the prediction results of multiple pedestrians in the prediction horizon might be socially incompatible with the interactions modeled by past trajectories. To overcome these limitations, this work proposes a novel trajectory prediction method called CSR, which consists of a cascaded conditional variational autoencoder (CVAE) module and a socially-aware regression module. The CVAE module estimates the future trajectories in a cascaded sequential manner. Specifically, each CVAE concatenates the past trajectories and the predicted location points so far as the input and predicts the adjacent location at the following time step. The socially-aware regression module generates offsets from the estimated future trajectories to produce the corrected predictions, which are more reasonable and accurate than the estimated trajectories. Experiments results demonstrate that the proposed method exhibits significant improvements over state-of-the-art methods on the Stanford Drone Dataset (SDD) and the ETH/UCY dataset of approximately 38.0% and 22.2%, respectively. The code is available at https://github.com/zhouhao94/CSR.
AbstractList •The proposed trajectory prediction method consists of a cascaded CVAE module and a socially aware regression module.•The cascaded CVAE module decouples and balances the loss function with respect to time steps and minimizes the losses at every time steps independently.•The socially aware regression module corrects the predictions by checking the compatibility between the interaction coding and the crude predicted trajectories. Pedestrian trajectory prediction is a key technology in many real applications such as video surveillance, social robot navigation, and autonomous driving, and significant progress has been made in this research topic. However, there remain two limitations of previous studies. First, the losses of the last time steps are heavier weighted than that of the beginning time steps in the objective function at the learning stage, causing the prediction errors generated at the beginning to accumulate to large errors at the last time steps at the inference stage. Second, the prediction results of multiple pedestrians in the prediction horizon might be socially incompatible with the interactions modeled by past trajectories. To overcome these limitations, this work proposes a novel trajectory prediction method called CSR, which consists of a cascaded conditional variational autoencoder (CVAE) module and a socially-aware regression module. The CVAE module estimates the future trajectories in a cascaded sequential manner. Specifically, each CVAE concatenates the past trajectories and the predicted location points so far as the input and predicts the adjacent location at the following time step. The socially-aware regression module generates offsets from the estimated future trajectories to produce the corrected predictions, which are more reasonable and accurate than the estimated trajectories. Experiments results demonstrate that the proposed method exhibits significant improvements over state-of-the-art methods on the Stanford Drone Dataset (SDD) and the ETH/UCY dataset of approximately 38.0% and 22.2%, respectively. The code is available at https://github.com/zhouhao94/CSR.
ArticleNumber 109030
Author Yang, Xu
Zhou, Hao
Ren, Dongchun
Huang, Hai
Fan, Mingyu
Author_xml – sequence: 1
  givenname: Hao
  surname: Zhou
  fullname: Zhou, Hao
  organization: National Key Laboratory of Science and Technology of Underwater Vehicle, Harbin Engineering University, Harbin, China
– sequence: 2
  givenname: Dongchun
  surname: Ren
  fullname: Ren, Dongchun
  organization: Research Center for Autonomous Vehicles, Meituan, Beijing, China
– sequence: 3
  givenname: Xu
  orcidid: 0000-0003-0553-4581
  surname: Yang
  fullname: Yang, Xu
  organization: State Key Laboratory of Management and Control for Complex System, Institute of Automation, Chinese Academy of Sciences, Beijing, China
– sequence: 4
  givenname: Mingyu
  orcidid: 0000-0002-0492-4708
  surname: Fan
  fullname: Fan, Mingyu
  email: fanmingyu@wzu.edu.cn
  organization: Research Center for Autonomous Vehicles, Meituan, Beijing, China
– sequence: 5
  givenname: Hai
  surname: Huang
  fullname: Huang, Hai
  email: haihus@163.com
  organization: National Key Laboratory of Science and Technology of Underwater Vehicle, Harbin Engineering University, Harbin, China
BookMark eNqFkE1LAzEQhoMoWD_-gYf8ga2TZLfbehBkqR8gWNrqNcwms5qybiRJLf33bq0nD3qaYWaeF-Y5YYed74ixCwFDAWJ0uRp-YDL-dShByn40AQUHbCDGpcoKkctDNgBQIlMS1DE7iXEFIMp-MWDrajG_4hVGg5Z45TvrkvMdtvwFg8Of_madPJ92xlsKfOPSG19447BttxluMBCf02ugGPtr3vjAZ2Qppp7v-DLgikzyYctngawzu8gzdtRgG-n8p56y59vpsrrPHp_uHqqbx8woGKWsIbJ1nU9GghBE09g6x7JsCoCcmholjsdYWAtQSgW1GuU5KWFKWYxLYWQ9Uacs3-ea4GMM1OiP4N4xbLUAvVOnV3qvTu_U6b26Hrv6hRmXvl2kgK79D77ew9Q_9uko6Ggcdab_PfQitPXu74AvboyQ2A
CitedBy_id crossref_primary_10_1016_j_eswa_2025_126557
crossref_primary_10_1016_j_isprsjprs_2023_10_001
crossref_primary_10_1016_j_patcog_2022_109293
crossref_primary_10_1016_j_patcog_2025_111667
crossref_primary_10_1016_j_patcog_2025_112315
crossref_primary_10_3390_robotics13010001
crossref_primary_10_1080_15568318_2025_2510413
crossref_primary_10_1016_j_patcog_2023_109592
crossref_primary_10_1016_j_patcog_2025_111847
crossref_primary_10_1109_TIM_2024_3472774
crossref_primary_10_3390_app15084285
crossref_primary_10_7717_peerj_cs_2842
crossref_primary_10_1016_j_neucom_2023_127117
crossref_primary_10_1016_j_knosys_2025_114266
Cites_doi 10.7551/mitpress/3206.001.0001
10.1016/j.patcog.2019.04.025
10.1162/neco.1997.9.8.1735
10.1016/j.patcog.2020.107800
10.20485/jsaeijae.7.AVEC14_53
10.1109/TITS.2008.2011691
10.1016/j.patcog.2021.108252
10.1109/LRA.2018.2852793
10.1016/j.neucom.2021.03.024
10.1109/TPAMI.2020.3038217
ContentType Journal Article
Copyright 2022
Copyright_xml – notice: 2022
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2022.109030
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-5142
ExternalDocumentID 10_1016_j_patcog_2022_109030
S0031320322005106
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-feedbb4961ea01ffdb4a77f5004efba2a88a5dd007230b3644e31c725871c2b93
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000861386400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Sat Nov 29 07:29:00 EST 2025
Tue Nov 18 22:17:21 EST 2025
Fri Feb 23 02:39:44 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords 99-00
Pedestrian trajectory prediction
Conditional variational autoencoder (CVAE)
Socially-aware model
11-01
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-feedbb4961ea01ffdb4a77f5004efba2a88a5dd007230b3644e31c725871c2b93
ORCID 0000-0003-0553-4581
0000-0002-0492-4708
ParticipantIDs crossref_primary_10_1016_j_patcog_2022_109030
crossref_citationtrail_10_1016_j_patcog_2022_109030
elsevier_sciencedirect_doi_10_1016_j_patcog_2022_109030
PublicationCentury 2000
PublicationDate January 2023
2023-01-00
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: January 2023
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2023
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Pellegrini, Ess, Schindler, Van Gool (bib0007) 2009
Huang, Wang, Pi, Song, Yang (bib0027) 2021; 112
Toledo-Moreo, Zamora-Izquierdo (bib0011) 2009; 10
Mohamed, Qian, Elhoseiny, Claudel (bib0014) 2020
Lerner, Chrysanthou, Lischinski (bib0008) 2007; volume 26
Li, Ma, Tomizuka (bib0041) 2019
Salzmann, Ivanovic, Chakravarty, Pavone (bib0028) 2020
Li, Yang, Tomizuka, Choi (bib0029) 2020; 33
Robicquet, Sadeghian, Alahi, Savarese (bib0006) 2016
Chung, Gulcehre, Cho, Bengio (bib0019) 2014
Lee, Choi, Vernaza, Choy, Torr, Chandraker (bib0038) 2017
Hochreiter, Schmidhuber (bib0018) 1997; 9
Bhattacharyya, Hanselmann, Fritz, Schiele, Straehle (bib0040) 2019
Paszke, Gross, Massa, Lerer, Bradbury, Chanan, Killeen, Lin, Gimelshein, Antiga (bib0036) 2019; 32
Hong, Sapp, Philbin (bib0001) 2019
Raksincharoensak, Hasegawa, Nagai (bib0002) 2016; 7
Mangalam, An, Girase, Malik (bib0031) 2021
Kosaraju, Sadeghian, Martín-Martín, Reid, Rezatofighi, Savarese (bib0035) 2019; 32
Girase, Gang, Malla, Li, Kanehara, Mangalam, Choi (bib0032) 2021
Zhou, Ren, Xia, Fan, Yang, Huang (bib0015) 2021; 445
Li, Ying, Chuah (bib0012) 2019
Liang, Jiang, Niebles, Hauptmann, Fei-Fei (bib0024) 2019
Wong, Xia, Peng, You (bib0033) 2021
Sadeghian, Kosaraju, Gupta, Savarese, Alahi (bib0017) 2018
Sadeghian, Kosaraju, Sadeghian, Hirose, Rezatofighi, Savarese (bib0023) 2019
Zhang, Xue, Zhang, Zheng, Ouyang (bib0025) 2020
Alahi, Goel, Ramanathan, Robicquet, Fei-Fei, Savarese (bib0020) 2016
Liang, Jiang, Hauptmann (bib0039) 2020
Kingma, Ba (bib0037) 2015
Luo, Cai, Bera, Hsu, Lee, Manocha (bib0003) 2018; 3
Gao, Sun, Zhao, Shen, Anguelov, Li, Schmid (bib0013) 2020
Mangalam, Girase, Agarwal, Lee, Adeli, Malik, Gaidon (bib0005) 2020
Deo, Trivedi (bib0034) 2020
C.E. Ramussen, C. Williams, Gaussian processes for machine learning (adaptive computation and machine learning), 2006, (????).
Lefèvre, Laugier, Ibañez Guzmán (bib0009) 2011
Xu, Yang, Du (bib0021) 2020; volume 34
Zhao, Gao, Lan, Sun, Sapp, Varadarajan, Shen, Shen, Chai, Schmid (bib0030) 2020
Pei, Qi, Zhang, Ma, Yang (bib0026) 2019; 93
Gupta, Johnson, Fei-Fei, Savarese, Alahi (bib0022) 2018
Zamboni, Kefato, Girdzijauskas, Norén, Dal Col (bib0016) 2022; 121
Xue, Huynh, Reynolds (bib0004) 2019
Lerner (10.1016/j.patcog.2022.109030_bib0008) 2007; volume 26
Robicquet (10.1016/j.patcog.2022.109030_bib0006) 2016
Salzmann (10.1016/j.patcog.2022.109030_bib0028) 2020
Lee (10.1016/j.patcog.2022.109030_bib0038) 2017
Li (10.1016/j.patcog.2022.109030_bib0012) 2019
Huang (10.1016/j.patcog.2022.109030_sbref0027) 2021; 112
Girase (10.1016/j.patcog.2022.109030_bib0032) 2021
Zhang (10.1016/j.patcog.2022.109030_sbref0025) 2020
Deo (10.1016/j.patcog.2022.109030_bib0034) 2020
Luo (10.1016/j.patcog.2022.109030_bib0003) 2018; 3
Mohamed (10.1016/j.patcog.2022.109030_bib0014) 2020
Zamboni (10.1016/j.patcog.2022.109030_sbref0016) 2022; 121
Lefèvre (10.1016/j.patcog.2022.109030_bib0009) 2011
Zhao (10.1016/j.patcog.2022.109030_bib0030) 2020
Wong (10.1016/j.patcog.2022.109030_bib0033) 2021
Liang (10.1016/j.patcog.2022.109030_bib0039) 2020
Raksincharoensak (10.1016/j.patcog.2022.109030_bib0002) 2016; 7
Toledo-Moreo (10.1016/j.patcog.2022.109030_bib0011) 2009; 10
Gupta (10.1016/j.patcog.2022.109030_bib0022) 2018
Gao (10.1016/j.patcog.2022.109030_bib0013) 2020
Sadeghian (10.1016/j.patcog.2022.109030_bib0017) 2018
Paszke (10.1016/j.patcog.2022.109030_bib0036) 2019; 32
Hochreiter (10.1016/j.patcog.2022.109030_bib0018) 1997; 9
Zhou (10.1016/j.patcog.2022.109030_bib0015) 2021; 445
Mangalam (10.1016/j.patcog.2022.109030_bib0031) 2021
10.1016/j.patcog.2022.109030_bib0010
Pellegrini (10.1016/j.patcog.2022.109030_bib0007) 2009
Chung (10.1016/j.patcog.2022.109030_bib0019) 2014
Alahi (10.1016/j.patcog.2022.109030_bib0020) 2016
Pei (10.1016/j.patcog.2022.109030_bib0026) 2019; 93
Bhattacharyya (10.1016/j.patcog.2022.109030_bib0040) 2019
Xue (10.1016/j.patcog.2022.109030_bib0004) 2019
Li (10.1016/j.patcog.2022.109030_bib0041) 2019
Li (10.1016/j.patcog.2022.109030_bib0029) 2020; 33
Kingma (10.1016/j.patcog.2022.109030_bib0037) 2015
Xu (10.1016/j.patcog.2022.109030_bib0021) 2020; volume 34
Mangalam (10.1016/j.patcog.2022.109030_bib0005) 2020
Liang (10.1016/j.patcog.2022.109030_bib0024) 2019
Kosaraju (10.1016/j.patcog.2022.109030_bib0035) 2019; 32
Hong (10.1016/j.patcog.2022.109030_bib0001) 2019
Sadeghian (10.1016/j.patcog.2022.109030_bib0023) 2019
References_xml – year: 2018
  ident: bib0017
  article-title: Trajnet: towards a benchmark for human trajectory prediction
  publication-title: arXiv preprint
– year: 2020
  ident: bib0030
  article-title: Tnt: target-driven trajectory prediction
  publication-title: arXiv preprint arXiv:2008.08294
– start-page: 961
  year: 2016
  end-page: 971
  ident: bib0020
  article-title: Social lstm: Human trajectory prediction in crowded spaces
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 683
  year: 2020
  end-page: 700
  ident: bib0028
  article-title: Trajectron++: Dynamically-feasible trajectory forecasting with heterogeneous data
  publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVIII 16
– start-page: 5725
  year: 2019
  end-page: 5734
  ident: bib0024
  article-title: Peeking into the future: Predicting future person activities and locations in videos
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– reference: C.E. Ramussen, C. Williams, Gaussian processes for machine learning (adaptive computation and machine learning), 2006, (????).
– start-page: 759
  year: 2020
  end-page: 776
  ident: bib0005
  article-title: It is not the journey but the destination: Endpoint conditioned trajectory prediction
  publication-title: European Conference on Computer Vision
– year: 2019
  ident: bib0001
  article-title: Rules of the road: Predicting driving behavior with a convolutional model of semantic interactions
  publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
– start-page: 15233
  year: 2021
  end-page: 15242
  ident: bib0031
  article-title: From goals, waypoints & paths to long term human trajectory forecasting
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– volume: 445
  start-page: 298
  year: 2021
  end-page: 308
  ident: bib0015
  article-title: Ast-gnn: an attention-based spatio-temporal graph neural network for interaction-aware pedestrian trajectory prediction
  publication-title: Neurocomputing
– year: 2020
  ident: bib0034
  article-title: Trajectory forecasts in unknown environments conditioned on grid-based plans
  publication-title: arXiv preprint arXiv:2001.00735
– volume: 10
  start-page: 180
  year: 2009
  end-page: 185
  ident: bib0011
  article-title: Imm-based lane-change prediction in highways with low-cost gps/ins
  publication-title: IEEE Trans. Intell. Transp. Syst.
– start-page: 11525
  year: 2020
  end-page: 11533
  ident: bib0013
  article-title: Vectornet: Encoding hd maps and agent dynamics from vectorized representation
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 3
  start-page: 3418
  year: 2018
  end-page: 3425
  ident: bib0003
  article-title: Porca: modeling and planning for autonomous driving among many pedestrians
  publication-title: IEEE Rob. Autom. Lett.
– start-page: 14424
  year: 2020
  end-page: 14432
  ident: bib0014
  article-title: Social-stgcnn: A social spatio-temporal graph convolutional neural network for human trajectory prediction
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 6150
  year: 2019
  end-page: 6156
  ident: bib0041
  article-title: Conditional generative neural system for probabilistic trajectory prediction
  publication-title: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
– year: 2019
  ident: bib0040
  article-title: Conditional flow variational autoencoders for structured sequence prediction
  publication-title: 4th Workshop on Bayesian Deep Learning
– volume: 7
  start-page: 53
  year: 2016
  end-page: 60
  ident: bib0002
  article-title: Motion planning and control of autonomous driving intelligence system based on risk potential optimization framework
  publication-title: Int. J. Automot. Eng.
– start-page: 261
  year: 2009
  end-page: 268
  ident: bib0007
  article-title: You’ll never walk alone: Modeling social behavior for multi-target tracking
  publication-title: 2009 IEEE 12th International Conference on Computer Vision
– volume: 112
  start-page: 107800
  year: 2021
  ident: bib0027
  article-title: Lstm based trajectory prediction model for cyclist utilizing multiple interactions with environment
  publication-title: Pattern Recognit.
– start-page: 1349
  year: 2019
  end-page: 1358
  ident: bib0023
  article-title: Sophie: An attentive gan for predicting paths compliant to social and physical constraints
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 336
  year: 2017
  end-page: 345
  ident: bib0038
  article-title: Desire: Distant future prediction in dynamic scenes with interacting agents
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: volume 34
  start-page: 12541
  year: 2020
  end-page: 12548
  ident: bib0021
  article-title: Cf-lstm: Cascaded feature-based long short-term networks for predicting pedestrian trajectory
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: 93
  start-page: 273
  year: 2019
  end-page: 282
  ident: bib0026
  article-title: Human trajectory prediction in crowded scene using social-affinity long short-term memory
  publication-title: Pattern Recognit.
– start-page: 2255
  year: 2018
  end-page: 2264
  ident: bib0022
  article-title: Social gan: Socially acceptable trajectories with generative adversarial networks
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: 32
  start-page: 137
  year: 2019
  end-page: 146
  ident: bib0035
  article-title: Social-biGAT: multimodal trajectory forecasting using bicycle-GAN and graph attention networks
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 583
  year: 2011
  end-page: 588
  ident: bib0009
  article-title: Exploiting map information for driver intention estimation at road intersections
  publication-title: 2011 ieee intelligent vehicles symposium (iv)
– year: 2014
  ident: bib0019
  article-title: Empirical evaluation of gated recurrent neural networks on sequence modeling
  publication-title: NIPS 2014 Workshop on Deep Learning, December 2014
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: bib0018
  article-title: Long short-term memory
  publication-title: Neural Comput.
– volume: 33
  start-page: 19783
  year: 2020
  end-page: 19794
  ident: bib0029
  article-title: Evolvegraph: multi-agent trajectory prediction with dynamic relational reasoning
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 9803
  year: 2021
  end-page: 9812
  ident: bib0032
  article-title: Loki: Long term and key intentions for trajectory prediction
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– year: 2015
  ident: bib0037
  article-title: Adam: A method for stochastic optimization
  publication-title: International Conference on Learning Representations (ICLR)
– start-page: 2038
  year: 2019
  end-page: 2047
  ident: bib0004
  article-title: Location-velocity attention for pedestrian trajectory prediction
  publication-title: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
– start-page: 3960
  year: 2019
  end-page: 3966
  ident: bib0012
  article-title: Grip: Graph-based interaction-aware trajectory prediction
  publication-title: 2019 IEEE Intelligent Transportation Systems Conference (ITSC)
– year: 2021
  ident: bib0033
  article-title: Msn: multi-style network for trajectory prediction
  publication-title: arXiv preprint arXiv:2107.00932
– volume: volume 26
  start-page: 655
  year: 2007
  end-page: 664
  ident: bib0008
  article-title: Crowds by example
  publication-title: Computer graphics forum
– year: 2020
  ident: bib0025
  article-title: Social-aware pedestrian trajectory prediction via states refinement LSTM
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 275
  year: 2020
  end-page: 292
  ident: bib0039
  article-title: Simaug: Learning robust representations from simulation for trajectory prediction
  publication-title: European Conference on Computer Vision
– volume: 121
  start-page: 108252
  year: 2022
  ident: bib0016
  article-title: Pedestrian trajectory prediction with convolutional neural networks
  publication-title: Pattern Recognit.
– volume: 32
  start-page: 8026
  year: 2019
  end-page: 8037
  ident: bib0036
  article-title: Pytorch: an imperative style, high-performance deep learning library
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 549
  year: 2016
  end-page: 565
  ident: bib0006
  article-title: Learning social etiquette: Human trajectory understanding in crowded scenes
  publication-title: European conference on computer vision
– start-page: 683
  year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0028
  article-title: Trajectron++: Dynamically-feasible trajectory forecasting with heterogeneous data
– start-page: 2038
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0004
  article-title: Location-velocity attention for pedestrian trajectory prediction
– ident: 10.1016/j.patcog.2022.109030_bib0010
  doi: 10.7551/mitpress/3206.001.0001
– start-page: 583
  year: 2011
  ident: 10.1016/j.patcog.2022.109030_bib0009
  article-title: Exploiting map information for driver intention estimation at road intersections
– start-page: 336
  year: 2017
  ident: 10.1016/j.patcog.2022.109030_bib0038
  article-title: Desire: Distant future prediction in dynamic scenes with interacting agents
– volume: 93
  start-page: 273
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0026
  article-title: Human trajectory prediction in crowded scene using social-affinity long short-term memory
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2019.04.025
– start-page: 14424
  year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0014
  article-title: Social-stgcnn: A social spatio-temporal graph convolutional neural network for human trajectory prediction
– year: 2014
  ident: 10.1016/j.patcog.2022.109030_bib0019
  article-title: Empirical evaluation of gated recurrent neural networks on sequence modeling
– year: 2018
  ident: 10.1016/j.patcog.2022.109030_bib0017
  article-title: Trajnet: towards a benchmark for human trajectory prediction
  publication-title: arXiv preprint
– volume: 32
  start-page: 8026
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0036
  article-title: Pytorch: an imperative style, high-performance deep learning library
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  ident: 10.1016/j.patcog.2022.109030_bib0018
  article-title: Long short-term memory
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0030
  article-title: Tnt: target-driven trajectory prediction
  publication-title: arXiv preprint arXiv:2008.08294
– volume: volume 34
  start-page: 12541
  year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0021
  article-title: Cf-lstm: Cascaded feature-based long short-term networks for predicting pedestrian trajectory
– volume: 112
  start-page: 107800
  year: 2021
  ident: 10.1016/j.patcog.2022.109030_sbref0027
  article-title: Lstm based trajectory prediction model for cyclist utilizing multiple interactions with environment
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2020.107800
– year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0040
  article-title: Conditional flow variational autoencoders for structured sequence prediction
– start-page: 3960
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0012
  article-title: Grip: Graph-based interaction-aware trajectory prediction
– year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0001
  article-title: Rules of the road: Predicting driving behavior with a convolutional model of semantic interactions
– volume: 7
  start-page: 53
  issue: AVEC14
  year: 2016
  ident: 10.1016/j.patcog.2022.109030_bib0002
  article-title: Motion planning and control of autonomous driving intelligence system based on risk potential optimization framework
  publication-title: Int. J. Automot. Eng.
  doi: 10.20485/jsaeijae.7.AVEC14_53
– start-page: 9803
  year: 2021
  ident: 10.1016/j.patcog.2022.109030_bib0032
  article-title: Loki: Long term and key intentions for trajectory prediction
– volume: 10
  start-page: 180
  issue: 1
  year: 2009
  ident: 10.1016/j.patcog.2022.109030_bib0011
  article-title: Imm-based lane-change prediction in highways with low-cost gps/ins
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2008.2011691
– volume: 121
  start-page: 108252
  year: 2022
  ident: 10.1016/j.patcog.2022.109030_sbref0016
  article-title: Pedestrian trajectory prediction with convolutional neural networks
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2021.108252
– start-page: 759
  year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0005
  article-title: It is not the journey but the destination: Endpoint conditioned trajectory prediction
– volume: volume 26
  start-page: 655
  year: 2007
  ident: 10.1016/j.patcog.2022.109030_bib0008
  article-title: Crowds by example
– start-page: 15233
  year: 2021
  ident: 10.1016/j.patcog.2022.109030_bib0031
  article-title: From goals, waypoints & paths to long term human trajectory forecasting
– year: 2015
  ident: 10.1016/j.patcog.2022.109030_bib0037
  article-title: Adam: A method for stochastic optimization
– volume: 33
  start-page: 19783
  year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0029
  article-title: Evolvegraph: multi-agent trajectory prediction with dynamic relational reasoning
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0034
  article-title: Trajectory forecasts in unknown environments conditioned on grid-based plans
  publication-title: arXiv preprint arXiv:2001.00735
– start-page: 275
  year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0039
  article-title: Simaug: Learning robust representations from simulation for trajectory prediction
– year: 2021
  ident: 10.1016/j.patcog.2022.109030_bib0033
  article-title: Msn: multi-style network for trajectory prediction
  publication-title: arXiv preprint arXiv:2107.00932
– volume: 3
  start-page: 3418
  issue: 4
  year: 2018
  ident: 10.1016/j.patcog.2022.109030_bib0003
  article-title: Porca: modeling and planning for autonomous driving among many pedestrians
  publication-title: IEEE Rob. Autom. Lett.
  doi: 10.1109/LRA.2018.2852793
– start-page: 11525
  year: 2020
  ident: 10.1016/j.patcog.2022.109030_bib0013
  article-title: Vectornet: Encoding hd maps and agent dynamics from vectorized representation
– volume: 445
  start-page: 298
  year: 2021
  ident: 10.1016/j.patcog.2022.109030_bib0015
  article-title: Ast-gnn: an attention-based spatio-temporal graph neural network for interaction-aware pedestrian trajectory prediction
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2021.03.024
– start-page: 1349
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0023
  article-title: Sophie: An attentive gan for predicting paths compliant to social and physical constraints
– volume: 32
  start-page: 137
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0035
  article-title: Social-biGAT: multimodal trajectory forecasting using bicycle-GAN and graph attention networks
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2020
  ident: 10.1016/j.patcog.2022.109030_sbref0025
  article-title: Social-aware pedestrian trajectory prediction via states refinement LSTM
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.3038217
– start-page: 2255
  year: 2018
  ident: 10.1016/j.patcog.2022.109030_bib0022
  article-title: Social gan: Socially acceptable trajectories with generative adversarial networks
– start-page: 261
  year: 2009
  ident: 10.1016/j.patcog.2022.109030_bib0007
  article-title: You’ll never walk alone: Modeling social behavior for multi-target tracking
– start-page: 6150
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0041
  article-title: Conditional generative neural system for probabilistic trajectory prediction
– start-page: 549
  year: 2016
  ident: 10.1016/j.patcog.2022.109030_bib0006
  article-title: Learning social etiquette: Human trajectory understanding in crowded scenes
– start-page: 5725
  year: 2019
  ident: 10.1016/j.patcog.2022.109030_bib0024
  article-title: Peeking into the future: Predicting future person activities and locations in videos
– start-page: 961
  year: 2016
  ident: 10.1016/j.patcog.2022.109030_bib0020
  article-title: Social lstm: Human trajectory prediction in crowded spaces
SSID ssj0017142
Score 2.486584
Snippet •The proposed trajectory prediction method consists of a cascaded CVAE module and a socially aware regression module.•The cascaded CVAE module decouples and...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 109030
SubjectTerms Conditional variational autoencoder (CVAE)
Pedestrian trajectory prediction
Socially-aware model
Title CSR: Cascade Conditional Variational Auto Encoder with Socially-aware Regression for Pedestrian Trajectory Prediction
URI https://dx.doi.org/10.1016/j.patcog.2022.109030
Volume 133
WOSCitedRecordID wos000861386400001&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
  customDbUrl:
  eissn: 1873-5142
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017142
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlgMXWl6ivLQHrq7sXbtec4uiVNBDFZWCAhdrn2miyI7SuLS_gL_NrHf9CEWFHrhYkbXeWJ5vZ2dmv5lB6D2hhmVxKALNInBQRJwFnCgeMGESDTs-jUNZN5tIT0_ZdJpNBoOfTS7M1TItCnZ9na3-q6jhHgjbps7eQ9ztpHADfoPQ4Qpih-s_CX70-cy6-SN-aanvNqVPzX3A7ys4xk3wb1iB1TkubEr72kVjXabu8ibgPywd7EzPHEfWUREnWum6x0dhC6Iv6mB_nV2o5rIVrrdyJ3XRTpso49lJ3Vn_94uyqrc7XrZnPV7zlcVMXlTtyG8-kj2tWoxxz_QvZjdVP1xBaC9c4VUwjQJKQrqlgintKVHLFXWHNbf0uws1LA5XsE-VM3DvCTnshm-X0_5tm2vJhw2vbZG7WXI7S-5meYB2SZpkoB53h5_G05P2QCqNYld43r99k4VZUwVvv82frZye5XK-jx57lwMPHVSeoIEunqK9pp0H9tr9GaoAOR-wxw3u4Qb3cIMtbrDHDba4wdu4wR1uMOAGd7jBHW5wh5vn6Mvx-Hz0MfBdOQIJ7uUmMGBVCVjTR5HmYWSMEjFPU5PAEtRGcMIZ44lStiQ9DQUFe1vTSKYkAddcEpHRF2inKAv9EuHYKCVCJpOImZhpya09yUOuhJFJzOMDRJuvmEtfst52Tlnmd8nwAAXtUytXsuUv49NGQLk3O505mQPq7nzy1T3_6TV61C2JN2hns670W_RQXm3ml-t3HnK_AAZWqH8
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=CSR%3A+Cascade+Conditional+Variational+Auto+Encoder+with+Socially-aware+Regression+for+Pedestrian+Trajectory+Prediction&rft.jtitle=Pattern+recognition&rft.au=Zhou%2C+Hao&rft.au=Ren%2C+Dongchun&rft.au=Yang%2C+Xu&rft.au=Fan%2C+Mingyu&rft.date=2023-01-01&rft.issn=0031-3203&rft.volume=133&rft.spage=109030&rft_id=info:doi/10.1016%2Fj.patcog.2022.109030&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patcog_2022_109030
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon