Please use this identifier to cite or link to this item: https://doi.org/10.1109/WACV48630.2021.00349
DC FieldValue
dc.titleGraphTCN: Spatio-temporal interaction modeling for human trajectory prediction
dc.contributor.authorWang, C
dc.contributor.authorCai, S
dc.contributor.authorTan, G
dc.date.accessioned2022-06-07T09:11:35Z
dc.date.available2022-06-07T09:11:35Z
dc.date.issued2021-01-01
dc.identifier.citationWang, C, Cai, S, Tan, G (2021-01-01). GraphTCN: Spatio-temporal interaction modeling for human trajectory prediction. Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021 abs/2003.07167 : 3449-3458. ScholarBank@NUS Repository. https://doi.org/10.1109/WACV48630.2021.00349
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/226658
dc.description.abstractPredicting the future paths of an agent's neighbors accurately and in a timely manner is central to the autonomous applications for collision avoidance. Conventional approaches, e.g., LSTM-based models, take considerable computational costs in the prediction, especially for the long sequence prediction. To support more efficient and accurate trajectory predictions, we propose a novel CNN-based spatial-temporal graph framework GraphTCN, which models the spatial interactions as social graphs and captures the spatio-temporal interactions with a modified temporal convolutional network. In contrast to conventional models, both the spatial and temporal modeling of our model are computed within each local time window. Therefore, it can be executed in parallel for much higher efficiency, and meanwhile with accuracy comparable to best-performing approaches. Experimental results confirm that our model achieves better performance in terms of both efficiency and accuracy as compared with state-of-the-art models on various trajectory prediction benchmark datasets.
dc.publisherIEEE
dc.sourceElements
dc.subjectcs.CV
dc.subjectcs.CV
dc.typeArticle
dc.date.updated2022-06-07T08:00:44Z
dc.contributor.departmentCOLLEGE OF ALICE & PETER TAN
dc.contributor.departmentDEPT OF COMPUTER SCIENCE
dc.description.doi10.1109/WACV48630.2021.00349
dc.description.sourcetitleProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
dc.description.volumeabs/2003.07167
dc.description.page3449-3458
dc.published.statePublished
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
2003.07167v6.pdf7.52 MBAdobe PDF

OPEN

Post-printView/Download

SCOPUSTM   
Citations

9
checked on Dec 2, 2022

Page view(s)

50
checked on Dec 1, 2022

Download(s)

2
checked on Dec 1, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.