Constructing holistic spatio-temporal scene graph for video semantic role labeling
As one of the core video semantic understanding tasks, Video Semantic Role Labeling
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
Y Zhao, H Fei, Y Cao, B Li, M Zhang, J Wei… - arXiv preprint arXiv …, 2023 - arxiv.org
Video Semantic Role Labeling (VidSRL) aims to detect the salient events from given videos,
by recognizing the predict-argument event structures and the interrelationships between …
by recognizing the predict-argument event structures and the interrelationships between …
Constructing holistic spatio-temporal scene graph for video semantic role labeling
Y ZHAO, H FEI, Y CAO, B LI, M ZHANG, J WEI… - 2023 - ink.library.smu.edu.sg
As one of the core video semantic understanding tasks, Video Semantic Role Labeling
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
Y Zhao, H Fei, Y Cao, B Li, M Zhang, J Wei… - arXiv e …, 2023 - ui.adsabs.harvard.edu
Abstract Video Semantic Role Labeling (VidSRL) aims to detect the salient events from
given videos, by recognizing the predict-argument event structures and the …
given videos, by recognizing the predict-argument event structures and the …
[PDF][PDF] CHUA, Tat-Seng
Y ZHAO, H FEI, Y CAO, B LI, M ZHANG… - … scene graph for …, 2023 - ink.library.smu.edu.sg
Constructing holistic spatio-temporal scene graph for video semantic role labeling Page 1
Singapore Management University Institutional Knowledge at Singapore Management …
Singapore Management University Institutional Knowledge at Singapore Management …