Recognising Human-Object Interactions Using Attention-based LSTMs

Simple item page
dc.contributor.authorAlmushyti, Munaen_US
dc.contributor.authorLi, Frederick W. B.en_US
dc.contributor.editorVidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.en_US
dc.date.accessioned2019-09-11T05:09:11Z
dc.date.available2019-09-11T05:09:11Z
dc.date.issued2019
dc.description.abstractRecognising Human-object interactions (HOIs) in videos is a challenge task especially when a human can interact with multiple objects. This paper attempts to solve the problem of HOIs by proposing a hierarchical framework that analyzes human-object interactions from a video sequence. The framework consists of LSTMs that firstly capture both human motion and temporal object information independently, followed by fusing these information through a bilinear layer to aggregate human-object features, which are then fed to a global deep LSTM to learn high-level information of HOIs. The proposed approach applies an attention mechanism to LSTMs in order to focus on important parts of human and object temporal information.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationComputer Graphics and Visual Computing (CGVC)
dc.identifier.doi10.2312/cgvc.20191269
dc.identifier.isbn978-3-03868-096-3
dc.identifier.pages135-139
dc.identifier.urihttps://doi.org/10.2312/cgvc.20191269
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/cgvc20191269
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectHuman
dc.subjectobject interactions (HOIs)
dc.subjectLSTM
dc.subjectCNN
dc.subjectHierarchical design
dc.subjectTemporal information
dc.subjectAttention
dc.titleRecognising Human-Object Interactions Using Attention-based LSTMsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
135-139.pdf
Size:
851.99 KB
Format:
Adobe Portable Document Format
Download
Collections
Computer Graphics & Visual Computing (CGVC) 2019