Almushyti, Muna and Li, Frederick W. B. (2019) 'Recognising human-object interactions using attention-based LSTMs.', in Computer Graphics and Visual Computing (CGVC). , pp. 135-139.
Recognising 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.
|Item Type:||Book chapter|
|Full text:||Publisher-imposed embargo |
(AM) Accepted Manuscript
File format - PDF (882Kb)
|Publisher Web site:||https://doi.org/10.2312/cgvc.20191269|
|Date accepted:||22 July 2019|
|Date deposited:||30 October 2019|
|Date of first online publication:||12 September 2019|
|Date first made open access:||No date available|
Save or Share this output
|Look up in GoogleScholar|