A trainable 3D interaction space aims to captures the associations between the triplet components and helps model the recognition of multiple triplets in the same frame.
Source: Nwoye et al.
Image source: Nwoye et al.Source: Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets
|🤖 No Components Found||You can add them if they exist; e.g. Mask R-CNN uses RoIAlign|