QR-kod

Offset-Adjustable Deformable Convolution and Region Proposal Network for Visual Tracking

Spatial information is considered as the key information in many computer vision tasks including visual tracking. We attempt to use spatial information to get essential knowledge of the tracking targets in videos. Adapting to the geometry variations of the objects, the deformable convolutional netwo...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphov: Haoran Wu, Zhiyong Xu, Jianlin Zhang, Ge Jia
Materialtyp: Artigo
Språk:Inglês
Utgiven: IEEE 2019-01-01
Serie:IEEE Access
Ämnen:
Länkar:https://ieeexplore.ieee.org/document/8750812/
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!