Hierarchical attentive recurrent tracking
Class-agnostic object tracking is particularly difficult in cluttered environments as target specific discriminative models cannot be learned a priori. Inspired by how the human visual cortex employs spatial attention and separate “where” and “what” processing pathways to actively suppress irrelevan...
Những tác giả chính: | Kosiorek, A, Bewley, A, Posner, H |
---|---|
Định dạng: | Conference item |
Được phát hành: |
Neural Information Processing Systems
2018
|
Những quyển sách tương tự
-
Deep tracking in the wild: End-to-end tracking using recurrent neural networks
Bằng: Dequaire, J, et al.
Được phát hành: (2017) -
End-to-end tracking and semantic segmentation using recurrent neural networks
Bằng: Ondruska, P, et al.
Được phát hành: (2016) -
Attentional control, rumination and recurrence of depression
Bằng: Figueroa, C, et al.
Được phát hành: (2019) -
Neural stethoscopes: Unifying analytic, auxiliary and adversarial network probing
Bằng: Fuchs, F, et al.
Được phát hành: (2018) -
Scrutinizing and de-biasing intuitive physics with neural stethoscopes
Bằng: Fuchs, FB, et al.
Được phát hành: (2019)