Attention Feature Filters

Introduced by Veluri et al. in NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras

An attention mechanism for content-based filtering of multi-level features. For example, recurrent features obtained by forward and backward passes of a bidirectional RNN block can be combined using attention feature filters, with unprocessed input features/embeddings as queries and recurrent features as keys/values.

Source: NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Colorization	1	20.00%
Key-Frame-based Video Super-Resolution (K = 15)	1	20.00%
Super-Resolution	1	20.00%
Total Energy	1	20.00%
Video Super-Resolution	1	20.00%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Attention Mechanisms