The phrase "attention map" is correct and usable in written English.
It is typically used in contexts related to machine learning, computer vision, or neuroscience to refer to a representation that highlights areas of focus or importance in data.
Example: "The attention map generated by the model clearly indicates which parts of the image were most relevant for the classification task."
Alternatives: "focus map" or "saliency map".
Target representation is then stored in the prefrontal cortex, which modulates the feature maps in the search image, and this results in the attention map.
Then a couple, each in a class on one: 4) Andrew's allegorical sound-map, and 5) John's radio-static attention map, if map it could be called; perhaps the most explicit attempt (settings aside) to represent sound by another sound.
However, if the visual attention map is available, it is also possible to substitute this map as the tracking efficiency [51].
A visual attention map is used to infer information about high-impact areas that are used to create stylized rendering with emphasis on the edges used in the composition of the final stylized image.
First, slides of orienteering checkpoints were shown and afterwards participants had to answer questions concerning aspects of short-term memory, focus of attention, map interpretation, estimation or descriptive abilities.
"It knows when your heartbeat or stress level rises and it records with a camera when your brain activity is highest to provide a sort of mood or attention map of your day".
The presented behavior involves an attention mapping mechanism based on 2D and 3D visual cues.
We then propose novel models with different levels of explicit supervision for learning attention maps during training.
But despite their popularity, the "correctness" of the implicitly-learned attention maps has only been assessed qualitatively by visualization of several examples.
We evaluate attention maps generated by state-of-the-art VQA models against human attention both qualitatively (via visualizations) and quantitatively (via rank-order correlation).
We show on the popular Flickr30k and COCO datasets that introducing supervision of attention maps during training solidly improves both attention correctness and caption quality, showing the promise of making machine perception more human-like.
