Low-level Visual Attributes
Basic visual features in an image that do not depend on semantic recognition, including color, brightness, contrast, texture, edges, and spatial frequency. They stand in contrast to holistic semantic associations.
Timeline (last 90 days)
In the PixCC dataset, humans showed a strategy shift: from holistic semantic association to describing low-level visual attributes (such as color and texture), whereas MLLMs tended to adhere to semantic-level association.
Low-level visual attributes refer to basic features in an image that do not depend on semantic recognition, including color, brightness, contrast, texture, edges, and spatial frequency.
Under noise interference, high-level semantic features are damaged first, while low-level features can still be extracted; humans can proactively shift attention from the semantic level to the perceptual level, which is a manifestation of cognitive flexibility in coping with visual uncertainty.
All Facts (3)
In the PixCC dataset, humans showed a strategy shift: from holistic semantic association to describing low-level visual attributes (such as color and texture), whereas MLLMs tended to adhere to semantic-level association.
50%UnverifiedLow-level visual attributes refer to basic features in an image that do not depend on semantic recognition, including color, brightness, contrast, texture, edges, and spatial frequency.
50%UnverifiedUnder noise interference, high-level semantic features are damaged first, while low-level features can still be extracted; humans can proactively shift attention from the semantic level to the perceptual level, which is a manifestation of cognitive flexibility in coping with visual uncertainty.
50%