Walther Dirk, Koch Christof
Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, 405 N. Mathews Ave., Urbana, IL 61801, USA.
Neural Netw. 2006 Nov;19(9):1395-407. doi: 10.1016/j.neunet.2006.10.001.
Selective visual attention is believed to be responsible for serializing visual information for recognizing one object at a time in a complex scene. But how can we attend to objects before they are recognized? In coherence theory of visual cognition, so-called proto-objects form volatile units of visual information that can be accessed by selective attention and subsequently validated as actual objects. We propose a biologically plausible model of forming and attending to proto-objects in natural scenes. We demonstrate that the suggested model can enable a model of object recognition in cortex to expand from recognizing individual objects in isolation to sequentially recognizing all objects in a more complex scene.
选择性视觉注意被认为负责序列化视觉信息，以便在复杂场景中一次识别一个物体。但是，我们如何在物体被识别之前就关注它们呢？在视觉认知的连贯理论中，所谓的原型物体形成了视觉信息的不稳定单元，这些单元可以通过选择性注意来访问，随后被确认为实际物体。我们提出了一个在自然场景中形成和关注原型物体的生物学上合理的模型。我们证明，所提出的模型可以使皮层中的物体识别模型从孤立地识别单个物体扩展到在更复杂的场景中依次识别所有物体。
