Pilarczyk Joanna, Kuniecki Michał
Psychophysiology Laboratory, Institute of Psychology, Jagiellonian University, Krakow, Poland.
J Vis. 2014 Oct 7;14(12):4. doi: 10.1167/14.12.4.
Emotional images are processed in a prioritized manner, attracting attention almost immediately. In the present study we used eye tracking to reveal what type of features within neutral, positive, and negative images attract early visual attention: semantics, visual saliency, or their interaction. Semantic regions of interest were selected by observers, while visual saliency was determined using the Graph-Based Visual Saliency model. Images were transformed by adding pink noise in several proportions to be presented in a sequence of increasing and decreasing clarity. Locations of the first two fixations were analyzed. The results showed dominance of semantic features over visual saliency in attracting attention. This dominance was linearly related to the signal-to-noise ratio. Semantic regions were fixated more often in emotional images than in neutral ones, if signal-to-noise ratio was high enough to allow participants to comprehend the gist of a scene. Visual saliency on its own did not attract attention above chance, even in the case of pure noise images. Regions both visually salient and semantically relevant attracted a similar amount of fixation compared to semantic regions alone, or even more in the case of neutral pictures. Results provide evidence for fast and robust detection of semantically relevant features.
情绪性图像是以一种优先的方式进行处理的，几乎能立即吸引注意力。在本研究中，我们使用眼动追踪来揭示中性、积极和消极图像中的何种特征会吸引早期视觉注意：语义、视觉显著性，还是它们的相互作用。观察者选择语义感兴趣区域，而视觉显著性则使用基于图的视觉显著性模型来确定。通过按几种比例添加粉红噪声来变换图像，以便在清晰度递增和递减的序列中呈现。分析前两次注视的位置。结果表明，在吸引注意力方面，语义特征比视觉显著性更具优势。这种优势与信噪比呈线性相关。如果信噪比足够高，使参与者能够理解场景的要点，那么情绪性图像中的语义区域比中性图像中的语义区域更常被注视。仅视觉显著性本身并不能吸引高于随机水平的注意力，即使在纯噪声图像的情况下也是如此。与单独的语义区域相比，视觉显著且语义相关的区域吸引的注视量相似，在中性图片的情况下甚至更多。研究结果为语义相关特征的快速且稳健的检测提供了证据。
