Emergence of visual saliency from natural scenes via context-mediated probability distributions coding

How do people distribute their attention while observing The Night Watch?

This study explored how people look at The Night Watch (1642), Rembrandt's masterpiece. Twenty-one participants each stood in front of the painting for 5 min, while their eyes were recorded with a mobile eye-tracker and their thoughts were verbalized with a think-aloud method. We computed a heatmap of the participants’ attentional distribution using a novel markerless mapping method. The results showed that the participants’ attention was mainly directed at the faces of the two central figures, the bright mascot girl in the painting, and detailed elements such as the apparel of the key figures. The eye-movement analysis and think-aloud data also showed that participants’ attention shifted from the faces of the key figures to other elements of the scene over the course of the 5 min. Our analyses are consistent with the theory that Rembrandt used light and texture to capture the viewer's attention. Finally, the robustness of the eye-tracking method was demonstrated by replicating the study on a smaller replica.

Multi-scale spatial concatenations of local features in natural scenes and scene classification

How does the visual system encode natural scenes? What are the basic structures of natural scenes? In current models of scene perception, there are two broad feature representations, global and local representations. Both representations are useful and have some successes; however, many observations on human scene perception seem to point to an intermediate-level representation. In this paper, we proposed natural scene structures, i.e., multi-scale spatial concatenations of local features, as an intermediate-level representation of natural scenes. To compile the natural scene structures, we first sampled a large number of multi-scale circular scene patches in a hexagonal configuration. We then performed independent component analysis on the patches and classified the independent components into a set of clusters using the K-means method. Finally, we obtained a set of natural scene structures, each of which is characterized by a set of dominant clusters of independent components. We examined a range of statistics of the natural scene structures, compiled from two widely used datasets of natural scenes, and modeled their spatial arrangements at larger spatial scales using adjacency matrices. We found that the natural scene structures include a full range of concatenations of visual features in natural scenes, and can be used to encode spatial information at various scales. We then selected a set of natural scene structures with high information, and used the occurring frequencies and the eigenvalues of the adjacency matrices to classify scenes in the datasets. We found that the performance of this model is comparable to or better than the state-of-the-art models on the two datasets. These results suggest that the natural scene structures are a useful intermediate-level representation of visual scenes for our understanding of natural scene perception.

Robust action recognition using multi-scale spatial-temporal concatenations of local features as natural action structures

Human and many other animals can detect, recognize, and classify natural actions in a very short time. How this is achieved by the visual system and how to make machines understand natural actions have been the focus of neurobiological studies and computational modeling in the last several decades. A key issue is what spatial-temporal features should be encoded and what the characteristics of their occurrences are in natural actions. Current global encoding schemes depend heavily on segmenting while local encoding schemes lack descriptive power. Here, we propose natural action structures, i.e., multi-size, multi-scale, spatial-temporal concatenations of local features, as the basic features for representing natural actions. In this concept, any action is a spatial-temporal concatenation of a set of natural action structures, which convey a full range of information about natural actions. We took several steps to extract these structures. First, we sampled a large number of sequences of patches at multiple spatial-temporal scales. Second, we performed independent component analysis on the patch sequences and classified the independent components into clusters. Finally, we compiled a large set of natural action structures, with each corresponding to a unique combination of the clusters at the selected spatial-temporal scales. To classify human actions, we used a set of informative natural action structures as inputs to two widely used models. We found that the natural action structures obtained here achieved a significantly better recognition performance than low-level features and that the performance was better than or comparable to the best current models. We also found that the classification performance with natural action structures as features was slightly affected by changes of scale and artificially added noise. We concluded that the natural action structures proposed here can be used as the basic encoding units of actions and may hold the key to natural action understanding.

Eye guidance in natural vision: reinterpreting salience

Models of gaze allocation in complex scenes are derived mainly from studies of static picture viewing. The dominant framework to emerge has been image salience, where properties of the stimulus play a crucial role in guiding the eyes. However, salience-based schemes are poor at accounting for many aspects of picture viewing and can fail dramatically in the context of natural task performance. These failures have led to the development of new models of gaze allocation in scene viewing that address a number of these issues. However, models based on the picture-viewing paradigm are unlikely to generalize to a broader range of experimental contexts, because the stimulus context is limited, and the dynamic, task-driven nature of vision is not represented. We argue that there is a need to move away from this class of model and find the principles that govern gaze allocation in a broader range of settings. We outline the major limitations of salience-based selection schemes and highlight what we have learned from studies of gaze allocation in natural vision. Clear principles of selection are found across many instances of natural vision and these are not the principles that might be expected from picture-viewing studies. We discuss the emerging theoretical framework for gaze allocation on the basis of reward maximization and uncertainty reduction.