Search

In modeling vision, there has been a remarkable progress in recognizing a range of scene components, but the problem of analyzing full scenes, an ultimate goal of visual perception, is still largely open. To deal with complete scenes, recent work focused on the training of models for extracting the full graph-like structure of a scene. In contrast with scene graphs, humans' scene perception focuses on selected structures in the scene, starting with a limited interpretation and evolving sequentially in a goal-directed manner [G. L. Malcolm, I. I. A. Groen, C. I. Baker, Trends. Cogn. Sci. 20, 843-856 (2016)]. Guidance is crucial throughout scene interpretation since the extraction of full scene representation is often infeasible. Here, we present a model that performs human-like guided scene interpretation, using an iterative bottom-up, top-down processing, in a "counterstream" structure motivated by cortical circuitry. The process proceeds by the sequential application of top-down instructions that guide the interpretation process. The results show how scene structures of interest to the viewer are extracted by an automatically selected sequence of top-down instructions. The model shows two further benefits. One is an inherent capability to deal well with the problem of combinatorial generalization--generalizing broadly to unseen scene configurations, which is limited in current network models [B. Lake, M. Baroni, 35th International Conference on Machine Learning, ICML 2018 (2018)]. The second is the ability to combine visual with nonvisual information at each cycle of the interpretation process, which is a key aspect for modeling human perception as well as advancing AI vision systems. [ABSTRACT FROM AUTHOR]

The goal in this work is to model the process of 'full interpretation' of object images, which is the ability to identify and localize all semantic features and parts that are recognized by human observers. The task is approached by dividing the interpretation of the complete object to the interpretation of multiple reduced but interpretable local regions. In such reduced regions, interpretation is simpler, since the number of semantic components is small, and the variability of possible configurations is low. We model the interpretation process by identifying primitive components and relations that play a useful role in local interpretation by humans. To identify useful components and relations used in the interpretation process, we consider the interpretation of 'minimal configurations': these are reduced local regions, which are minimal in the sense that further reduction renders them unrecognizable and uninterpretable. We show that such minimal interpretable images have useful properties, which we use to identify informative features and relations used for full interpretation. We describe our interpretation model, and show results of detailed interpretations of minimal configurations, produced automatically by the model. Finally, we discuss possible extensions and implications of full interpretation to difficult visual tasks, such as recognizing social interactions, which are beyond the scope of current models of visual recognition. [ABSTRACT FROM AUTHOR]

Discovering the visual features and representations used by the brain to recognize objects is a central problem in the study of vision. Recently, neural network models of visual object recognition, including biological and deep network models, have shown remarkable progress and have begun to rival human performance in some challenging tasks. These models are trained on image examples and learn to extract features and representations and to use them for categorization. It remains unclear, however, whether the representations and learning processes discovered by current models are similar to those used by the human visual system. Here we show, by introducing and using minimal recognizable images, that the human visual system uses features and processes that are not used by current models and that are critical for recognition. We found by psychophysical studies that at the level of minimal recognizable images a minute change in the image can have a drastic effect on recognition, thus identifying features that are critical for the task. Simulations then showed that current models cannot explain this sensitivity to precise feature configurations and, more generally, do not learn to recognize minimal images at a human level. The role of the features shown here is revealed uniquely at theminimal level, where the contribution of each feature is essential. A full understanding of the learning and use of such features will extend our understanding of visual recognition and its cortical mechanisms and will enhance the capacity of computational models to learn from visual experience and to deal with recognition and detailed image interpretation. [ABSTRACT FROM AUTHOR]

The same scene can be depicted by multiple visual media. For example, the same event can be captured by a comic image or a movie frame; the same object can be represented by a photograph or by a 3D computer graphics model. In order to extract the visual analogies that are at the heart of cross-media analysis, spatial matching is required. This matching is commonly achieved by extracting key points and scoring multiple, randomly generated mapping hypotheses. The more consensus a hypothesis can draw, the higher its score. In this paper, we go beyond the conventional set-size measure for the quality of a match and present a more general hypothesis score that attempts to reflect how likely is each hypothesized transformation to be the correct one for the matching task at hand. This is achieved by considering additional, contextual cues for the relevance of a hypothesized transformation. This context changes from one matching task to another and reflects different properties of the match, beyond the size of a consensus set. We demonstrate that by learning how to correctly score each hypothesis based on these features we are able to deal much more robustly with the challenges required to allow cross-media analysis, leading to correct matches where conventional methods fail. [ABSTRACT FROM AUTHOR]

Prominent theories of action recognition suggest that during the recognition of actions the physical patterns of the action is associated with only one action interpretation (e.g., a person waving his arm is recognized as waving). In contrast to this view, studies examining the visual categorization of objects show that objects are recognized in multiple ways (e.g., a VW Beetle can be recognized as a car or a beetle) and that categorization performance is based on the visual and motor movement similarity between objects. Here, we studied whether we find evidence for multiple levels of categorization for social interactions (physical interactions with another person, e.g., handshakes). To do so, we compared visual categorization of objects and social interactions (Experiments 1 and 2) in a grouping task and assessed the usefulness of motor and visual cues (Experiments 3, 4, and 5) for object and social interaction categorization. Additionally, we measured recognition performance associated with recognizing objects and social interactions at different categorization levels (Experiment 6). We found that basic level object categories were associated with a clear recognition advantage compared to subordinate recognition but basic level social interaction categories provided only a little recognition advantage. Moreover, basic level object categories were more strongly associated with similar visual and motor cues than basic level social interaction categories. The results suggest that cognitive categories underlying the recognition of objects and social interactions are associated with different performances. These results are in line with the idea that the same action can be associated with several action interpretations (e.g., a person waving his arm can be recognized as waving or greeting). [ABSTRACT FROM PUBLISHER]