Scene perception: detecting and judging objects undergoing relational violations.

By Irving Biederman, R. J. Mezzanotte, J. C. Rabinowitz. 1982

Subfields: Neuroscience, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

Relation Networks for Object Detection (2017, background): “The subsequent approaches [7, 36] try more complex relation models, by taking additional position and size [3] into account.”
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks (2018, background): “Context-based features have a rich history of use in computer vision, motivated by studies in perception that have shown that contextual information influences the accuracy and efficiency of object recognition and detection by humans [2, 13].”
Contextual Action Recognition with R*CNN (2015, background): “[3] identify five classes of relationships (presence, position, size, support and interposition) between an object and its setting and conduct experiments to measure how well humans identify objects when those relationships are violated.”
Contextual Modulation of Target Saliency (2001, background): “Although there is growing evidence of the role of contextual information in human perception [1], research in computational vision is dominated by object-based representations [5,9,10,15].”
Adopting Abstract Images for Semantic Scene Understanding (2016, background): “Interestingly, knowledge of whether or not a person’s gaze is directed towards an object increases the CMI score.”
Symbolic Graph Reasoning Meets Convolutions (2018, background): “As emphasized in [3], visual reasoning over external knowledge is crucial for human decision-making.”
Context based object categorization: A critical survey (2010, unknown): “Information about typical configurations of objects in a scene has been studied in psychology and computer vision for years, in order to understand its effects in visual search, localization and recognition performance [1] [3] [4] [19] [23].”
Actions in context (2009, background): “Visual context has a long history of research with early studies in cognitive science [1].”
How long to get to the “gist” of real-world natural scenes? (2005, background): “Alternatively, many studies have suggested that scene categorization can be performed very efficiently from very brief visual presentations (Biederman et al., 1982; Intraub, 1997; Oliva & Schyns, 1997, 2000; Potter, 1975, 1976; Potter & Levy, 1969; Schyns & Oliva, 1994).”
A similarity measure for analyzing human activities using human-object interaction context (2014, background): “It has been shown that modeling the context of human-object interactions plays an important role in the human visual systems operation [7].”
Quantifying the role of context in visual object recognition (2010, background): “Indeed, a number of these studies used detection paradigms in which the performance measure (d’) explicitly aims to eliminate the possibility of the context providing task-relevant information, which would be factored out as response bias (Biederman et al., 1982; Hollingworth & Henderson, 1998).”
Iterative Visual Reasoning Beyond Convolutions (2018, background): “Unlike humans where visual reasoning about the space and semantics is crucial [1], our current visual systems lack any context reasoning beyond convolutions with large receptive fields.”
VISUAL SALIENCY DOES NOT ACCOUNT FOR EYE MOVEMENTS DURING VISUAL SEARCH IN REAL-WORLD SCENES (2007, background): “A second source of information that can guide gaze is scene schema knowledge, the generic semantic and spatial knowledge about a particular category of scene ( Biederman, Mezzanotte, & Rabinowitz, 1982; Friedman, 1979; Mandler & Johnson, 1977).”