The effects of contextual scenes on the identification of objects

By tephen E. Palmer. 1975

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, background): “Humans facilitate object recognition by learned associations (covariation) and co-occurrences via memories of perceptual interactions that have been experienced (Palmer, 1975; Chun & Jiang, 1998, 1999; Davenport & Potter, 2004; Bonner & Epstein, 2021).”
Humans, but Not Deep Neural Networks, Often Miss Giant Targets in Scenes. (2017, background): “Classic studies have demonstrated that a variety of violations in the relationship between a target and a scene can influence object detection for very briefly presented (150 ms) line drawings in the visual periphery [40, 41].”
A Cortical Mechanism for Triggering Top-Down Facilitation in Visual Object Recognition (2003, background): “To start even earlier than that, top-down processing must use quick mechanisms and partial information (see Palmer, 1975a, for related remarks).”
Object categorization using co-occurrence, location and appearance (2008, background): “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, 2, 3, 11, 17, 28].”
Scene Consistency in Object and Background Perception (2004, background): “Objects are identified more accurately when primed by a semantically consistent scene than when primed by an inconsistent scene (Palmer, 1975).”
Situated simulation in the human conceptual system (2003, background): “First, it supports perception, predicting the entities and events likely to be perceived in a scene, thereby speeding their processing (e.g., Biederman, 1981; Palmer, 1975).”
Contextual cueing: implicit learning and memory of visual context guides spatial attention. (1998, background): “has demonstrated that a coherent, semantically related visual context can facilitate the detection and identification of component objects and events (Biederman, 1972; Biederman, 1981; Biederman, Mezzanotte, & Rabinowitz, 1982; Boyce, Pollatsek, & Rayner, 1989; Friedman, 1979; Loftus & Mackworth, 19”
3D-VLA: A 3D Vision-Language-Action Generative World Model (2024, unknown): “However, they neglect the fact that human beings are situated within a far richer 3D physical world beyond 2D images - they reason, plan, and act based on their 3D understanding of the environment (Palmer, 1975; Pylyshyn, 2003; Marr, 2010).”
Modeling the influence of task on attention. (2005, background): “…(semantic category) of a scene is very useful in determining scene context, and is known to guide eye movements (Biederman, Mezzanotte, & Rabinowitz , 1982; Chun & Jiang, 1998; De Graef, Christiaens , & dÕYdewalle, 1990; Henderson & Hollingworth, 1999; Palmer, 1975; Rensink, 2000; Torralba, 2003).”
Is vision continuous with cognition? The case for cognitive impenetrability of visual perception. (1999, background): “object type is present (see, e.g., Friedman 1979; Palmer 1975), object type discrimination should be better when the target object is consistent versus inconsistent with the scene.”
Spatial Memory for Context Reasoning in Object Detection (2017, background): “Apart from strong psychological evidence [4, 37, 64, 65] that context is vital for humans to recognize objects, many empirical studies in the computer vision community [10, 11, 16, 22, 23, 43, 60, 62, 73, 82, 83] have also suggested that recognition algorithms can be improved by proper modeling of…”
Quantifying the role of context in visual object recognition (2010, background): “Under these conditions, several studies have found a facilitory effect of semantically appropriate contexts (Auckland, Cave, & Donnelly, 2007; Davenport, 2007; Davenport & Potter, 2004; Palmer, 1975).”
Scene perception: detecting and judging objects undergoing relational violations. (1982, background): “(1973), and Palmer (1975), showed that the Probabil i ty relation could readily be accessed f rom a scene, but neither s tudy was designed to directly assess a perceptual effect.”