Object Perception as Bayesian Inference. Kersten, D., Mamassian, P., & Yuille, A. Annual Review of Psychology, 55(1):271–304, February, 2004. ![Object Perception as Bayesian Inference [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.
@article{kersten_object_2004,
title = {Object {Perception} as {Bayesian} {Inference}},
volume = {55},
issn = {0066-4308, 1545-2085},
url = {https://www.annualreviews.org/doi/10.1146/annurev.psych.55.090902.142005},
doi = {10/djzsrk},
abstract = {We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.},
language = {en},
number = {1},
urldate = {2023-01-03},
journal = {Annual Review of Psychology},
author = {Kersten, Daniel and Mamassian, Pascal and Yuille, Alan},
month = feb,
year = {2004},
pages = {271--304},
}
Downloads: 0
{"_id":"HEC7YsZgJQBTPF7pF","bibbaseid":"kersten-mamassian-yuille-objectperceptionasbayesianinference-2004","downloads":0,"creationDate":"2015-02-08T05:14:47.878Z","title":"Object Perception as Bayesian Inference","author_short":["Kersten, D.","Mamassian, P.","Yuille, A."],"year":2004,"bibtype":"article","biburl":"https://bibbase.org/zotero/marsicanus","bibdata":{"bibtype":"article","type":"article","title":"Object Perception as Bayesian Inference","volume":"55","issn":"0066-4308, 1545-2085","url":"https://www.annualreviews.org/doi/10.1146/annurev.psych.55.090902.142005","doi":"10/djzsrk","abstract":"We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.","language":"en","number":"1","urldate":"2023-01-03","journal":"Annual Review of Psychology","author":[{"propositions":[],"lastnames":["Kersten"],"firstnames":["Daniel"],"suffixes":[]},{"propositions":[],"lastnames":["Mamassian"],"firstnames":["Pascal"],"suffixes":[]},{"propositions":[],"lastnames":["Yuille"],"firstnames":["Alan"],"suffixes":[]}],"month":"February","year":"2004","pages":"271–304","bibtex":"@article{kersten_object_2004,\n\ttitle = {Object {Perception} as {Bayesian} {Inference}},\n\tvolume = {55},\n\tissn = {0066-4308, 1545-2085},\n\turl = {https://www.annualreviews.org/doi/10.1146/annurev.psych.55.090902.142005},\n\tdoi = {10/djzsrk},\n\tabstract = {We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2023-01-03},\n\tjournal = {Annual Review of Psychology},\n\tauthor = {Kersten, Daniel and Mamassian, Pascal and Yuille, Alan},\n\tmonth = feb,\n\tyear = {2004},\n\tpages = {271--304},\n}\n\n","author_short":["Kersten, D.","Mamassian, P.","Yuille, A."],"key":"kersten_object_2004","id":"kersten_object_2004","bibbaseid":"kersten-mamassian-yuille-objectperceptionasbayesianinference-2004","role":"author","urls":{"Paper":"https://www.annualreviews.org/doi/10.1146/annurev.psych.55.090902.142005"},"metadata":{"authorlinks":{}},"html":""},"search_terms":["object","perception","bayesian","inference","kersten","mamassian","yuille"],"keywords":[],"authorIDs":[],"dataSources":["hEoKh4ygEAWbAZ5iy","MDN92uztrK9rBiHJj"]}