Matches in SemOpenAlex for { <https://semopenalex.org/work/W2067570568> ?p ?o ?g. }
- W2067570568 endingPage "972" @default.
- W2067570568 startingPage "945" @default.
- W2067570568 abstract "Neurobiological data from the cerebral cortex of the macaque monkey suggest a model of object recognition that is a series of four computational stages. These are executed in seven major hierarchically arranged areas of processing, each area with an input and an output layer of cells. The first computational stage occurs within early visual cortex and involves the first two cortical areas. Here it appears that boundaries between image regions and logical groupings of local oriented image elements that “belong” together are computed. These processes segregate image attributes that can then be treated as arising from the same object. The next three visual cortical areas execute the second computational stage and display sensitivity to an ever increasing complexity and variety of visual shape features (e.g., T junctions, concentric rings, spotted triangle shape). The third stage of processing seems to utilize combinations of these shape features to establish selectivity to what we refer to as object-feature instances (i.e., the approximate appearance of a small number of object attributes seen under particular viewing conditions). Cells in these areas tolerate change in position but show only limited generalization for change in retinal size, orientation, or perspective view. The fourth computational process occurs within the final cortical areas and gives rise to cell selectivity showing object constancy across size and orientation. This process probably occurs through pooling of the outputs of cells responsive to different instances of the same object view. Importantly, constancy across perspective view (i.e., the transition between viewer-centred and object-centred representation) does not seem to be completed except by a small percentage of cells. Synaptic changes encompassing various associative (e.g., Hebbian) and non-associative (e.g., decorrelating) procedures may allow cells throughout the stages of processing to become tuned to frequently experienced image attributes, shapes, and objects. Associative learning procedures operating over short time periods may underlie the progressive generalization over changing viewing conditions. Constancy across position, orientation, size, and, finally, perspective view and object parts is established slowly as each area pools the appropriate outputs of the less specific cells in the preceding area. After such learning procedures, the visual system can operate to resolve the appearance of unexpected objects primarily in a feedforward manner, without the need for lateral inhibition or feedback loops, a property few models embody. This feedforward processing does not deny the possibility that top-down influences, although poorly understood, may play a role in nulling image aspects that are predictable in appearance and/or not the object of attention such that only features containing relevant discriminatory information are processed further." @default.
- W2067570568 created "2016-06-24" @default.
- W2067570568 creator A5038083093 @default.
- W2067570568 creator A5067081616 @default.
- W2067570568 date "1994-01-01" @default.
- W2067570568 modified "2023-09-27" @default.
- W2067570568 title "Modeling visual recognition from neurobiological constraints" @default.
- W2067570568 cites W111819287 @default.
- W2067570568 cites W1422705218 @default.
- W2067570568 cites W1526492552 @default.
- W2067570568 cites W1529973897 @default.
- W2067570568 cites W1535510227 @default.
- W2067570568 cites W1565561704 @default.
- W2067570568 cites W1565688840 @default.
- W2067570568 cites W1574974356 @default.
- W2067570568 cites W1585281952 @default.
- W2067570568 cites W1609956528 @default.
- W2067570568 cites W1619416921 @default.
- W2067570568 cites W162615862 @default.
- W2067570568 cites W1671528879 @default.
- W2067570568 cites W1763512962 @default.
- W2067570568 cites W1810979160 @default.
- W2067570568 cites W1821977603 @default.
- W2067570568 cites W1831238016 @default.
- W2067570568 cites W1853938811 @default.
- W2067570568 cites W1869259979 @default.
- W2067570568 cites W1892030233 @default.
- W2067570568 cites W1901661521 @default.
- W2067570568 cites W1935489410 @default.
- W2067570568 cites W1951259116 @default.
- W2067570568 cites W1964173056 @default.
- W2067570568 cites W1964958617 @default.
- W2067570568 cites W1967087917 @default.
- W2067570568 cites W1969982193 @default.
- W2067570568 cites W1972079284 @default.
- W2067570568 cites W1974738414 @default.
- W2067570568 cites W1975700187 @default.
- W2067570568 cites W1976048712 @default.
- W2067570568 cites W1977092534 @default.
- W2067570568 cites W1978052431 @default.
- W2067570568 cites W1979493286 @default.
- W2067570568 cites W1984214648 @default.
- W2067570568 cites W1986898623 @default.
- W2067570568 cites W1989770516 @default.
- W2067570568 cites W1991083066 @default.
- W2067570568 cites W1992084645 @default.
- W2067570568 cites W1992914861 @default.
- W2067570568 cites W1993236244 @default.
- W2067570568 cites W1997037178 @default.
- W2067570568 cites W1997801654 @default.
- W2067570568 cites W1999599673 @default.
- W2067570568 cites W1999908130 @default.
- W2067570568 cites W2000956876 @default.
- W2067570568 cites W2004544999 @default.
- W2067570568 cites W2004547450 @default.
- W2067570568 cites W2005386795 @default.
- W2067570568 cites W2006208182 @default.
- W2067570568 cites W2009102154 @default.
- W2067570568 cites W2012521891 @default.
- W2067570568 cites W2013128811 @default.
- W2067570568 cites W2013239224 @default.
- W2067570568 cites W2016217177 @default.
- W2067570568 cites W2020336912 @default.
- W2067570568 cites W2021706204 @default.
- W2067570568 cites W2023861411 @default.
- W2067570568 cites W2027914108 @default.
- W2067570568 cites W2028585769 @default.
- W2067570568 cites W2034952622 @default.
- W2067570568 cites W2036292818 @default.
- W2067570568 cites W2036968376 @default.
- W2067570568 cites W2038853266 @default.
- W2067570568 cites W2040124307 @default.
- W2067570568 cites W2042201713 @default.
- W2067570568 cites W2042343184 @default.
- W2067570568 cites W2042438889 @default.
- W2067570568 cites W2045609834 @default.
- W2067570568 cites W2047183410 @default.
- W2067570568 cites W2049076553 @default.
- W2067570568 cites W2053144375 @default.
- W2067570568 cites W2054369832 @default.
- W2067570568 cites W2057151444 @default.
- W2067570568 cites W2058251015 @default.
- W2067570568 cites W2064167646 @default.
- W2067570568 cites W2064440086 @default.
- W2067570568 cites W2066730845 @default.
- W2067570568 cites W2067856593 @default.
- W2067570568 cites W2074854285 @default.
- W2067570568 cites W2075496740 @default.
- W2067570568 cites W2076263339 @default.
- W2067570568 cites W2078264053 @default.
- W2067570568 cites W2079948225 @default.
- W2067570568 cites W2080370442 @default.
- W2067570568 cites W2080876520 @default.
- W2067570568 cites W2081388730 @default.
- W2067570568 cites W2082627290 @default.
- W2067570568 cites W2085475905 @default.
- W2067570568 cites W2085989895 @default.
- W2067570568 cites W2091587311 @default.