FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2103147032> ?p ?o ?g. }

• W2103147032 abstract "Invariant object recognition is a remarkable ability of primates' visual system that its underlying mechanism has constantly been under intense investigations. Computational modeling is a valuable tool toward understanding the processes involved in invariant object recognition. Although recent computational models have shown outstanding performances on challenging image databases, they fail to perform well in image categorization under more complex image variations. Studies have shown that making sparse representation of objects by extracting more informative visual features through a feedforward sweep can lead to higher recognition performances. Here, however, we show that when the complexity of image variations is high, even this approach results in poor performance compared to humans. To assess the performance of models and humans in invariant object recognition tasks, we built a parametrically controlled image database consisting of several object categories varied in different dimensions and levels, rendered from 3D planes. Comparing the performance of several object recognition models with human observers shows that only in low-level image variations the models perform similar to humans in categorization tasks. Furthermore, the results of our behavioral experiments demonstrate that, even under difficult experimental conditions (i.e., briefly presented masked stimuli with complex image variations), human observers performed outstandingly well, suggesting that the models are still far from resembling humans in invariant object recognition. Taken together, we suggest that learning sparse informative visual features, although desirable, is not a complete solution for future progresses in object-vision modeling. We show that this approach is not of significant help in solving the computational crux of object recognition (i.e., invariant object recognition) when the identity-preserving image variations become more complex." @default.
• W2103147032 created "2016-06-24" @default.
• W2103147032 creator A5010085516 @default.
• W2103147032 creator A5018126797 @default.
• W2103147032 creator A5061993462 @default.
• W2103147032 creator A5062614453 @default.
• W2103147032 creator A5081630631 @default.
• W2103147032 date "2014-07-18" @default.
• W2103147032 modified "2023-10-17" @default.
• W2103147032 title "Feedforward object-vision models only tolerate small image variations compared to human" @default.
• W2103147032 cites W1587214067 @default.
• W2103147032 cites W1844800426 @default.
• W2103147032 cites W1963597874 @default.
• W2103147032 cites W1967011375 @default.
• W2103147032 cites W1971017968 @default.
• W2103147032 cites W1972445013 @default.
• W2103147032 cites W1980368669 @default.
• W2103147032 cites W1981794758 @default.
• W2103147032 cites W1987433256 @default.
• W2103147032 cites W1990037101 @default.
• W2103147032 cites W1992480897 @default.
• W2103147032 cites W2000908757 @default.
• W2103147032 cites W2004586880 @default.
• W2103147032 cites W2005202754 @default.
• W2103147032 cites W2011029045 @default.
• W2103147032 cites W2016706073 @default.
• W2103147032 cites W2017108196 @default.
• W2103147032 cites W2022638524 @default.
• W2103147032 cites W2023090292 @default.
• W2103147032 cites W2026369573 @default.
• W2103147032 cites W2026942141 @default.
• W2103147032 cites W2034887640 @default.
• W2103147032 cites W2037090920 @default.
• W2103147032 cites W2038032054 @default.
• W2103147032 cites W2043149073 @default.
• W2103147032 cites W2052139382 @default.
• W2103147032 cites W2057307785 @default.
• W2103147032 cites W2058616551 @default.
• W2103147032 cites W2060487744 @default.
• W2103147032 cites W2060551285 @default.
• W2103147032 cites W2060841692 @default.
• W2103147032 cites W2063951486 @default.
• W2103147032 cites W2079124220 @default.
• W2103147032 cites W2085840637 @default.
• W2103147032 cites W2086396353 @default.
• W2103147032 cites W2089632738 @default.
• W2103147032 cites W2091845343 @default.
• W2103147032 cites W2098580305 @default.
• W2103147032 cites W2103410189 @default.
• W2103147032 cites W2103888644 @default.
• W2103147032 cites W2105464770 @default.
• W2103147032 cites W2109887449 @default.
• W2103147032 cites W2111096131 @default.
• W2103147032 cites W2113291211 @default.
• W2103147032 cites W2113299665 @default.
• W2103147032 cites W2114977008 @default.
• W2103147032 cites W2116360511 @default.
• W2103147032 cites W2117731089 @default.
• W2103147032 cites W2120907531 @default.
• W2103147032 cites W2123544472 @default.
• W2103147032 cites W2125680649 @default.
• W2103147032 cites W2129673518 @default.
• W2103147032 cites W2131470433 @default.
• W2103147032 cites W2132172482 @default.
• W2103147032 cites W2134469260 @default.
• W2103147032 cites W2138692731 @default.
• W2103147032 cites W2144730066 @default.
• W2103147032 cites W2144982973 @default.
• W2103147032 cites W2146246269 @default.
• W2103147032 cites W2146656425 @default.
• W2103147032 cites W2148073157 @default.
• W2103147032 cites W2149194912 @default.
• W2103147032 cites W2150644816 @default.
• W2103147032 cites W2155582136 @default.
• W2103147032 cites W2159940566 @default.
• W2103147032 cites W2160654481 @default.
• W2103147032 cites W2162950292 @default.
• W2103147032 cites W2166130385 @default.
• W2103147032 cites W2168202614 @default.
• W2103147032 cites W2230767397 @default.
• W2103147032 cites W4294214781 @default.
• W2103147032 doi "https://doi.org/10.3389/fncom.2014.00074" @default.
• W2103147032 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/4103258" @default.
• W2103147032 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25100986" @default.
• W2103147032 hasPublicationYear "2014" @default.
• W2103147032 type Work @default.
• W2103147032 sameAs 2103147032 @default.
• W2103147032 citedByCount "29" @default.
• W2103147032 countsByYear W21031470322014 @default.
• W2103147032 countsByYear W21031470322015 @default.
• W2103147032 countsByYear W21031470322016 @default.
• W2103147032 countsByYear W21031470322017 @default.
• W2103147032 countsByYear W21031470322018 @default.
• W2103147032 countsByYear W21031470322019 @default.
• W2103147032 countsByYear W21031470322021 @default.
• W2103147032 countsByYear W21031470322022 @default.
• W2103147032 countsByYear W21031470322023 @default.
• W2103147032 crossrefType "journal-article" @default.
• W2103147032 hasAuthorship W2103147032A5010085516 @default.
• W2103147032 hasAuthorship W2103147032A5018126797 @default.

• next