Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100395108> ?p ?o ?g. }
- W3100395108 endingPage "71" @default.
- W3100395108 startingPage "55" @default.
- W3100395108 abstract "Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art." @default.
- W3100395108 created "2020-11-23" @default.
- W3100395108 creator A5022929869 @default.
- W3100395108 creator A5036133390 @default.
- W3100395108 creator A5042087981 @default.
- W3100395108 creator A5063230532 @default.
- W3100395108 creator A5064029620 @default.
- W3100395108 creator A5079112987 @default.
- W3100395108 date "2017-09-11" @default.
- W3100395108 modified "2023-10-18" @default.
- W3100395108 title "Scale coding bag of deep features for human attribute and action recognition" @default.
- W3100395108 cites W1524680991 @default.
- W3100395108 cites W1551774182 @default.
- W3100395108 cites W1606858007 @default.
- W3100395108 cites W1909952827 @default.
- W3100395108 cites W1960777822 @default.
- W3100395108 cites W1966385142 @default.
- W3100395108 cites W1976921161 @default.
- W3100395108 cites W2012592962 @default.
- W3100395108 cites W2014788385 @default.
- W3100395108 cites W2016171122 @default.
- W3100395108 cites W2022735534 @default.
- W3100395108 cites W2031489346 @default.
- W3100395108 cites W2038052836 @default.
- W3100395108 cites W2038765747 @default.
- W3100395108 cites W2048931426 @default.
- W3100395108 cites W2066941820 @default.
- W3100395108 cites W2072477074 @default.
- W3100395108 cites W2076035429 @default.
- W3100395108 cites W2088866137 @default.
- W3100395108 cites W2095288130 @default.
- W3100395108 cites W2102605133 @default.
- W3100395108 cites W2102734144 @default.
- W3100395108 cites W2104657103 @default.
- W3100395108 cites W2109494908 @default.
- W3100395108 cites W2116084929 @default.
- W3100395108 cites W2117103983 @default.
- W3100395108 cites W2117539524 @default.
- W3100395108 cites W2125574651 @default.
- W3100395108 cites W2128560777 @default.
- W3100395108 cites W2129933262 @default.
- W3100395108 cites W2129947832 @default.
- W3100395108 cites W2132068907 @default.
- W3100395108 cites W2139132812 @default.
- W3100395108 cites W2147238549 @default.
- W3100395108 cites W2147414309 @default.
- W3100395108 cites W2151103935 @default.
- W3100395108 cites W2152161678 @default.
- W3100395108 cites W2155490028 @default.
- W3100395108 cites W2161381512 @default.
- W3100395108 cites W2161969291 @default.
- W3100395108 cites W2162762921 @default.
- W3100395108 cites W2167146493 @default.
- W3100395108 cites W2169852119 @default.
- W3100395108 cites W2171896402 @default.
- W3100395108 cites W2172188317 @default.
- W3100395108 cites W2244122599 @default.
- W3100395108 cites W2519653692 @default.
- W3100395108 cites W2534457893 @default.
- W3100395108 cites W2538008885 @default.
- W3100395108 cites W2963173190 @default.
- W3100395108 cites W300523764 @default.
- W3100395108 cites W3104752576 @default.
- W3100395108 cites W33977162 @default.
- W3100395108 doi "https://doi.org/10.1007/s00138-017-0871-1" @default.
- W3100395108 hasPublicationYear "2017" @default.
- W3100395108 type Work @default.
- W3100395108 sameAs 3100395108 @default.
- W3100395108 citedByCount "23" @default.
- W3100395108 countsByYear W31003951082018 @default.
- W3100395108 countsByYear W31003951082019 @default.
- W3100395108 countsByYear W31003951082020 @default.
- W3100395108 countsByYear W31003951082021 @default.
- W3100395108 countsByYear W31003951082022 @default.
- W3100395108 countsByYear W31003951082023 @default.
- W3100395108 crossrefType "journal-article" @default.
- W3100395108 hasAuthorship W3100395108A5022929869 @default.
- W3100395108 hasAuthorship W3100395108A5036133390 @default.
- W3100395108 hasAuthorship W3100395108A5042087981 @default.
- W3100395108 hasAuthorship W3100395108A5063230532 @default.
- W3100395108 hasAuthorship W3100395108A5064029620 @default.
- W3100395108 hasAuthorship W3100395108A5079112987 @default.
- W3100395108 hasBestOaLocation W31003951081 @default.
- W3100395108 hasConcept C104317684 @default.
- W3100395108 hasConcept C105795698 @default.
- W3100395108 hasConcept C108583219 @default.
- W3100395108 hasConcept C115961682 @default.
- W3100395108 hasConcept C153180895 @default.
- W3100395108 hasConcept C154945302 @default.
- W3100395108 hasConcept C1667742 @default.
- W3100395108 hasConcept C167611913 @default.
- W3100395108 hasConcept C179518139 @default.
- W3100395108 hasConcept C185592680 @default.
- W3100395108 hasConcept C189391414 @default.
- W3100395108 hasConcept C199360897 @default.
- W3100395108 hasConcept C205649164 @default.
- W3100395108 hasConcept C2778755073 @default.
- W3100395108 hasConcept C33923547 @default.