FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1567302070> ?p ?o ?g. }

• W1567302070 endingPage "1907" @default.
• W1567302070 startingPage "1901" @default.
• W1567302070 abstract "Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still remains an open problem, mainly due to the complex underlying object layouts and insufficient multi-label training images. In this work, we propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Some unique characteristics of this flexible deep CNN infrastructure include: 1) no ground-truth bounding box information is required for training; 2) the whole HCP infrastructure is robust to possibly noisy and/or redundant hypotheses; 3) the shared CNN is flexible and can be well pre-trained with a large-scale single-label image dataset, e.g., ImageNet; and 4) it may naturally output multi-label prediction results. Experimental results on Pascal VOC 2007 and VOC 2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts. In particular, the mAP reaches 90.5% by HCP only and 93.2% after the fusion with our complementary result in [12] based on hand-crafted features on the VOC 2012 dataset." @default.
• W1567302070 created "2016-06-24" @default.
• W1567302070 creator A5008141914 @default.
• W1567302070 creator A5008961324 @default.
• W1567302070 creator A5013673544 @default.
• W1567302070 creator A5014362734 @default.
• W1567302070 creator A5028127027 @default.
• W1567302070 creator A5039765869 @default.
• W1567302070 creator A5047929313 @default.
• W1567302070 creator A5087043856 @default.
• W1567302070 date "2016-09-01" @default.
• W1567302070 modified "2023-10-18" @default.
• W1567302070 title "HCP: A Flexible CNN Framework for Multi-Label Image Classification" @default.
• W1567302070 cites W1524680991 @default.
• W1567302070 cites W1606858007 @default.
• W1567302070 cites W1849277567 @default.
• W1567302070 cites W1950136256 @default.
• W1567302070 cites W1991367009 @default.
• W1567302070 cites W2010181071 @default.
• W1567302070 cites W2027922120 @default.
• W1567302070 cites W2031489346 @default.
• W1567302070 cites W2046382188 @default.
• W1567302070 cites W2048335335 @default.
• W1567302070 cites W2062118960 @default.
• W1567302070 cites W2066624635 @default.
• W1567302070 cites W2066650804 @default.
• W1567302070 cites W2072238386 @default.
• W1567302070 cites W2088049833 @default.
• W1567302070 cites W2097117768 @default.
• W1567302070 cites W2102605133 @default.
• W1567302070 cites W2108598243 @default.
• W1567302070 cites W2121947440 @default.
• W1567302070 cites W2127194945 @default.
• W1567302070 cites W2130325614 @default.
• W1567302070 cites W2134557905 @default.
• W1567302070 cites W2151103935 @default.
• W1567302070 cites W2153635508 @default.
• W1567302070 cites W2161381512 @default.
• W1567302070 cites W2162915993 @default.
• W1567302070 cites W2166049352 @default.
• W1567302070 cites W2179352600 @default.
• W1567302070 cites W2534457893 @default.
• W1567302070 cites W2546302380 @default.
• W1567302070 cites W2618530766 @default.
• W1567302070 cites W2911964244 @default.
• W1567302070 cites W2963173190 @default.
• W1567302070 cites W7746136 @default.
• W1567302070 doi "https://doi.org/10.1109/tpami.2015.2491929" @default.
• W1567302070 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26513778" @default.
• W1567302070 hasPublicationYear "2016" @default.
• W1567302070 type Work @default.
• W1567302070 sameAs 1567302070 @default.
• W1567302070 citedByCount "519" @default.
• W1567302070 countsByYear W15673020702014 @default.
• W1567302070 countsByYear W15673020702015 @default.
• W1567302070 countsByYear W15673020702016 @default.
• W1567302070 countsByYear W15673020702017 @default.
• W1567302070 countsByYear W15673020702018 @default.
• W1567302070 countsByYear W15673020702019 @default.
• W1567302070 countsByYear W15673020702020 @default.
• W1567302070 countsByYear W15673020702021 @default.
• W1567302070 countsByYear W15673020702022 @default.
• W1567302070 countsByYear W15673020702023 @default.
• W1567302070 crossrefType "journal-article" @default.
• W1567302070 hasAuthorship W1567302070A5008141914 @default.
• W1567302070 hasAuthorship W1567302070A5008961324 @default.
• W1567302070 hasAuthorship W1567302070A5013673544 @default.
• W1567302070 hasAuthorship W1567302070A5014362734 @default.
• W1567302070 hasAuthorship W1567302070A5028127027 @default.
• W1567302070 hasAuthorship W1567302070A5039765869 @default.
• W1567302070 hasAuthorship W1567302070A5047929313 @default.
• W1567302070 hasAuthorship W1567302070A5087043856 @default.
• W1567302070 hasBestOaLocation W15673020702 @default.
• W1567302070 hasConcept C108583219 @default.
• W1567302070 hasConcept C115961682 @default.
• W1567302070 hasConcept C119857082 @default.
• W1567302070 hasConcept C146849305 @default.
• W1567302070 hasConcept C147037132 @default.
• W1567302070 hasConcept C153180895 @default.
• W1567302070 hasConcept C154945302 @default.
• W1567302070 hasConcept C199360897 @default.
• W1567302070 hasConcept C2984842247 @default.
• W1567302070 hasConcept C41008148 @default.
• W1567302070 hasConcept C63584917 @default.
• W1567302070 hasConcept C70437156 @default.
• W1567302070 hasConcept C75294576 @default.
• W1567302070 hasConcept C75608658 @default.
• W1567302070 hasConcept C81363708 @default.
• W1567302070 hasConceptScore W1567302070C108583219 @default.
• W1567302070 hasConceptScore W1567302070C115961682 @default.
• W1567302070 hasConceptScore W1567302070C119857082 @default.
• W1567302070 hasConceptScore W1567302070C146849305 @default.
• W1567302070 hasConceptScore W1567302070C147037132 @default.
• W1567302070 hasConceptScore W1567302070C153180895 @default.
• W1567302070 hasConceptScore W1567302070C154945302 @default.
• W1567302070 hasConceptScore W1567302070C199360897 @default.
• W1567302070 hasConceptScore W1567302070C2984842247 @default.
• W1567302070 hasConceptScore W1567302070C41008148 @default.

• next