Matches in SemOpenAlex for { <https://semopenalex.org/work/W2336302573> ?p ?o ?g. }
- W2336302573 abstract "Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positive and hard negative examples enhance the final performance in particular object retrieval with compact codes." @default.
- W2336302573 created "2016-06-24" @default.
- W2336302573 creator A5019409717 @default.
- W2336302573 creator A5038939197 @default.
- W2336302573 creator A5046083819 @default.
- W2336302573 date "2016-04-08" @default.
- W2336302573 modified "2023-09-27" @default.
- W2336302573 title "CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples" @default.
- W2336302573 cites W1524680991 @default.
- W2336302573 cites W1556531089 @default.
- W2336302573 cites W1563795667 @default.
- W2336302573 cites W1565312575 @default.
- W2336302573 cites W1577117850 @default.
- W2336302573 cites W1608697715 @default.
- W2336302573 cites W1686810756 @default.
- W2336302573 cites W1833123814 @default.
- W2336302573 cites W1839408879 @default.
- W2336302573 cites W1908016767 @default.
- W2336302573 cites W1920702274 @default.
- W2336302573 cites W1926837203 @default.
- W2336302573 cites W1949049686 @default.
- W2336302573 cites W1979931042 @default.
- W2336302573 cites W2007477183 @default.
- W2336302573 cites W2023991840 @default.
- W2336302573 cites W2024047694 @default.
- W2336302573 cites W2071027807 @default.
- W2336302573 cites W2076188996 @default.
- W2336302573 cites W2076434944 @default.
- W2336302573 cites W2099443716 @default.
- W2336302573 cites W2099482512 @default.
- W2336302573 cites W2102605133 @default.
- W2336302573 cites W2117539524 @default.
- W2336302573 cites W2131846894 @default.
- W2336302573 cites W2138621090 @default.
- W2336302573 cites W2141362318 @default.
- W2336302573 cites W2143432975 @default.
- W2336302573 cites W2148809531 @default.
- W2336302573 cites W2149357475 @default.
- W2336302573 cites W2150307973 @default.
- W2336302573 cites W2151103935 @default.
- W2336302573 cites W2157364932 @default.
- W2336302573 cites W2161381512 @default.
- W2336302573 cites W2163446794 @default.
- W2336302573 cites W2164022341 @default.
- W2336302573 cites W2179042386 @default.
- W2336302573 cites W2319888919 @default.
- W2336302573 cites W2340690086 @default.
- W2336302573 cites W2953360861 @default.
- W2336302573 cites W54214434 @default.
- W2336302573 cites W2951136860 @default.
- W2336302573 hasPublicationYear "2016" @default.
- W2336302573 type Work @default.
- W2336302573 sameAs 2336302573 @default.
- W2336302573 citedByCount "15" @default.
- W2336302573 countsByYear W23363025732016 @default.
- W2336302573 countsByYear W23363025732017 @default.
- W2336302573 countsByYear W23363025732018 @default.
- W2336302573 countsByYear W23363025732019 @default.
- W2336302573 countsByYear W23363025732020 @default.
- W2336302573 crossrefType "posted-content" @default.
- W2336302573 hasAuthorship W2336302573A5019409717 @default.
- W2336302573 hasAuthorship W2336302573A5038939197 @default.
- W2336302573 hasAuthorship W2336302573A5046083819 @default.
- W2336302573 hasConcept C111919701 @default.
- W2336302573 hasConcept C115961682 @default.
- W2336302573 hasConcept C119857082 @default.
- W2336302573 hasConcept C153180895 @default.
- W2336302573 hasConcept C154945302 @default.
- W2336302573 hasConcept C162324750 @default.
- W2336302573 hasConcept C1667742 @default.
- W2336302573 hasConcept C187736073 @default.
- W2336302573 hasConcept C2780451532 @default.
- W2336302573 hasConcept C2781235140 @default.
- W2336302573 hasConcept C2781238097 @default.
- W2336302573 hasConcept C31972630 @default.
- W2336302573 hasConcept C41008148 @default.
- W2336302573 hasConcept C81363708 @default.
- W2336302573 hasConcept C81917197 @default.
- W2336302573 hasConceptScore W2336302573C111919701 @default.
- W2336302573 hasConceptScore W2336302573C115961682 @default.
- W2336302573 hasConceptScore W2336302573C119857082 @default.
- W2336302573 hasConceptScore W2336302573C153180895 @default.
- W2336302573 hasConceptScore W2336302573C154945302 @default.
- W2336302573 hasConceptScore W2336302573C162324750 @default.
- W2336302573 hasConceptScore W2336302573C1667742 @default.
- W2336302573 hasConceptScore W2336302573C187736073 @default.
- W2336302573 hasConceptScore W2336302573C2780451532 @default.
- W2336302573 hasConceptScore W2336302573C2781235140 @default.
- W2336302573 hasConceptScore W2336302573C2781238097 @default.
- W2336302573 hasConceptScore W2336302573C31972630 @default.
- W2336302573 hasConceptScore W2336302573C41008148 @default.
- W2336302573 hasConceptScore W2336302573C81363708 @default.
- W2336302573 hasConceptScore W2336302573C81917197 @default.
- W2336302573 hasLocation W23363025731 @default.
- W2336302573 hasOpenAccess W2336302573 @default.
- W2336302573 hasPrimaryLocation W23363025731 @default.
- W2336302573 hasRelatedWork W1524680991 @default.
- W2336302573 hasRelatedWork W1556531089 @default.
- W2336302573 hasRelatedWork W1686810756 @default.
- W2336302573 hasRelatedWork W1979931042 @default.