Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300691741> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4300691741 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.
- W4300691741 created "2022-10-04" @default.
- W4300691741 creator A5019409717 @default.
- W4300691741 creator A5038939197 @default.
- W4300691741 creator A5046083819 @default.
- W4300691741 date "2016-04-08" @default.
- W4300691741 modified "2023-09-27" @default.
- W4300691741 title "CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples" @default.
- W4300691741 doi "https://doi.org/10.48550/arxiv.1604.02426" @default.
- W4300691741 hasPublicationYear "2016" @default.
- W4300691741 type Work @default.
- W4300691741 citedByCount "0" @default.
- W4300691741 crossrefType "posted-content" @default.
- W4300691741 hasAuthorship W4300691741A5019409717 @default.
- W4300691741 hasAuthorship W4300691741A5038939197 @default.
- W4300691741 hasAuthorship W4300691741A5046083819 @default.
- W4300691741 hasBestOaLocation W43006917411 @default.
- W4300691741 hasConcept C111919701 @default.
- W4300691741 hasConcept C115961682 @default.
- W4300691741 hasConcept C153180895 @default.
- W4300691741 hasConcept C154945302 @default.
- W4300691741 hasConcept C162324750 @default.
- W4300691741 hasConcept C1667742 @default.
- W4300691741 hasConcept C187736073 @default.
- W4300691741 hasConcept C2780451532 @default.
- W4300691741 hasConcept C2781235140 @default.
- W4300691741 hasConcept C2781238097 @default.
- W4300691741 hasConcept C31972630 @default.
- W4300691741 hasConcept C41008148 @default.
- W4300691741 hasConcept C81363708 @default.
- W4300691741 hasConcept C81917197 @default.
- W4300691741 hasConceptScore W4300691741C111919701 @default.
- W4300691741 hasConceptScore W4300691741C115961682 @default.
- W4300691741 hasConceptScore W4300691741C153180895 @default.
- W4300691741 hasConceptScore W4300691741C154945302 @default.
- W4300691741 hasConceptScore W4300691741C162324750 @default.
- W4300691741 hasConceptScore W4300691741C1667742 @default.
- W4300691741 hasConceptScore W4300691741C187736073 @default.
- W4300691741 hasConceptScore W4300691741C2780451532 @default.
- W4300691741 hasConceptScore W4300691741C2781235140 @default.
- W4300691741 hasConceptScore W4300691741C2781238097 @default.
- W4300691741 hasConceptScore W4300691741C31972630 @default.
- W4300691741 hasConceptScore W4300691741C41008148 @default.
- W4300691741 hasConceptScore W4300691741C81363708 @default.
- W4300691741 hasConceptScore W4300691741C81917197 @default.
- W4300691741 hasLocation W43006917411 @default.
- W4300691741 hasOpenAccess W4300691741 @default.
- W4300691741 hasPrimaryLocation W43006917411 @default.
- W4300691741 hasRelatedWork W1837097281 @default.
- W4300691741 hasRelatedWork W1966410754 @default.
- W4300691741 hasRelatedWork W2007544051 @default.
- W4300691741 hasRelatedWork W2016398835 @default.
- W4300691741 hasRelatedWork W2092957489 @default.
- W4300691741 hasRelatedWork W2325242284 @default.
- W4300691741 hasRelatedWork W2363840281 @default.
- W4300691741 hasRelatedWork W2732542196 @default.
- W4300691741 hasRelatedWork W2963891724 @default.
- W4300691741 hasRelatedWork W2975200075 @default.
- W4300691741 isParatext "false" @default.
- W4300691741 isRetracted "false" @default.
- W4300691741 workType "article" @default.