FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288046246> ?p ?o ?g. }

• W4288046246 endingPage "109499" @default.
• W4288046246 startingPage "109499" @default.
• W4288046246 abstract "Anchor-free based object detection has recently seen important progress benefiting from the advances in convolution neural networks. However, the detection performance for human faces is not so satisfactory. First of all, many existing anchor-free methods only focus on a certain scale of the feature map, such a mechanism often fails to perceive the important multi-scale context, resulting in a low recall rate of faces with large scale variations. To solve this problem, we propose to boost the face detection by adaptive learning to perceive the focal scale. To be specific, we design an online scale adaptation strategy to heuristically guide each layer detector to detect faces of different scales in multi-branch structures, which reduces outliers and improves recall rates. In additional, we also argue that the detection head with single convolution layer widely used in anchor-free methods is not robust enough to image context. Therefore, we augment the network by a context-aware detection module. The module dynamically generates different detectors for different input images based on their context to adapt to their image features, reducing the dependence on feature extraction ability of backbone network, and avoiding feature deviations in different scenes. Extensive experiments demonstrate that our method achieves significant performance gains compared to previous anchor-free methods and is comparable to the most advanced anchor-based face detection methods." @default.
• W4288046246 created "2022-07-27" @default.
• W4288046246 creator A5014825654 @default.
• W4288046246 creator A5022526821 @default.
• W4288046246 creator A5042114145 @default.
• W4288046246 creator A5056681935 @default.
• W4288046246 creator A5091220468 @default.
• W4288046246 date "2022-10-01" @default.
• W4288046246 modified "2023-10-18" @default.
• W4288046246 title "Scale adaption-guided human face detection" @default.
• W4288046246 cites W2034025266 @default.
• W4288046246 cites W2194775991 @default.
• W4288046246 cites W2570343428 @default.
• W4288046246 cites W2579152745 @default.
• W4288046246 cites W2735721798 @default.
• W4288046246 cites W2778476852 @default.
• W4288046246 cites W2888313892 @default.
• W4288046246 cites W2952565170 @default.
• W4288046246 cites W2963037989 @default.
• W4288046246 cites W2963299996 @default.
• W4288046246 cites W2963307811 @default.
• W4288046246 cites W2963566548 @default.
• W4288046246 cites W2963572007 @default.
• W4288046246 cites W2963856926 @default.
• W4288046246 cites W2963927307 @default.
• W4288046246 cites W2964347837 @default.
• W4288046246 cites W2982770724 @default.
• W4288046246 cites W2985214930 @default.
• W4288046246 cites W2989604896 @default.
• W4288046246 cites W3000557356 @default.
• W4288046246 cites W3012573144 @default.
• W4288046246 cites W3020895012 @default.
• W4288046246 cites W3034552680 @default.
• W4288046246 cites W3048631361 @default.
• W4288046246 cites W3093565423 @default.
• W4288046246 cites W3102701618 @default.
• W4288046246 cites W3103152812 @default.
• W4288046246 cites W3103294617 @default.
• W4288046246 cites W3108009897 @default.
• W4288046246 cites W3122249885 @default.
• W4288046246 cites W3125127021 @default.
• W4288046246 cites W3136119502 @default.
• W4288046246 cites W3152390103 @default.
• W4288046246 cites W3159793249 @default.
• W4288046246 cites W3160701750 @default.
• W4288046246 cites W3165352316 @default.
• W4288046246 cites W3170226651 @default.
• W4288046246 cites W4200615098 @default.
• W4288046246 cites W4205216778 @default.
• W4288046246 cites W4280614260 @default.
• W4288046246 doi "https://doi.org/10.1016/j.knosys.2022.109499" @default.
• W4288046246 hasPublicationYear "2022" @default.
• W4288046246 type Work @default.
• W4288046246 citedByCount "3" @default.
• W4288046246 countsByYear W42880462462022 @default.
• W4288046246 countsByYear W42880462462023 @default.
• W4288046246 crossrefType "journal-article" @default.
• W4288046246 hasAuthorship W4288046246A5014825654 @default.
• W4288046246 hasAuthorship W4288046246A5022526821 @default.
• W4288046246 hasAuthorship W4288046246A5042114145 @default.
• W4288046246 hasAuthorship W4288046246A5056681935 @default.
• W4288046246 hasAuthorship W4288046246A5091220468 @default.
• W4288046246 hasConcept C121332964 @default.
• W4288046246 hasConcept C144024400 @default.
• W4288046246 hasConcept C153180895 @default.
• W4288046246 hasConcept C154945302 @default.
• W4288046246 hasConcept C2778755073 @default.
• W4288046246 hasConcept C2779304628 @default.
• W4288046246 hasConcept C31510193 @default.
• W4288046246 hasConcept C36289849 @default.
• W4288046246 hasConcept C41008148 @default.
• W4288046246 hasConcept C4641261 @default.
• W4288046246 hasConcept C62520636 @default.
• W4288046246 hasConceptScore W4288046246C121332964 @default.
• W4288046246 hasConceptScore W4288046246C144024400 @default.
• W4288046246 hasConceptScore W4288046246C153180895 @default.
• W4288046246 hasConceptScore W4288046246C154945302 @default.
• W4288046246 hasConceptScore W4288046246C2778755073 @default.
• W4288046246 hasConceptScore W4288046246C2779304628 @default.
• W4288046246 hasConceptScore W4288046246C31510193 @default.
• W4288046246 hasConceptScore W4288046246C36289849 @default.
• W4288046246 hasConceptScore W4288046246C41008148 @default.
• W4288046246 hasConceptScore W4288046246C4641261 @default.
• W4288046246 hasConceptScore W4288046246C62520636 @default.
• W4288046246 hasLocation W42880462461 @default.
• W4288046246 hasOpenAccess W4288046246 @default.
• W4288046246 hasPrimaryLocation W42880462461 @default.
• W4288046246 hasRelatedWork W1533852771 @default.
• W4288046246 hasRelatedWork W1599954882 @default.
• W4288046246 hasRelatedWork W2003685048 @default.
• W4288046246 hasRelatedWork W2010373410 @default.
• W4288046246 hasRelatedWork W2033537011 @default.
• W4288046246 hasRelatedWork W2544717100 @default.
• W4288046246 hasRelatedWork W2939627439 @default.
• W4288046246 hasRelatedWork W2181570714 @default.
• W4288046246 hasRelatedWork W2185710225 @default.
• W4288046246 hasRelatedWork W2556027189 @default.
• W4288046246 hasVolume "253" @default.

• next