Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287263149> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4287263149 abstract "Benefiting from the pioneering design of generic object detectors, significant achievements have been made in the field of face detection. Typically, the architectures of the backbone, feature pyramid layer, and detection head module within the face detector all assimilate the excellent experience from general object detectors. However, several effective methods, including label assignment and scale-level data augmentation strategy, fail to maintain consistent superiority when applying on the face detector directly. Concretely, the former strategy involves a vast body of hyper-parameters and the latter one suffers from the challenge of scale distribution bias between different detection tasks, which both limit their generalization abilities. Furthermore, in order to provide accurate face bounding boxes for facial down-stream tasks, the face detector imperatively requires the elimination of false alarms. As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are necessary for advancing face detectors. In this paper, we focus on resolving three aforementioned challenges that exiting methods are difficult to finish off and present a novel face detector, termed MogFace. In our Mogface, three key components, Adaptive Online Incremental Anchor Mining Strategy, Selective Scale Enhancement Strategy and Hierarchical Context-Aware Module, are separately proposed to boost the performance of face detectors. Finally, to the best of our knowledge, our MogFace is the best face detector on the Wider Face leader-board, achieving all champions across different testing scenarios. The code is available at url{https://github.com/damo-cv/MogFace}." @default.
- W4287263149 created "2022-07-25" @default.
- W4287263149 creator A5019560977 @default.
- W4287263149 creator A5023363049 @default.
- W4287263149 creator A5033411069 @default.
- W4287263149 creator A5073110676 @default.
- W4287263149 creator A5086529957 @default.
- W4287263149 creator A5087131650 @default.
- W4287263149 date "2021-03-20" @default.
- W4287263149 modified "2023-10-17" @default.
- W4287263149 title "MogFace: Towards a Deeper Appreciation on Face Detection" @default.
- W4287263149 doi "https://doi.org/10.48550/arxiv.2103.11139" @default.
- W4287263149 hasPublicationYear "2021" @default.
- W4287263149 type Work @default.
- W4287263149 citedByCount "0" @default.
- W4287263149 crossrefType "posted-content" @default.
- W4287263149 hasAuthorship W4287263149A5019560977 @default.
- W4287263149 hasAuthorship W4287263149A5023363049 @default.
- W4287263149 hasAuthorship W4287263149A5033411069 @default.
- W4287263149 hasAuthorship W4287263149A5073110676 @default.
- W4287263149 hasAuthorship W4287263149A5086529957 @default.
- W4287263149 hasAuthorship W4287263149A5087131650 @default.
- W4287263149 hasBestOaLocation W42872631491 @default.
- W4287263149 hasConcept C115961682 @default.
- W4287263149 hasConcept C121332964 @default.
- W4287263149 hasConcept C134306372 @default.
- W4287263149 hasConcept C138885662 @default.
- W4287263149 hasConcept C144024400 @default.
- W4287263149 hasConcept C147037132 @default.
- W4287263149 hasConcept C151730666 @default.
- W4287263149 hasConcept C153180895 @default.
- W4287263149 hasConcept C154945302 @default.
- W4287263149 hasConcept C177148314 @default.
- W4287263149 hasConcept C2776151529 @default.
- W4287263149 hasConcept C2776401178 @default.
- W4287263149 hasConcept C2778755073 @default.
- W4287263149 hasConcept C2779304628 @default.
- W4287263149 hasConcept C2779343474 @default.
- W4287263149 hasConcept C31510193 @default.
- W4287263149 hasConcept C31972630 @default.
- W4287263149 hasConcept C33923547 @default.
- W4287263149 hasConcept C36289849 @default.
- W4287263149 hasConcept C41008148 @default.
- W4287263149 hasConcept C41895202 @default.
- W4287263149 hasConcept C4641261 @default.
- W4287263149 hasConcept C62520636 @default.
- W4287263149 hasConcept C63584917 @default.
- W4287263149 hasConcept C71681937 @default.
- W4287263149 hasConcept C76155785 @default.
- W4287263149 hasConcept C86803240 @default.
- W4287263149 hasConcept C94915269 @default.
- W4287263149 hasConceptScore W4287263149C115961682 @default.
- W4287263149 hasConceptScore W4287263149C121332964 @default.
- W4287263149 hasConceptScore W4287263149C134306372 @default.
- W4287263149 hasConceptScore W4287263149C138885662 @default.
- W4287263149 hasConceptScore W4287263149C144024400 @default.
- W4287263149 hasConceptScore W4287263149C147037132 @default.
- W4287263149 hasConceptScore W4287263149C151730666 @default.
- W4287263149 hasConceptScore W4287263149C153180895 @default.
- W4287263149 hasConceptScore W4287263149C154945302 @default.
- W4287263149 hasConceptScore W4287263149C177148314 @default.
- W4287263149 hasConceptScore W4287263149C2776151529 @default.
- W4287263149 hasConceptScore W4287263149C2776401178 @default.
- W4287263149 hasConceptScore W4287263149C2778755073 @default.
- W4287263149 hasConceptScore W4287263149C2779304628 @default.
- W4287263149 hasConceptScore W4287263149C2779343474 @default.
- W4287263149 hasConceptScore W4287263149C31510193 @default.
- W4287263149 hasConceptScore W4287263149C31972630 @default.
- W4287263149 hasConceptScore W4287263149C33923547 @default.
- W4287263149 hasConceptScore W4287263149C36289849 @default.
- W4287263149 hasConceptScore W4287263149C41008148 @default.
- W4287263149 hasConceptScore W4287263149C41895202 @default.
- W4287263149 hasConceptScore W4287263149C4641261 @default.
- W4287263149 hasConceptScore W4287263149C62520636 @default.
- W4287263149 hasConceptScore W4287263149C63584917 @default.
- W4287263149 hasConceptScore W4287263149C71681937 @default.
- W4287263149 hasConceptScore W4287263149C76155785 @default.
- W4287263149 hasConceptScore W4287263149C86803240 @default.
- W4287263149 hasConceptScore W4287263149C94915269 @default.
- W4287263149 hasLocation W42872631491 @default.
- W4287263149 hasOpenAccess W4287263149 @default.
- W4287263149 hasPrimaryLocation W42872631491 @default.
- W4287263149 hasRelatedWork W1560697087 @default.
- W4287263149 hasRelatedWork W1989039360 @default.
- W4287263149 hasRelatedWork W2003685048 @default.
- W4287263149 hasRelatedWork W2532573070 @default.
- W4287263149 hasRelatedWork W2544717100 @default.
- W4287263149 hasRelatedWork W2607108626 @default.
- W4287263149 hasRelatedWork W269042006 @default.
- W4287263149 hasRelatedWork W2884888700 @default.
- W4287263149 hasRelatedWork W2997667844 @default.
- W4287263149 hasRelatedWork W4225418833 @default.
- W4287263149 isParatext "false" @default.
- W4287263149 isRetracted "false" @default.
- W4287263149 workType "article" @default.