FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210672363> ?p ?o ?g. }

• W4210672363 endingPage "108254" @default.
• W4210672363 startingPage "108254" @default.
• W4210672363 abstract "Performance of pedestrian detection, which is one of the essential tasks in automatic drive, relies heavily on a large number of labels. Some researchers proposed unsupervised domain adaptive frameworks to improve the detection accuracy in wild datasets to reduce the need for labels. However, it is not a down-to-earth and cost-effective way for deploying these frameworks in practical engineering because it needs both source and target data for training. Unlike the former research, this work presents a new fine-tuning method without using source and target data for unsupervised detection. In this work, different well-trained models from the source domain are regarded as less-accurate experts in the wild domain, where a multi-expert learning algorithm is applied to learn from the difference between these models and fuse bounding boxes to present more accurate detection results. Experimental results on three common pedestrian detection datasets show that our method can efficiently improve the detection accuracy under unsupervised settings. Our method can also achieve better performance without source and target data involved compared with state-of-the-art works." @default.
• W4210672363 created "2022-02-08" @default.
• W4210672363 creator A5008117563 @default.
• W4210672363 creator A5036320354 @default.
• W4210672363 creator A5057964928 @default.
• W4210672363 creator A5068624653 @default.
• W4210672363 creator A5071217995 @default.
• W4210672363 date "2022-04-01" @default.
• W4210672363 modified "2023-10-14" @default.
• W4210672363 title "Multi-expert learning for fusion of pedestrian detection bounding box" @default.
• W4210672363 cites W2033547469 @default.
• W4210672363 cites W2058757422 @default.
• W4210672363 cites W2115579991 @default.
• W4210672363 cites W2125556102 @default.
• W4210672363 cites W2194775991 @default.
• W4210672363 cites W2312481402 @default.
• W4210672363 cites W2340897893 @default.
• W4210672363 cites W2428342532 @default.
• W4210672363 cites W2551693289 @default.
• W4210672363 cites W2565639579 @default.
• W4210672363 cites W2594507094 @default.
• W4210672363 cites W2895451584 @default.
• W4210672363 cites W2896540732 @default.
• W4210672363 cites W2909843718 @default.
• W4210672363 cites W2931141826 @default.
• W4210672363 cites W2940510674 @default.
• W4210672363 cites W2948500038 @default.
• W4210672363 cites W2962687275 @default.
• W4210672363 cites W2962850098 @default.
• W4210672363 cites W2963037989 @default.
• W4210672363 cites W2963351448 @default.
• W4210672363 cites W2963403405 @default.
• W4210672363 cites W2963404857 @default.
• W4210672363 cites W2964277612 @default.
• W4210672363 cites W2982770724 @default.
• W4210672363 cites W3010381534 @default.
• W4210672363 cites W3035396860 @default.
• W4210672363 cites W3084188201 @default.
• W4210672363 cites W3095638603 @default.
• W4210672363 cites W3098319575 @default.
• W4210672363 cites W3101295814 @default.
• W4210672363 cites W3119481194 @default.
• W4210672363 cites W4205220354 @default.
• W4210672363 doi "https://doi.org/10.1016/j.knosys.2022.108254" @default.
• W4210672363 hasPublicationYear "2022" @default.
• W4210672363 type Work @default.
• W4210672363 citedByCount "8" @default.
• W4210672363 countsByYear W42106723632022 @default.
• W4210672363 countsByYear W42106723632023 @default.
• W4210672363 crossrefType "journal-article" @default.
• W4210672363 hasAuthorship W4210672363A5008117563 @default.
• W4210672363 hasAuthorship W4210672363A5036320354 @default.
• W4210672363 hasAuthorship W4210672363A5057964928 @default.
• W4210672363 hasAuthorship W4210672363A5068624653 @default.
• W4210672363 hasAuthorship W4210672363A5071217995 @default.
• W4210672363 hasConcept C115961682 @default.
• W4210672363 hasConcept C119599485 @default.
• W4210672363 hasConcept C119857082 @default.
• W4210672363 hasConcept C124101348 @default.
• W4210672363 hasConcept C127413603 @default.
• W4210672363 hasConcept C134306372 @default.
• W4210672363 hasConcept C141353440 @default.
• W4210672363 hasConcept C147037132 @default.
• W4210672363 hasConcept C153180895 @default.
• W4210672363 hasConcept C154945302 @default.
• W4210672363 hasConcept C22212356 @default.
• W4210672363 hasConcept C2776145971 @default.
• W4210672363 hasConcept C2776151529 @default.
• W4210672363 hasConcept C2777113093 @default.
• W4210672363 hasConcept C2780156472 @default.
• W4210672363 hasConcept C33923547 @default.
• W4210672363 hasConcept C36503486 @default.
• W4210672363 hasConcept C41008148 @default.
• W4210672363 hasConcept C63584917 @default.
• W4210672363 hasConcept C8038995 @default.
• W4210672363 hasConceptScore W4210672363C115961682 @default.
• W4210672363 hasConceptScore W4210672363C119599485 @default.
• W4210672363 hasConceptScore W4210672363C119857082 @default.
• W4210672363 hasConceptScore W4210672363C124101348 @default.
• W4210672363 hasConceptScore W4210672363C127413603 @default.
• W4210672363 hasConceptScore W4210672363C134306372 @default.
• W4210672363 hasConceptScore W4210672363C141353440 @default.
• W4210672363 hasConceptScore W4210672363C147037132 @default.
• W4210672363 hasConceptScore W4210672363C153180895 @default.
• W4210672363 hasConceptScore W4210672363C154945302 @default.
• W4210672363 hasConceptScore W4210672363C22212356 @default.
• W4210672363 hasConceptScore W4210672363C2776145971 @default.
• W4210672363 hasConceptScore W4210672363C2776151529 @default.
• W4210672363 hasConceptScore W4210672363C2777113093 @default.
• W4210672363 hasConceptScore W4210672363C2780156472 @default.
• W4210672363 hasConceptScore W4210672363C33923547 @default.
• W4210672363 hasConceptScore W4210672363C36503486 @default.
• W4210672363 hasConceptScore W4210672363C41008148 @default.
• W4210672363 hasConceptScore W4210672363C63584917 @default.
• W4210672363 hasConceptScore W4210672363C8038995 @default.
• W4210672363 hasLocation W42106723631 @default.
• W4210672363 hasOpenAccess W4210672363 @default.
• W4210672363 hasPrimaryLocation W42106723631 @default.

• next