Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896540732> ?p ?o ?g. }
- W2896540732 endingPage "659" @default.
- W2896540732 startingPage "643" @default.
- W2896540732 abstract "Though Faster R-CNN based two-stage detectors have witnessed significant boost in pedestrian detection accuracy, it is still slow for practical applications. One solution is to simplify this working flow as a single-stage detector. However, current single-stage detectors (e.g. SSD) have not presented competitive accuracy on common pedestrian detection benchmarks. This paper is towards a successful pedestrian detector enjoying the speed of SSD while maintaining the accuracy of Faster R-CNN. Specifically, a structurally simple but effective module called Asymptotic Localization Fitting (ALF) is proposed, which stacks a series of predictors to directly evolve the default anchor boxes of SSD step by step into improving detection results. As a result, during training the latter predictors enjoy more and better-quality positive samples, meanwhile harder negatives could be mined with increasing IoU thresholds. On top of this, an efficient single-stage pedestrian detection architecture (denoted as ALFNet) is designed, achieving state-of-the-art performance on CityPersons and Caltech, two of the largest pedestrian detection benchmarks, and hence resulting in an attractive pedestrian detector in both accuracy and speed. Code is available at https://github.com/VideoObjectSearch/ALFNet ." @default.
- W2896540732 created "2018-10-26" @default.
- W2896540732 creator A5019092879 @default.
- W2896540732 creator A5028602988 @default.
- W2896540732 creator A5034654778 @default.
- W2896540732 creator A5071037763 @default.
- W2896540732 creator A5087044141 @default.
- W2896540732 date "2018-01-01" @default.
- W2896540732 modified "2023-10-15" @default.
- W2896540732 title "Learning Efficient Single-Stage Pedestrian Detectors by Asymptotic Localization Fitting" @default.
- W2896540732 cites W1475617732 @default.
- W2896540732 cites W1536680647 @default.
- W2896540732 cites W1650122911 @default.
- W2896540732 cites W1903127635 @default.
- W2896540732 cites W1932624639 @default.
- W2896540732 cites W1976818984 @default.
- W2896540732 cites W2031454541 @default.
- W2896540732 cites W2102605133 @default.
- W2896540732 cites W2108598243 @default.
- W2896540732 cites W2125556102 @default.
- W2896540732 cites W2159386181 @default.
- W2896540732 cites W2194775991 @default.
- W2896540732 cites W2200528286 @default.
- W2896540732 cites W2288122362 @default.
- W2896540732 cites W2490270993 @default.
- W2896540732 cites W2497039038 @default.
- W2896540732 cites W2520951797 @default.
- W2896540732 cites W2531915888 @default.
- W2896540732 cites W2565639579 @default.
- W2896540732 cites W2570343428 @default.
- W2896540732 cites W2594507094 @default.
- W2896540732 cites W2607037079 @default.
- W2896540732 cites W2613599172 @default.
- W2896540732 cites W2962850098 @default.
- W2896540732 cites W2962917547 @default.
- W2896540732 cites W2962992847 @default.
- W2896540732 cites W2963037989 @default.
- W2896540732 cites W2963315052 @default.
- W2896540732 cites W2963351448 @default.
- W2896540732 cites W2963516811 @default.
- W2896540732 cites W2963681621 @default.
- W2896540732 cites W2963786238 @default.
- W2896540732 cites W2963813458 @default.
- W2896540732 cites W2963998989 @default.
- W2896540732 cites W2964241181 @default.
- W2896540732 cites W3106250896 @default.
- W2896540732 cites W345900524 @default.
- W2896540732 doi "https://doi.org/10.1007/978-3-030-01264-9_38" @default.
- W2896540732 hasPublicationYear "2018" @default.
- W2896540732 type Work @default.
- W2896540732 sameAs 2896540732 @default.
- W2896540732 citedByCount "150" @default.
- W2896540732 countsByYear W28965407322019 @default.
- W2896540732 countsByYear W28965407322020 @default.
- W2896540732 countsByYear W28965407322021 @default.
- W2896540732 countsByYear W28965407322022 @default.
- W2896540732 countsByYear W28965407322023 @default.
- W2896540732 crossrefType "book-chapter" @default.
- W2896540732 hasAuthorship W2896540732A5019092879 @default.
- W2896540732 hasAuthorship W2896540732A5028602988 @default.
- W2896540732 hasAuthorship W2896540732A5034654778 @default.
- W2896540732 hasAuthorship W2896540732A5071037763 @default.
- W2896540732 hasAuthorship W2896540732A5087044141 @default.
- W2896540732 hasConcept C11413529 @default.
- W2896540732 hasConcept C127413603 @default.
- W2896540732 hasConcept C146978453 @default.
- W2896540732 hasConcept C153180895 @default.
- W2896540732 hasConcept C154945302 @default.
- W2896540732 hasConcept C177264268 @default.
- W2896540732 hasConcept C199360897 @default.
- W2896540732 hasConcept C22212356 @default.
- W2896540732 hasConcept C2776760102 @default.
- W2896540732 hasConcept C2777113093 @default.
- W2896540732 hasConcept C2780156472 @default.
- W2896540732 hasConcept C3020376581 @default.
- W2896540732 hasConcept C41008148 @default.
- W2896540732 hasConcept C76155785 @default.
- W2896540732 hasConcept C94915269 @default.
- W2896540732 hasConceptScore W2896540732C11413529 @default.
- W2896540732 hasConceptScore W2896540732C127413603 @default.
- W2896540732 hasConceptScore W2896540732C146978453 @default.
- W2896540732 hasConceptScore W2896540732C153180895 @default.
- W2896540732 hasConceptScore W2896540732C154945302 @default.
- W2896540732 hasConceptScore W2896540732C177264268 @default.
- W2896540732 hasConceptScore W2896540732C199360897 @default.
- W2896540732 hasConceptScore W2896540732C22212356 @default.
- W2896540732 hasConceptScore W2896540732C2776760102 @default.
- W2896540732 hasConceptScore W2896540732C2777113093 @default.
- W2896540732 hasConceptScore W2896540732C2780156472 @default.
- W2896540732 hasConceptScore W2896540732C3020376581 @default.
- W2896540732 hasConceptScore W2896540732C41008148 @default.
- W2896540732 hasConceptScore W2896540732C76155785 @default.
- W2896540732 hasConceptScore W2896540732C94915269 @default.
- W2896540732 hasLocation W28965407321 @default.
- W2896540732 hasOpenAccess W2896540732 @default.
- W2896540732 hasPrimaryLocation W28965407321 @default.
- W2896540732 hasRelatedWork W1976827262 @default.
- W2896540732 hasRelatedWork W2101960027 @default.