Matches in SemOpenAlex for { <https://semopenalex.org/work/W2954156922> ?p ?o ?g. }
- W2954156922 endingPage "2673" @default.
- W2954156922 startingPage "2663" @default.
- W2954156922 abstract "Human detection is one of the long-standing computer vision tasks, and it has been a cornerstone for many real-world applications, such as photo album organization, video surveillance, and autonomous driving. Benefiting from deep learning technologies, such as convolutional neural networks and modern object detectors, have been achieving much improved accuracy in generic object detection tasks. In this paper, we aim to improve deep learning-based human detection. Our main idea is to exploit semantic context information for human detection by using deep-learnt semantic features provided by semantic segmentation masks. Segmentation masks play as an attention mechanism and enforce the detectors to focus on the image regions where potential object candidates are likely to appear. Meanwhile, the extra segmentation mask channel can also guide the convolutional kernels to automatically learn more discriminative features which make it easier to distinguish the background and foreground. We implement our methods with two popular detection frameworks, i.e., faster R-CNN and SSD and experimentally analyze the effectiveness of the proposed methods. Evaluation results on the widely used MS-COCO dataset and the very recent CrowdHuman dataset are provided. Our proposed methods outperform the baseline detectors and achieve better performance on highly occluded human detection." @default.
- W2954156922 created "2019-07-12" @default.
- W2954156922 creator A5003131173 @default.
- W2954156922 creator A5006294869 @default.
- W2954156922 creator A5021984184 @default.
- W2954156922 creator A5084521046 @default.
- W2954156922 date "2020-08-01" @default.
- W2954156922 modified "2023-10-11" @default.
- W2954156922 title "Human Detection Aided by Deeply Learned Semantic Masks" @default.
- W2954156922 cites W1536680647 @default.
- W2954156922 cites W1565402342 @default.
- W2954156922 cites W1903029394 @default.
- W2954156922 cites W2097117768 @default.
- W2954156922 cites W2102605133 @default.
- W2954156922 cites W2108598243 @default.
- W2954156922 cites W2151103935 @default.
- W2954156922 cites W2161969291 @default.
- W2954156922 cites W2168195382 @default.
- W2954156922 cites W2194775991 @default.
- W2954156922 cites W2302502886 @default.
- W2954156922 cites W2412782625 @default.
- W2954156922 cites W2497039038 @default.
- W2954156922 cites W2531409750 @default.
- W2954156922 cites W2549139847 @default.
- W2954156922 cites W2555182955 @default.
- W2954156922 cites W2557728737 @default.
- W2954156922 cites W2565639579 @default.
- W2954156922 cites W2594507094 @default.
- W2954156922 cites W2601564443 @default.
- W2954156922 cites W2604967609 @default.
- W2954156922 cites W2613599172 @default.
- W2954156922 cites W2743905801 @default.
- W2954156922 cites W2798775284 @default.
- W2954156922 cites W2884030607 @default.
- W2954156922 cites W2895077992 @default.
- W2954156922 cites W2896524115 @default.
- W2954156922 cites W2902502320 @default.
- W2954156922 cites W2963037989 @default.
- W2954156922 cites W2963150697 @default.
- W2954156922 cites W2963315052 @default.
- W2954156922 cites W2963363373 @default.
- W2954156922 cites W2963563573 @default.
- W2954156922 cites W2963681621 @default.
- W2954156922 cites W2963998989 @default.
- W2954156922 cites W2964309882 @default.
- W2954156922 cites W3098217967 @default.
- W2954156922 cites W3151111735 @default.
- W2954156922 doi "https://doi.org/10.1109/tcsvt.2019.2924912" @default.
- W2954156922 hasPublicationYear "2020" @default.
- W2954156922 type Work @default.
- W2954156922 sameAs 2954156922 @default.
- W2954156922 citedByCount "9" @default.
- W2954156922 countsByYear W29541569222019 @default.
- W2954156922 countsByYear W29541569222020 @default.
- W2954156922 countsByYear W29541569222022 @default.
- W2954156922 countsByYear W29541569222023 @default.
- W2954156922 crossrefType "journal-article" @default.
- W2954156922 hasAuthorship W2954156922A5003131173 @default.
- W2954156922 hasAuthorship W2954156922A5006294869 @default.
- W2954156922 hasAuthorship W2954156922A5021984184 @default.
- W2954156922 hasAuthorship W2954156922A5084521046 @default.
- W2954156922 hasConcept C108583219 @default.
- W2954156922 hasConcept C119857082 @default.
- W2954156922 hasConcept C120665830 @default.
- W2954156922 hasConcept C121332964 @default.
- W2954156922 hasConcept C124504099 @default.
- W2954156922 hasConcept C151730666 @default.
- W2954156922 hasConcept C153180895 @default.
- W2954156922 hasConcept C154945302 @default.
- W2954156922 hasConcept C165696696 @default.
- W2954156922 hasConcept C192209626 @default.
- W2954156922 hasConcept C2776151529 @default.
- W2954156922 hasConcept C2779343474 @default.
- W2954156922 hasConcept C31972630 @default.
- W2954156922 hasConcept C38652104 @default.
- W2954156922 hasConcept C41008148 @default.
- W2954156922 hasConcept C76155785 @default.
- W2954156922 hasConcept C81363708 @default.
- W2954156922 hasConcept C86803240 @default.
- W2954156922 hasConcept C89600930 @default.
- W2954156922 hasConcept C94915269 @default.
- W2954156922 hasConcept C97931131 @default.
- W2954156922 hasConceptScore W2954156922C108583219 @default.
- W2954156922 hasConceptScore W2954156922C119857082 @default.
- W2954156922 hasConceptScore W2954156922C120665830 @default.
- W2954156922 hasConceptScore W2954156922C121332964 @default.
- W2954156922 hasConceptScore W2954156922C124504099 @default.
- W2954156922 hasConceptScore W2954156922C151730666 @default.
- W2954156922 hasConceptScore W2954156922C153180895 @default.
- W2954156922 hasConceptScore W2954156922C154945302 @default.
- W2954156922 hasConceptScore W2954156922C165696696 @default.
- W2954156922 hasConceptScore W2954156922C192209626 @default.
- W2954156922 hasConceptScore W2954156922C2776151529 @default.
- W2954156922 hasConceptScore W2954156922C2779343474 @default.
- W2954156922 hasConceptScore W2954156922C31972630 @default.
- W2954156922 hasConceptScore W2954156922C38652104 @default.
- W2954156922 hasConceptScore W2954156922C41008148 @default.
- W2954156922 hasConceptScore W2954156922C76155785 @default.