Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285229583> ?p ?o ?g. }
- W4285229583 endingPage "21300" @default.
- W4285229583 startingPage "21291" @default.
- W4285229583 abstract "Although pedestrian detection has achieved promising performance with the development of deep learning techniques, it remains a great challenge to detect heavily occluded pedestrians in crowd scenes. Therefore, to make the anchor-free network pay more attention to learning the hard examples of occluded pedestrians, we propose a simple but effective Occlusion-aware Anchor-Free Network (namely OAF-Net) for pedestrian detection in crowd scenes. Specifically, we first design a novel occlusion-aware detection head, which includes three separate center prediction branches combining with the scale and offset prediction branches. In the detection head of OAF-Net, occluded pedestrian instances are assigned to the most suitable center prediction branch according to the occlusion level of human body. To optimize the center prediction, we accordingly propose a novel weighted Focal Loss where pedestrian instances are assigned with different weights according to their visibility ratios, so that the occluded pedestrians are up-weighted during the training process. Our OAF-Net is able to model different occlusion levels of pedestrian instances effectively, and can be optimized towards catching a high-level understanding of the hard training samples of occluded pedestrians. Experiments on the challenging CityPersons, Caltech, and CrowdHuman benchmarks sufficiently validate the efficacy of our OAF-Net for pedestrian detection in crowd scenes." @default.
- W4285229583 created "2022-07-14" @default.
- W4285229583 creator A5026324175 @default.
- W4285229583 creator A5027835055 @default.
- W4285229583 creator A5064394634 @default.
- W4285229583 creator A5066862201 @default.
- W4285229583 creator A5071969709 @default.
- W4285229583 date "2022-11-01" @default.
- W4285229583 modified "2023-10-05" @default.
- W4285229583 title "OAF-Net: An Occlusion-Aware Anchor-Free Network for Pedestrian Detection in a Crowd" @default.
- W4285229583 cites W1536680647 @default.
- W4285229583 cites W1999954621 @default.
- W4285229583 cites W2031454541 @default.
- W4285229583 cites W2031638733 @default.
- W4285229583 cites W2059363354 @default.
- W4285229583 cites W2108598243 @default.
- W4285229583 cites W2125556102 @default.
- W4285229583 cites W2151454023 @default.
- W4285229583 cites W2152369758 @default.
- W4285229583 cites W2156547346 @default.
- W4285229583 cites W2168356304 @default.
- W4285229583 cites W2194775991 @default.
- W4285229583 cites W2200528286 @default.
- W4285229583 cites W2497039038 @default.
- W4285229583 cites W2565639579 @default.
- W4285229583 cites W2594507094 @default.
- W4285229583 cites W2612624696 @default.
- W4285229583 cites W2613599172 @default.
- W4285229583 cites W2775890136 @default.
- W4285229583 cites W2792824754 @default.
- W4285229583 cites W2799199435 @default.
- W4285229583 cites W2883363148 @default.
- W4285229583 cites W2884561390 @default.
- W4285229583 cites W2888728082 @default.
- W4285229583 cites W2894820835 @default.
- W4285229583 cites W2894878591 @default.
- W4285229583 cites W2895451584 @default.
- W4285229583 cites W2896540732 @default.
- W4285229583 cites W2916798096 @default.
- W4285229583 cites W2925287836 @default.
- W4285229583 cites W2962850098 @default.
- W4285229583 cites W2963037989 @default.
- W4285229583 cites W2963093690 @default.
- W4285229583 cites W2963299996 @default.
- W4285229583 cites W2963315052 @default.
- W4285229583 cites W2963318220 @default.
- W4285229583 cites W2963323244 @default.
- W4285229583 cites W2963404857 @default.
- W4285229583 cites W2963604034 @default.
- W4285229583 cites W2963681621 @default.
- W4285229583 cites W2963769056 @default.
- W4285229583 cites W2963927307 @default.
- W4285229583 cites W2964080601 @default.
- W4285229583 cites W2964121718 @default.
- W4285229583 cites W2986357608 @default.
- W4285229583 cites W2989604896 @default.
- W4285229583 cites W2990075400 @default.
- W4285229583 cites W2990130718 @default.
- W4285229583 cites W2997344726 @default.
- W4285229583 cites W3007237990 @default.
- W4285229583 cites W3007529723 @default.
- W4285229583 cites W3034638324 @default.
- W4285229583 cites W3034955056 @default.
- W4285229583 cites W3035323039 @default.
- W4285229583 cites W3082231033 @default.
- W4285229583 cites W3092665420 @default.
- W4285229583 cites W3092687228 @default.
- W4285229583 cites W3093583077 @default.
- W4285229583 cites W3095638603 @default.
- W4285229583 cites W3098361319 @default.
- W4285229583 cites W3164282918 @default.
- W4285229583 cites W3173632533 @default.
- W4285229583 cites W3177452291 @default.
- W4285229583 cites W639708223 @default.
- W4285229583 doi "https://doi.org/10.1109/tits.2022.3171250" @default.
- W4285229583 hasPublicationYear "2022" @default.
- W4285229583 type Work @default.
- W4285229583 citedByCount "7" @default.
- W4285229583 countsByYear W42852295832022 @default.
- W4285229583 countsByYear W42852295832023 @default.
- W4285229583 crossrefType "journal-article" @default.
- W4285229583 hasAuthorship W4285229583A5026324175 @default.
- W4285229583 hasAuthorship W4285229583A5027835055 @default.
- W4285229583 hasAuthorship W4285229583A5064394634 @default.
- W4285229583 hasAuthorship W4285229583A5066862201 @default.
- W4285229583 hasAuthorship W4285229583A5071969709 @default.
- W4285229583 hasConcept C123403432 @default.
- W4285229583 hasConcept C127413603 @default.
- W4285229583 hasConcept C14166107 @default.
- W4285229583 hasConcept C153180895 @default.
- W4285229583 hasConcept C153294291 @default.
- W4285229583 hasConcept C154945302 @default.
- W4285229583 hasConcept C164705383 @default.
- W4285229583 hasConcept C175291020 @default.
- W4285229583 hasConcept C199360897 @default.
- W4285229583 hasConcept C205649164 @default.
- W4285229583 hasConcept C22212356 @default.
- W4285229583 hasConcept C2524010 @default.