DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Jung Uk | ko |
dc.contributor.author | Park, Sungjune | ko |
dc.contributor.author | Ro, Yong Man | ko |
dc.date.accessioned | 2021-10-15T00:30:38Z | - |
dc.date.available | 2021-10-15T00:30:38Z | - |
dc.date.created | 2021-07-23 | - |
dc.date.created | 2021-07-23 | - |
dc.date.created | 2021-07-23 | - |
dc.date.created | 2021-07-23 | - |
dc.date.issued | 2021-10-15 | - |
dc.identifier.citation | 18th IEEE/CVF International Conference on Computer Vision (ICCV), pp.3030 - 3039 | - |
dc.identifier.uri | http://hdl.handle.net/10203/288200 | - |
dc.description.abstract | Although the visual appearances of small-scale objects are not well observed, humans can recognize them by associating the visual cues of small objects from their memorized appearance. It is called cued recall. In this paper, motivated by the memory process of humans, we introduce a novel pedestrian detection framework that imitates cued recall in detecting small-scale pedestrians. We propose a large-scale embedding learning with the large-scale pedestrian recalling memory (LPR Memory). The purpose of the proposed large-scale embedding learning is to memorize and recall the large-scale pedestrian appearance via the LPR Memory. To this end, we employ the large-scale pedestrian exemplar set, so that, the LPR Memory can recall the information of the large-scale pedestrians from the small-scale pedestrians. Comprehensive quantitative and qualitative experimental results validate the effectiveness of the proposed framework with the LPR Memory. | - |
dc.language | English | - |
dc.publisher | Computer Vision Foundation, IEEE Computer Society | - |
dc.title | Robust Small-scale Pedestrian Detection with Cued Recall via Memory Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000797698903024 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 3030 | - |
dc.citation.endingpage | 3039 | - |
dc.citation.publicationname | 18th IEEE/CVF International Conference on Computer Vision (ICCV) | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Virtual | - |
dc.identifier.doi | 10.1109/ICCV48922.2021.00304 | - |
dc.contributor.localauthor | Ro, Yong Man | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.