Robust Small-scale Pedestrian Detection with Cued Recall via Memory Learning

Cited 5 time in webofscience Cited 0 time in scopus
  • Hit : 190
  • Download : 0
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.
Publisher
Computer Vision Foundation, IEEE Computer Society
Issue Date
2021-10-15
Language
English
Citation

18th IEEE/CVF International Conference on Computer Vision (ICCV), pp.3030 - 3039

DOI
10.1109/ICCV48922.2021.00304
URI
http://hdl.handle.net/10203/288200
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 5 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0