Every reference with a DOI in the deposited reference list resolved to a known
work in Crossref or DataCite at the dated check, and none carried a retraction,
withdrawal, or removal notice.
The 31 references without a DOI — listed, not checked
no DOI — not checkedref1
no DOI — not checkedA discriminatively trained, multiscale, deformable part model
no DOI — not checkedref5
no DOI — not checkedref6
no DOI — not checkedref7
no DOI — not checkedYou only look once: Unified, real-time object detection
no DOI — not checkedref10
no DOI — not checkedref11
no DOI — not checkedref12
no DOI — not checkedCutmix: Regularization strategy to train strong classifiers with localizable features
no DOI — not checkedCspnet: A new backbone that can enhance learning capability of CNN
no DOI — not checkedref15
no DOI — not checkedLearning data augmentation strategies for object detection
no DOI — not checkedref17
no DOI — not checkedFeature pyramid networks for object detection
no DOI — not checkedref19
no DOI — not checkedAugfpn: Improving multiscale feature learning for object detection
no DOI — not checkedref21
no DOI — not checkedAttention-yolo: Yolo detection algorithm that introduces attention mechanism networks
no DOI — not checkedAn improved small object detection algorithm based on attention mechanism and feature fusion
no DOI — not checkedref25
no DOI — not checkedCBAM: convolutional block attention module
no DOI — not checkedref28
no DOI — not checkedFocal loss for dense object detection
no DOI — not checkedref30
no DOI — not checkedFeature pyramid networks for object detection
no DOI — not checkedref32
no DOI — not checkedCascade R-CNN: delving into high quality object detection
no DOI — not checkedRrnet: A hybrid detector for object detection in drone-captured images
no DOI — not checkedClustered object detection in aerial images
no DOI — not checkedTph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios
checked 2026-08-27 — re-checked daily as this page is visited;
titles and statuses come from Crossref and DataCite and are not part of the signed record
Both snippets point at the live badge image and link back to this page. The
badge re-renders from the daily check, so an embed never goes stale by more than a day of visits.