AI Paper Atlas

Research map / Detection and segmentation / CNN features

Consistency-Aware Anchor Pyramid Network for Crowd Localization

Xinyan Liu, Guorong Li, Yuankai Qi, Zhenjun Han, Anton van den Hengel, Nicu Sebe, Ming–Hsuan Yang, Qingming Huang

TPAMI 2024 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add AAPS and CTR together (ablation)anchor-based crowd localizer · JHU-CROWD++F1: 76.2 -> 82.5Improved
add CTR to the baseline without AAPS (ablation)anchor-based crowd localizer · JHU-CROWD++F1: 76.2 -> 78.7Improved
add AAPS to the baseline without CTR (ablation)anchor-based crowd localizer · JHU-CROWD++F1: 76.2 -> 81.5Improved
add CTR on top of AAPS (ablation)anchor-based crowd localizer · JHU-CROWD++F1: 81.5 -> 82.5Improved
use three anchor levels 1,4,8 instead of single level of 4 anchors (ablation)AAPS · JHU-CROWD++F1: 78.7 -> 82.5Improved
use anchor counts 1,2,4 instead of 1,4,8 (ablation)AAPS · JHU-CROWD++F1: 82.5 -> 76.2Hurt
add a fourth anchor level (10 to 16 anchors) (ablation)AAPS · JHU-CROWD++F1: 82.5 -> 82.1No clear effect
add K-means anchor priors instead of uniform anchors (ablation)AAPS · JHU-CROWD++F1: 82.1 -> 82.5Improved
add cascade region count loss instead of MSE loss (ablation)AAPS · JHU-CROWD++F1: 80.8 -> 82.5Improved
add cascade region count loss instead of MSE loss (ablation)AAPS · JHU-CROWD++MAE: 63.4 vs 64.2Hurt
use ConvNext-S instead of HRNet-48 backboneproposed method · JHU-CROWD++F1: 80.7 -> 82.5Improved
use ConvNext-S instead of HRNet-48 backboneproposed method · UCF-QNRFF1: 79.3 vs 79.2No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy