.png){kind=icon}
.png){kind=icon}
Return
Count2Density: Crowd density estimation without location-level annotations
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2026.113755.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Predicts crowd density maps using only count-level supervision. • Eliminates costly location-level annotations maintaining spatial accuracy. • Leverages a historical map bank to generate pseudo-density maps. • Self-supervised contrastive regulariser enhances spatial awareness. • Outperforms state-of-the-art on major crowd counting benchmarks.
Keywords:
Density estimation
Count-level annotations
Weak-supervision
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
View more organizations