TAPNet fuses RGB and thermal imagery using attention and feature-decomposition modules and reports improved crowd counting and localization on two UAV datasets.
The effectiveness of a simplified model structure for crowd counting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network
TAPNet fuses RGB and thermal imagery using attention and feature-decomposition modules and reports improved crowd counting and localization on two UAV datasets.