Inserting non-local attention layers at multiple feature levels in a ResNet-50 backbone improves video-based person re-ID (90.0 percent rank-1 on MARS), and a reduced variant cuts FLOPs by 72.7 percent with a 1.1 point accuracy drop.
Sta: Spatial-temporal attention for large-scale video-based person re-identification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification
Inserting non-local attention layers at multiple feature levels in a ResNet-50 backbone improves video-based person re-ID (90.0 percent rank-1 on MARS), and a reduced variant cuts FLOPs by 72.7 percent with a 1.1 point accuracy drop.