In this paper, we transfer some techniques used in computer vision to crowd counting and verify whether they are valid. These techniques are attention mechanism, using larger receptive filed and combination of two different ways ——MSE loss and Bayesian loss. Experiments show that channel attention and spatial attention is not helpful for crowd counting; using larger receptive filed can improve model performance and context-aware method is better than SPP block; combination of two different ways is also not helpful for crowd counting.
Are attention, larger receptive filed and multi task loss good for crowd counting?
2021-10-20
1045479 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Spatio-Channel Attention Blocks for Cross-modal Crowd Counting
British Library Conference Proceedings | 2023
|Multi-view branch-shared subway platform crowd counting method
British Library Conference Proceedings | 2023
|