TransCrowd: Weakly-Supervised Crowd Counting with Transformer

19 Apr 2021 Dingkang Liang Xiwu Chen Wei Xu Yu Zhou Xiang Bai

The mainstream crowd counting methods usually utilize the convolution neural network (CNN) to regress a density map, requiring point-level annotations. However, annotating each person with a point is an expensive and laborious process... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Softmax
Output Functions
Layer Normalization
Normalization
Label Smoothing
Regularization
Residual Connection
Skip Connections
Multi-Head Attention
Attention Modules
BPE
Subword Segmentation
Dropout
Regularization
Adam
Stochastic Optimization
Dense Connections
Feedforward Networks
Scaled Dot-Product Attention
Attention Mechanisms
Transformer
Transformers
Convolution
Convolutions