.png){kind=icon}
返回
Attentive encoder-decoder networks for crowd counting
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.11.087.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Crowd counting that aims to estimate the crowd density has recently made significant progress but remains an unsolved problem due to several challenges. In this paper, we propose an Attentive Encoder-Decoder Network (AEDNet) to overcome the notorious scale-variation problem in crowd counting. Our major contributions can be summarized in three aspects. First, we design an Attentive Feature Refinement (AFR) block in the encoder to adaptively extract multi-scale features. AFR compares the spatial information in different scales through the attention mechanism and then adaptively assign importance weights to each point, which highlights the distinctive roles in multi-scale feature extraction. Second, we develop a Separable Non-local Fusion (SNF) block in the decoder with the self-attention mechanism to aggregate multi-scale features from different layers, which not only achieves the sufficient feature fusion by capturing long-range dependencies, but also vastly reduces the computation cost compared to the original non-local operation. Third, we propose a Regional MSE (R-MSE) loss to tackle the pixel-isolation problems in regular MSE loss. To demonstrate the effectiveness of the proposed AEDNet, we conduct extensive experiments on four widely-used crowd counting datasets, and our AEDNet consistently achieves the state-of-the-art performance. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Crowd counting
Scale-variation
Attention mechanism
Separable non-local
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
PREAI
分享收藏
分享收藏
查看更多内容