论文标题
沙发网：二阶和一阶注意网络，用于人群计数
SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting
论文作者
论文摘要
由于其在智能城市中的广泛应用，近年来，从图像/视频中计数的自动人群都吸引了更多的关注。但是，建模茂密的人群的头脑具有挑战性，大多数现有作品都变得不那么可靠。为了获得适当的人群代表，在这项工作中，我们提出了SOFA-NET（二阶和一阶注意网络）：提取二阶统计数据，以保留对频道的空间信息的选择性，以确保狭窄的头部统计数据，而一阶统计数据可以增强头部特征区域的特征区域歧视，以用作辅助信息。通过多流构建结构，所提出的二阶/一阶统计信息被学习并转化为可靠表示的精炼的注意力。我们在四个公共数据集上评估了我们的方法，并在大多数公共数据集上达到了最先进的方法。还进行了广泛的实验，以研究拟议的沙发网中的组件，结果表明，在具有挑战性的情况下，第二阶/一阶统计数据对人群进行建模。据我们所知，我们是第一项探索人群计数的第二阶/一阶统计数据的工作。
Automated crowd counting from images/videos has attracted more attention in recent years because of its wide application in smart cities. But modelling the dense crowd heads is challenging and most of the existing works become less reliable. To obtain the appropriate crowd representation, in this work we proposed SOFA-Net(Second-Order and First-order Attention Network): second-order statistics were extracted to retain selectivity of the channel-wise spatial information for dense heads while first-order statistics, which can enhance the feature discrimination for the heads' areas, were used as complementary information. Via a multi-stream architecture, the proposed second/first-order statistics were learned and transformed into attention for robust representation refinement. We evaluated our method on four public datasets and the performance reached state-of-the-art on most of them. Extensive experiments were also conducted to study the components in the proposed SOFA-Net, and the results suggested the high-capability of second/first-order statistics on modelling crowd in challenging scenarios. To the best of our knowledge, we are the first work to explore the second/first-order statistics for crowd counting.
