论文标题
针对基于视频的人重新识别外观的3D卷积
Appearance-Preserving 3D Convolution for Video-based Person Re-identification
论文作者
论文摘要
由于人的检测结果不完善和姿势变化，因此在基于视频的人重新识别（REID）中，时间出现不可避免。在这种情况下，3D卷积可能会破坏人视频剪辑的外观表示，因此里德是有害的。为了解决这个问题，我们提出了由两个组成部分组成的外观表现为3D卷积（AP3D）：外观保留模块（APM）和3D卷积内核。随着APM在像素级别的相邻特征图对齐时，以下3D卷积可以建模有关保持外观表示质量的前提的时间信息。通过简单地用AP3D替换原始的3D卷积内核来将AP3D与现有的3D Convnets结合使用。广泛的实验证明了AP3D对基于视频的REID的有效性，并且在三个广泛使用的数据集上的结果超过了最新的。代码可在以下网址提供：https：//github.com/guxinqian/ap3d。
Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID). In this case, 3D convolution may destroy the appearance representation of person video clips, thus it is harmful to ReID. To address this problem, we propose AppearancePreserving 3D Convolution (AP3D), which is composed of two components: an Appearance-Preserving Module (APM) and a 3D convolution kernel. With APM aligning the adjacent feature maps in pixel level, the following 3D convolution can model temporal information on the premise of maintaining the appearance representation quality. It is easy to combine AP3D with existing 3D ConvNets by simply replacing the original 3D convolution kernels with AP3Ds. Extensive experiments demonstrate the effectiveness of AP3D for video-based ReID and the results on three widely used datasets surpass the state-of-the-arts. Code is available at: https://github.com/guxinqian/AP3D.
