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.

提出了一种 AppearancePreserving 3D Convolution 方法，由 Appearance-Preserving Module (APM) 和 3D 卷积核组成，可对齐相邻的特征图从而在维持外观表示质量的前提下模拟时间信息，适用于视频人物识别领域，并在三个常用数据集上取得了优于现有方法的成果。

基于外观保持的三维卷积用于视频人物重新识别