论文标题
AFE-CNN：具有动作功能增强功能的基于3D骨架的动作识别
AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement
论文作者
论文摘要
现有的基于3D骨架的动作识别方法通过将手工制作的动作功能编码为图像格式和CNN解码，从而达到了令人印象深刻的性能。但是，这种方法在两种方面受到限制：a）手工制作的动作功能很难处理具有挑战性的动作，b）它们通常需要复杂的CNN模型来提高动作识别精度，这通常会发生重大计算负担。为了克服这些局限性，我们引入了一种新颖的AFE-CNN，它致力于增强基于3D骨架的动作的特征，以适应具有挑战性的动作。我们提出功能从关键关节，骨向量，关键框架和时间视角增强模块，因此，AFE-CNN对摄像机视图和身体大小的变化更为强大，并显着提高了对挑战性动作的识别精度。此外，我们的AFE-CNN采用了轻巧的CNN模型来增强动作功能的图像，从而确保了比最先进的方法低得多的计算负担。我们在三个基于基准骨架的动作数据集上评估了AFE-CNN：NTU RGB+D，NTU RGB+D 120和UTKINECT-ACTION3D，并具有广泛的实验结果，这表明了我们对AFE-CNN的出色表现。
Existing 3D skeleton-based action recognition approaches reach impressive performance by encoding handcrafted action features to image format and decoding by CNNs. However, such methods are limited in two ways: a) the handcrafted action features are difficult to handle challenging actions, and b) they generally require complex CNN models to improve action recognition accuracy, which usually occur heavy computational burden. To overcome these limitations, we introduce a novel AFE-CNN, which devotes to enhance the features of 3D skeleton-based actions to adapt to challenging actions. We propose feature enhance modules from key joint, bone vector, key frame and temporal perspectives, thus the AFE-CNN is more robust to camera views and body sizes variation, and significantly improve the recognition accuracy on challenging actions. Moreover, our AFE-CNN adopts a light-weight CNN model to decode images with action feature enhanced, which ensures a much lower computational burden than the state-of-the-art methods. We evaluate the AFE-CNN on three benchmark skeleton-based action datasets: NTU RGB+D, NTU RGB+D 120, and UTKinect-Action3D, with extensive experimental results demonstrate our outstanding performance of AFE-CNN.
