Graph convolutional networks (GCN) have recently been studied to exploit the graph topology of the human body for skeleton-based action recognition. However, most of these methods unfortunately aggregate messages via an inflexible pattern for various action samples, lacking the awareness of intra-class variety and the suitableness for skeleton sequences, which often contain redundant or even detrimental connections. In this paper, we propose a novel Deformable Graph Convolutional Network (DeGCN) to adaptively capture the most informative joints. The proposed DeGCN learns the deformable sampling locations on both spatial and temporal graphs, enabling the model to perceive discriminative receptive fields. Notably, considering human action is inherently continuous, the corresponding temporal features are defined in a continuous latent space. Furthermore, we design an innovative multi-branch framework, which not only strikes a better trade-off between accuracy and model size, but also elevates the effect of ensemble between the joint and bone modalities remarkably. Extensive experiments show that our proposed method achieves state-of-the-art performances on three widely used datasets, NTU RGB+D, NTU RGB+D 120, and NW-UCLA.

3-D hand pose estimation is an essential problem for human–computer interaction. Most of the existing depth-based hand pose estimation methods consume 2-D depth map or 3-D volume via 2-D/3-D convolutional neural networks. In this paper, we propose a deep semantic hand pose regression network (SHPR-Net) for hand pose estimation from point sets, which consists of two subnetworks: a semantic segmentation subnetwork and a hand pose regression subnetwork. The semantic segmentation network assigns semantic labels for each point in the point set. The pose regression network integrates the semantic priors with both input and late fusion strategy and regresses the final hand pose. Two transformation matrices are learned from the point set and applied to transform the input point cloud and inversely transform the output pose, respectively, which makes the SHPR-Net more robust to geometric transformations. Experiments on NYU, ICVL, and MSRA hand pose data sets demonstrate that our SHPR-Net achieves high performance on par with the start-of-the-art methods. We also show that our method can be naturally extended to hand pose estimation from the multi-view depth data and achieves further improvement on the NYU data set.

Exploiting both RGB (2D appearance) and Depth (3D geometry) information can improve the performance of semantic segmentation. However, due to the inherent difference between the RGB and Depth information, it remains a challenging problem in how to integrate RGB-D features effectively. In this letter, to address this issue, we propose a Non-local Aggregation Network (NANet), with a well-designed Multi-modality Non-local Aggregation Module (MNAM), to better exploit the non-local context of RGB-D features at multi-stage. Compared with most existing RGB-D semantic segmentation schemes, which only exploit local RGB-D features, the MNAM enables the aggregation of non-local RGB-D information along both spatial and channel dimensions. The proposed NANet achieves comparable performances with state-of-the-art methods on popular RGB-D benchmarks, NYUDv2 and SUN-RGBD.

Dynamic hand gesture recognition has attracted increasing attention because of its importance for human–computer interaction. In this paper, we propose a novel motion feature augmented network (MFA-Net) for dynamic hand gesture recognition from skeletal data. MFA-Net exploits motion features of finger and global movements to augment features of deep network for gesture recognition. To describe finger articulated movements, finger motion features are extracted from the hand skeleton sequence via a variational autoencoder. Global motion features are utilized to represent the global movements of hand skeleton. These motion features along with the skeleton sequence are then fed into three branches of a recurrent neural network (RNN), which augment the motion features for RNN and improve the classification performance. The proposed MFA-Net is evaluated on two challenging skeleton-based dynamic hand gesture datasets, including DHG-14/28 dataset and SHREC’17 dataset. Experimental results demonstrate that our proposed method achieves comparable performance on DHG-14/28 dataset and better performance on SHREC’17 dataset when compared with start-of-the-art methods.

Fast and robust object grasping in clutter is a crucial component of robotics. Most current works resort to the whole observed point cloud for 6-Dof grasp generation, ignoring the guidance information excavated from global semantics, thus limiting high-quality grasp generation and real-time performance. In this work, we show that the widely used heatmaps are underestimated in the efficiency of 6-Dof grasp generation. Therefore, we propose an effective local grasp generator combined with grasp heatmaps as guidance, which infers in a global-to-local semantic-to-point way. Specifically, Gaussian encoding and the grid-based strategy are applied to predict grasp heatmaps as guidance to aggregate local points into graspable regions and provide global semantic information. Further, a novel non-uniform anchor sampling mechanism is designed to improve grasp accuracy and diversity. Benefiting from the high-efficiency encoding in the image space and focusing on points in local graspable regions, our framework can perform high-quality grasp detection in real-time and achieve state-of-the-art results. In addition, real robot experiments demonstrate the effectiveness of our method with a success rate of 94% and a clutter completion rate of 100%.