Junsong Yuan

TL;DR: A Deformable Pose Traversal Convolution Network is proposed that applies one-dimensional convolution to traverse the 3D pose for its representation and optimizes the convolution kernel for each joint, by considering contextual joints with various weights.

TL;DR: Wang et al. as mentioned in this paper proposed 3D dynamic voxel (3DV) to represent 3D motion pattern effectively and efficiently for depth-based 3D action recognition, which achieved an accuracy of 82.4% and 93.5% on NTU RGB+D 120 with the cross-subject and crosssetup test setting respectively.

TL;DR: The development of novel organic photoactive materials, especially non-fullerene acceptors (NFAs), has progressed rapidly in the recent years through the development of new organic photactive materials as discussed by the authors .

TL;DR: This paper exploits the local temporal context of pedestrians in videos and proposes a tube feature aggregation network (TFAN) aiming at enhancing pedestrian detectors against severe occlusions, and devise a temporally discriminative embedding module (TDEM) and a part-based relation module (PRM) to better handle tube drifting and heavy occlusion.