Shi-Min Hu

TL;DR: This paper presents a brand new pose-based instance segmentation framework for humans which separates instances based on human pose, not proposal region detection, and demonstrates that this framework can achieve similar accuracy to the detection-based approach, and can moreover better handle occlusion, which is the most challenging problem in the Detection-based framework.

TL;DR: This paper proposes LinkNet, a 2D-3D linked multi-modal network served for online semantic segmentation of RGB-D videos, which is essential for real-time applications such as robot navigation.

TL;DR: Qualitative and quantitative analysis demonstrates the feasibility of the automatic indoor scene modeling approach using deep features from neural networks in understanding and modeling semantics-enriched indoor scenes by evaluating the performance of reconstruction accuracy, computation performance and scene complexity.

TL;DR: Towards Zero Copy (TZC) as discussed by the authors is an efficient IPC technique that can generate messages that can be divided into two parts, one part is transmitted through a socket and the other part uses shared memory, the part within shared memory is never copied or serialized during its lifetime.

TL;DR: A novel rigging‐skinning flow control scheme for fluid animation is proposed to animate fluids intuitively and efficiently, avoiding completely iterative trials or time‐consuming nonlinear optimization.