Heng-Da Cheng

TL;DR: This paper proposes a novel game theory based method for tracking two dimensional articulated human poses in monocular video sequences using a new probability scheme of game theory to find optimal solutions of human poses.

TL;DR: Zhang et al. as discussed by the authors decompose breast ultrasound image into layers using Neutro-Connectedness, and then utilize the layers to generate the foreground and background maps; and finally propose a novel objective function to estimate the tumor saliency by integrating the foreground map, background map, adaptive center bias, and region-based correlation cues.

TL;DR: This paper proposes an optimization embedded bagging (OEBag) approach to increase the sensitivity by learning the complex distributions in the minority class more precisely and selectively learns the minority examples that are misclassified easily by referring to examples in out-of-bag.

TL;DR: Experimental results show that this novel image reversible watermarking is proposed based on neural network and parity property can obtain higher capacity and preserve good visual quality.

TL;DR: The essential parallelism and simplicity of the proposed algorithm make it easy to implement by using a VLSI array architecture, and each pixel only needs to perform addition and comparison, and communicate only with its immediate neighbor pixels during the entire computation period.