Dong Wang

TL;DR: Amulet is presented, a generic aggregating multi-level convolutional feature framework for salient object detection that provides accurate salient object labeling and performs favorably against state-of-the-art approaches in terms of near all compared evaluation metrics.

TL;DR: This paper proposes a novel online object tracking algorithm with sparse prototypes, which exploits both classic principal component analysis (PCA) algorithms with recent sparse representation schemes for learning effective appearance models, and introduces l1 regularization into the PCA reconstruction.

TL;DR: A novel deep fully convolutional network model for accurate salient object detection and an effective hybrid upsampling method to reduce the checkerboard artifacts of deconvolution operators in the authors' decoder network are proposed.

TL;DR: In this paper, a shape memory polymer layer was added to the actuator body to enhance its stiffness by up to 120 times without sacrificing flexibility and adaptivity, and the printed Joule-heating circuit and fluidic cooling microchannel enable fast heating and cooling rates and allow the FRST actuator to complete a softening-stiffening cycle within 32 s.

TL;DR: The proposed Least Soft-thresold Squares (LSS) algorithm models the error term with the Gaussian-Laplacian distribution, which can be solved efficiently and derived a LSS distance to measure the difference between an observation sample and the dictionary.