arXiv subjects

Jianping Shi

Publications and source records attributed to Jianping Shi.

77 records · Page 5Linked to original sources

arXiv2015

Hierarchical Saliency Detection on Extended CSSD

Complex structures commonly exist in natural images. When an image contains small-scale high-contrast patterns either in the background or foreground, saliency detection could be adversely affected, resulting erroneous and non-uniform saliency assignment. The issue forms a fundamental challenge for prior methods. We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. Different from varying patch sizes or downsizing images, we measure region-based scales. The final saliency values are inferred optimally combining all the saliency cues in different scales using hierarchical inference. Through our inference model, single-scale information is selected to obtain a saliency map. Our method improves detection quality on many images that cannot be handled well traditionally. We also construct an extended Complex Scene Saliency Dataset (ECSSD) to include complex but general natural images.

cs.CV↗

arXiv2015

Bounded-Distortion Metric Learning

Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering. Although a greatly distorted metric space has a high degree of freedom to fit training data, it is prone to overfitting and numerical inaccuracy. This paper presents {\it bounded-distortion metric learning} (BDML), a new metric learning framework which amounts to finding an optimal Mahalanobis metric space with a bounded-distortion constraint. An efficient solver based on the multiplicative weights update method is proposed. Moreover, we generalize BDML to pseudo-metric learning and devise the semidefinite relaxation and a randomized algorithm to approximately solve it. We further provide theoretical analysis to show that distortion is a key ingredient for stability and generalization ability of our BDML algorithm. Extensive experiments on several benchmark datasets yield promising results.

cs.LG↗

arXiv2015

Understanding and Diagnosing Visual Tracking Systems

Several benchmark datasets for visual tracking research have been proposed in recent years. Despite their usefulness, whether they are sufficient for understanding and diagnosing the strengths and weaknesses of different trackers remains questionable. To address this issue, we propose a framework by breaking a tracker down into five constituent parts, namely, motion model, feature extractor, observation model, model updater, and ensemble post-processor. We then conduct ablative experiments on each component to study how it affects the overall result. Surprisingly, our findings are discrepant with some common beliefs in the visual tracking research community. We find that the feature extractor plays the most important role in a tracker. On the other hand, although the observation model is the focus of many studies, we find that it often brings no significant improvement. Moreover, the motion model and model updater contain many details that could affect the result. Also, the ensemble post-processor can improve the result substantially when the constituent trackers have high diversity. Based on our findings, we put together some very elementary building blocks to give a basic tracker which is competitive in performance to the state-of-the-art trackers. We believe our framework can provide a solid baseline when conducting controlled experiments for visual tracking research.

cs.CV↗

arXiv2015

Etching-free transfer of wafer-scale MoS2 films

How to transfer MoS2 films from growth substrates onto target substrates is a critical issue for its practical applications. However, it remains a great challenge to avoid the sample degradation and substrate destruction, since current transfer method inevitably employs a wet chemical etching process. Herein, we develop an etching-free transfer method for transferring wafer-scale MoS2 films onto arbitrary substrates by using ultrasonication. Briefly, the collapse of ultrasonication-generated microbubbles at the interface between polymer-coated MoS2 film and substrates induce sufficient force to delaminate the MoS2 films. Using this method the MoS2 films can be transferred from all the substrates (silica, mica, strontium titanate, sapphire) and remains the original sample morphology and quality. This method guarantees a simple transfer process, allows the reuse of growth substrates, without the presence of any hazardous etchants. The etching-free transfer method may promote the broad applications of MoS2 in electronics, optoelectronics and catalysis.

cond-mat.mtrl-sci↗

arXiv2014

Directly grown monolayer MoS2 on Au foils as efficient hydrogen evolution catalysts

Synthesis of monolayer MoS2 is essential for fulfilling the potential of MoS2 in catalysis, optoelectronics and valleytronics, etc. Herein, we report for the first time the scalable growth of high quality, domain size tunable (edge length from ~ 200 nm to 50 μm), strictly monolayer MoS2 on commercially available Au foils, via a low pressure chemical vapor deposition method. The nanosized triangular MoS2 flakes on Au foils was proved to be an excellent electrocatalyst for hydrogen evolution reaction (HER), featured by a rather low Tafel slope (61 mV/decade) and a supreme exchange current density (38.1 μA/cm2). The abundant active edge sites and the excellent electron coupling between MoS2 and Au foils account for the extraordinary HER activity. Our work presents a sound proof that strictly monolayer MoS2 assembled on a well selected electrode can manifest comparable or even superior HER property than that of nanoparticles or few-layer MoS2 electrocatalyst.

cond-mat.mtrl-sci↗