High-sensitivity detection of heavy metal ions in solution is critical for environmental monitoring. In this paper, a dual-mode method namely hybrid electrochemical-surface plasmon resonance (SPR) …
In recent years, Siamese network based trackers have significantly advanced the state-of-the-art in real-time tracking. Despite their success, Siamese trackers tend to suffer from high memory costs…
Conventional machine learning algorithms suffer the problem that the model trained on existing data fails to generalize well to the data sampled from other distributions. To tackle this issue, unsu…
In this article, we model a set of pixelwise object segmentation tasks — automatic video segmentation (AVS), image co-segmentation (ICS) and few-shot semantic segmentation (FSS) — in a unified …
We study how investors in peer-to-peer (P2P) lending use their information advantages in decisions on when to place bids. Literature documents that better-informed bidders may withhold bidding unti…
In this paper, we address the issue of data imbalance in learning deep models for visual object tracking. Although it is well known that data distribution plays a crucial role in learning and infer…
We introduce a novel network, called CO-attention siamese network (COSNet), to address the zero-shot video object segmentation task in a holistic fashion. We exploit the inherent correlation among …
We theoreticallydemonstrate the realization of the ultranarrow dual-band perfect absorption at visible range in 3D metamaterials comprising Au vertical split-ring resonators (VSRRs) array above a t…
Microbottle resonators (MBR) have attracted research interest for studying nonlinear optical interactions in last two decades, due to the ultra-tight optical confinement in spaces of three dimensio…