skip to main content

Search for: All records

Creators/Authors contains: "Xiong, H."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. The key challenge in photorealistic style transfer is that an algorithm should faithfully transfer the style of a reference photo to a content photo while the generated image should look like one captured by a camera. Although several photorealistic style transfer algorithms have been proposed, they need to rely on post- and/or pre-processing to make the generated images look photorealistic. If we disable the additional processing, these algorithms would fail to produce plausible photorealistic stylization in terms of detail preservation and photorealism. In this work, we propose an effective solution to these issues. Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration. In the C-step, we propose a dense auto-encoder named PhotoNet based on a carefully designed pre-analysis. PhotoNet integrates a feature aggregation module (BFA) and instance normalized skip links (INSL). To generate faithful stylization, we introduce multiple style transfer modules in the decoder and INSLs. PhotoNet significantly outperforms existing algorithms in terms of both efficiency and effectiveness. In the P-step, we adopt a neural architecture search method to accelerate PhotoNet. We propose an automatic network pruning framework in the manner of teacher-student learning for photorealistic stylization. Themore »network architecture named PhotoNAS resulted from the search achieves significant acceleration over PhotoNet while keeping the stylization effects almost intact. We conduct extensive experiments on both image and video transfer. The results show that our method can produce favorable results while achieving 20-30 times acceleration in comparison with the existing state-of-the-art approaches. It is worth noting that the proposed algorithm accomplishes better performance without any pre- or post-processing.« less
  2. Abstract

    Being the lightest, most mobile atom that exists, hydrogen plays an important role in the chemistry of hydrocarbons, proteins and peptides and most biomolecules. Hydrogen can undergo transfer, exchange and migration processes, having considerable impact on the chemical behavior of these molecules. Although much has been learned about reaction dynamics involving one hydrogen atom, less is known about those processes where two or more hydrogen atoms participate. Here we show that single and double hydrogen migrations occurring in ethanol cations and dications take place within a few hundred fs to ps, using a 3D imaging and laser pump-probe technique. For double hydrogen migration, the hydrogens are not correlated, with the second hydrogen migration promoting the breakup of the C–O bond. The probability of double hydrogen migration is quite significant, suggesting that double hydrogen migration plays a more important role than generally assumed. The conclusions are supported by state-of-the-art molecular dynamics calculations.