Images are widely used by companies to advertise their products and promote awareness of their brands.The automatic synthesis of advertising images is challenging because the advertising message must be clearly convey...Images are widely used by companies to advertise their products and promote awareness of their brands.The automatic synthesis of advertising images is challenging because the advertising message must be clearly conveyed while complying with the style required for the product,brand,or target audience.In this study,we proposed a data-driven method to capture individual design attributes and the relationships between elements in advertising images with the aim of automatically synthesizing the input of elements into an advertising image according to a specified style.To achieve this multi-format advertisement design,we created a dataset containing 13280 advertising images with rich annotations that encompassed the outlines and colors of the elements,in addition to the classes and goals of the advertisements.Using our probabilistic models,users guided the style of synthesized advertisements via additional constraints(e.g.,context-based keywords).We applied our method to a variety of design tasks,and the results were evaluated in several perceptual studies,which showed that our method improved users’satisfaction by 7.1%compared to designs generated by nonprofessional students,and that more users preferred the coloring results of our designs to those generated by the color harmony model and Colormind.展开更多
Mineralization of the ZIF-8 in the presence of biomacromolecules has been demonstrated to be a general way for making bioentities@ZIFs composites.The ZIF-8 crystals permit controlled storage and utilization of the bio...Mineralization of the ZIF-8 in the presence of biomacromolecules has been demonstrated to be a general way for making bioentities@ZIFs composites.The ZIF-8 crystals permit controlled storage and utilization of the bioentities,thus can benefit drug delivery,cold-chain breaking etc.With the increasing needs on personal care and distributed manufacturing,automated synthesis controlled by a computer becomes the next challenge.In this work,we designed an automatic synthesis system to prepare PEG mineralized ZIF-8 composite particles.This system is based on flow chemistry with the microfluidic chips fabricated by femtosecond laser micromachining.The particles were synthesized and monitored automatically.Furthermore,this synthesizer could be extended for fabrication of vaccine particles under remote control through internet.展开更多
基金Project supported by the National Science and Technology Innovation 2030 Major Project of the Ministry of Science and Technology of China(No.2018AAA0100700)the National Natural Science Foundation of China(No.61672451)+2 种基金the Provincial Key Research and Development Plan of Zhejiang Province,China(No.2019C03137)the China Postdoctoral Science Foundation(No.2018M630658)the Alibaba-Zhejiang University Joint Institute of Frontier Technologies。
文摘Images are widely used by companies to advertise their products and promote awareness of their brands.The automatic synthesis of advertising images is challenging because the advertising message must be clearly conveyed while complying with the style required for the product,brand,or target audience.In this study,we proposed a data-driven method to capture individual design attributes and the relationships between elements in advertising images with the aim of automatically synthesizing the input of elements into an advertising image according to a specified style.To achieve this multi-format advertisement design,we created a dataset containing 13280 advertising images with rich annotations that encompassed the outlines and colors of the elements,in addition to the classes and goals of the advertisements.Using our probabilistic models,users guided the style of synthesized advertisements via additional constraints(e.g.,context-based keywords).We applied our method to a variety of design tasks,and the results were evaluated in several perceptual studies,which showed that our method improved users’satisfaction by 7.1%compared to designs generated by nonprofessional students,and that more users preferred the coloring results of our designs to those generated by the color harmony model and Colormind.
基金supported by National Natural Science Foundation of China(No.11674340)Key Project of the Shanghai Science and Technology Committee(No.18DZ1112700)。
文摘Mineralization of the ZIF-8 in the presence of biomacromolecules has been demonstrated to be a general way for making bioentities@ZIFs composites.The ZIF-8 crystals permit controlled storage and utilization of the bioentities,thus can benefit drug delivery,cold-chain breaking etc.With the increasing needs on personal care and distributed manufacturing,automated synthesis controlled by a computer becomes the next challenge.In this work,we designed an automatic synthesis system to prepare PEG mineralized ZIF-8 composite particles.This system is based on flow chemistry with the microfluidic chips fabricated by femtosecond laser micromachining.The particles were synthesized and monitored automatically.Furthermore,this synthesizer could be extended for fabrication of vaccine particles under remote control through internet.
