结合多尺度与多层级聚合的卷轴画图像描述模型

打开文本图片集

DOI：10.16652/j.issn.1004-373x.2025.17.007引用格式：，，.结合多尺度与多层级聚合的卷轴画图像描述模型[J].现代电子技术，2025，48（17）：41-47.

关键词：图像描述；卷轴画图像；多尺度特征；非对称卷积；多层级聚合解码；Transformer中图分类号：TN919-34；TP391 文献标识码：A 文章编号：1004-373X（2025）17-0041-07

Scroll painting image caption model combining multi-scale and multi-level aggregation

YUE Chaoyang1，HU Wenjin1²， ZHANG Fujun1 （1.KeyLabotofigsticduraloutinstrutiostnUesityou; 2.SchoolofMathematicsandComputerScience，NorthwestMinzu University，Lanzhou73oo3o，China）

Abstract：Thecrollpaintingimageshavediferentsizesandacertainspatialdistributioncharacteristics，andthetrasforer based encodinglayerisprone tolosingkeyimage information，soascroll painting imagecaptionmodel MMAcombiningmultiscaleandmulti-levelaggregationisproposed.Inthestageofencoding，byintroducingasymmetricconvolutionandmulti-scale featuremodules，theabilityof theconvolutionlayertoobtainspatialinformationcanbeimprovedefectivelyandtheglobaland localmulti-scalecontextualinformationofthescrollpaintingimagecanbeintegratedtoobtainafeaturerepresentationwithrich semanticinforatio.Amulti-evelaggationnetworkisdsigndintestageofeoding.Byggatingtefeatursofit codinglayers，thesemanticinformationofthehigh-levelcodinglayerandthecontentinformationofthelow-levelcodinglayeare utilizedeffctivelytherebyaleviatingtheinformationlossefetivelyExperimentalresultsshowthatthemodelachievsood resultsonthescrollpintingdataset，improving BLEU-4andMETEORby26.7%and0.9%，respectively，incomparisonwiththe NIC （neural image caption） model，and generates more accurate description sentences.

Keywords：imagecaption;scroll paintingimage；multi-scale feature；asymmetricconvolution；multi-levelaggregation decoding; Transformer

0 引言

卷轴画作为我国独特的绘画艺术形式，通过对卷轴画进行图像描述能够帮助人们赏析和理解卷轴画，促进文化交流，同时为卷轴画的研究和数字化保护提供技术支持。（剩余10500字）