{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:52:59Z","timestamp":1781848379993,"version":"3.54.5"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,24]]},"DOI":"10.1109\/iscas66217.2026.11562184","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:06:41Z","timestamp":1781813201000},"page":"952-956","source":"Crossref","is-referenced-by-count":0,"title":["MMCap: Multi-Level CLIP Feature Fusion with Multiway Dynamic Dense Connections for Urban Incivility Scene Captioning"],"prefix":"10.1109","author":[{"given":"Yeping","family":"Zhao","sequence":"first","affiliation":[{"name":"Anhui University,School of Internet,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Ma","sequence":"additional","affiliation":[{"name":"Anhui University,School of Internet,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Civilization Office of Yingshang County, Fuyang City,Fuyang,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohui","family":"Deng","sequence":"additional","affiliation":[{"name":"Anhui University,School of Internet,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinghan","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui University,School of Internet,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoming","family":"Xu","sequence":"additional","affiliation":[{"name":"Anhui University,School of Internet,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/150"},{"key":"ref10","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_32"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645378"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671918"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33163"},{"key":"ref16","article-title":"Urbanfeel: A comprehensive benchmark for temporal and perceptual understanding of city scenes through human perspective","author":"He","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00586"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref19","article-title":"From clip to dino: Visual encoders shout in multi-modal large language models","author":"Jiang","year":"2023"},{"key":"ref20","article-title":"MUDDFormer: Breaking residual bottlenecks in transformers via multiway dynamic dense connections","volume-title":"Forty-second International Conference on Machine Learning","author":"Xiao"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIP65915.2025.11171515"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref27","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref28","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Text summarization branches out","author":"Lin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref31","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"}],"event":{"name":"2026 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Shanghai, China","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["2026 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11561899\/11561804\/11562184.pdf?arnumber=11562184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:28:58Z","timestamp":1781846938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11562184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iscas66217.2026.11562184","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}