{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T23:35:18Z","timestamp":1784158518587,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Jiangsu Province Carbon Peak Carbon Neutrality Science and Technology Innovation Special Fund Project","award":["BT2025029"],"award-info":[{"award-number":["BT2025029"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576091"],"award-info":[{"award-number":["62576091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Southeast University Big Data Computing Center"},{"name":"Southeast University Kunpeng & Ascend Center of Cultivation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3665006","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:48Z","timestamp":1771276068000},"page":"5487-5496","source":"Crossref","is-referenced-by-count":1,"title":["L-CLIPScore: A Lightweight Embedding-Based Captioning Metric for Evaluating and Training"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1268-6453","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6077-6704","authenticated-orcid":false,"given":"Yingzhe","family":"Peng","sequence":"additional","affiliation":[{"name":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8276-2679","authenticated-orcid":false,"given":"Xu","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3261-642X","authenticated-orcid":false,"given":"Ruoxi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4959-8878","authenticated-orcid":false,"given":"Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-5053","authenticated-orcid":false,"given":"Fei","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning CNN-LSTM architectures for image caption generation","author":"Soh","year":"2016","journal-title":"Dept. Comput. Sci., Stanford Univ"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref10","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358411"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.eval4nlp-1.4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747440"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.29"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref17","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.253"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"ref21","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"ref23","article-title":"CLIP-TD: CLIP targeted distillation for vision-language tasks","author":"Wang","year":"2022"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref25","first-page":"6298","article-title":"SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Long","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref30","article-title":"Compact bidirectional transformer for image captioning","author":"Zhou","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3241517"},{"key":"ref33","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref34","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1220"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01740"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref45","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref47","article-title":"Pruning filters for efficient ConvNets","author":"Li","year":"2016"},{"key":"ref48","article-title":"Vision transformer pruning","author":"Zhu","year":"2021"},{"key":"ref49","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref52","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref53","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref56","first-page":"7324","article-title":"Making convolutional networks shift-invariant again","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref60","article-title":"From images to sentences through scene description graphs using commonsense reasoning and knowledge","author":"Aditya","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref64","first-page":"5579","article-title":"VinVL: Revisiting visual representations in vision-language models","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Gao","year":"2021"},{"key":"ref65","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.93"},{"key":"ref67","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016"},{"key":"ref68","article-title":"Spontaneous reward hacking in iterative self-refinement","author":"Pan","year":"2024"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11397221.pdf?arnumber=11397221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:53:36Z","timestamp":1783108416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3665006","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}