{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:55:49Z","timestamp":1763060149457,"version":"3.45.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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","award":["62476029","62225601","U23B2052"],"award-info":[{"award-number":["62476029","62225601","U23B2052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Beijing University of Posts and Telecommunications","award":["2025TSQY08"],"award-info":[{"award-number":["2025TSQY08"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3607747","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T17:31:50Z","timestamp":1758130310000},"page":"8474-8485","source":"Crossref","is-referenced-by-count":0,"title":["Detailed Object Description With Controllable Dimensions"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8793-2174","authenticated-orcid":false,"given":"Xinran","family":"Wang","sequence":"first","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0522-2083","authenticated-orcid":false,"given":"Haiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoteng","family":"Li","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4726-093X","authenticated-orcid":false,"given":"Kongming","family":"Liang","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"China Telecom Artificial Intelligence Technology Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9045-1339","authenticated-orcid":false,"given":"Jun","family":"Guo","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ELECO47770.2019.8990630"},{"key":"ref3","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref4","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2023"},{"article-title":"Qwen-Vl: A versatile vision-language model for understanding, localization, text reading, and beyond","year":"2023","author":"Bai","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"year":"2024","key":"ref9","article-title":"GPT-4o"},{"article-title":"GPT-4 technical report","year":"2024","author":"A.","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_42"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328298"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref17","article-title":"Grounding multimodal large language models to the world","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Peng","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00680"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612274"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755316"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref26","article-title":"Tag2Text: Guiding vision-language model via image tagging","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Huang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref28","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Schuhmann","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_17"},{"key":"ref30","first-page":"76137","article-title":"Dense and aligned captions (DAC) promote compositional reasoning in VL models","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Doveh","year":"2023"},{"article-title":"PixLore: A dataset-driven approach to rich image captioning","year":"2024","author":"Bonilla-Salvador","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3407695"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322329"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref37","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Li","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301279"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1186\/s40001-024-02044-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/QICAR61538.2024.10496601"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-024-10306-z"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-024-07019-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"year":"2024","key":"ref45","article-title":"Llama 3 model card"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_23"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00432"},{"key":"ref51","first-page":"137610","article-title":"Benchmarking complex instruction-following with multiple constraints composition","volume-title":"Proc. 38th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wen","year":"2024"},{"key":"ref52","first-page":"111172","article-title":"FlexCap: Describe anything in images in controllable detail","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Dwibedi","year":"2024"},{"article-title":"Caption anything: Interactive image description with diverse multimodal controls","year":"2023","author":"Wang","key":"ref53"},{"key":"ref54","article-title":"MIA-Bench: Towards better instruction following evaluation of multimodal LLMs","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Qian","year":"2025"},{"article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","year":"2024","author":"Fu","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01263"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01263"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.290"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref62","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Cho","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01255"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_2"},{"key":"ref67","first-page":"71737","article-title":"OMG-LLaVA: Bridging image-level, object-level, pixel-level reasoning and understanding","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"ref69","first-page":"45083","article-title":"Debiasing pretrained generative models by uniformly sampling semantic attributes","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Gerych","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2836461"},{"key":"ref71","first-page":"64681","article-title":"Learning to parameterize visual attributes for open-set fine-grained retrieval","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02124"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref74","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":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%  ChatGPT quality","year":"2023","author":"Chiang","key":"ref77"},{"article-title":"Qwen2-Vl: Enhancing vision-language models perception of the world at any resolution","year":"2024","author":"Wang","key":"ref78"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1405.0312"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11169501.pdf?arnumber=11169501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:53Z","timestamp":1763059493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11169501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3607747","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}