{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:15Z","timestamp":1777888695238,"version":"3.51.4"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62376153,62402318,24Z990200676"],"award-info":[{"award-number":["62376153,62402318,24Z990200676"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01924","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20694-20704","source":"Crossref","is-referenced-by-count":3,"title":["FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text"],"prefix":"10.1109","author":[{"given":"Bingchao","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Ning","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyu","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanang","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Huawei Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Comalign: Compositional alignment in vision-language models","author":"Abdollah","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Alexey","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Internlm2 technical report","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Pixart-: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Prismlayers: Open data for high-quality multi-layer transparent image generative models","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref8","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.6"},{"key":"ref16","article-title":"Openvocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Synthclip: Are we ready for a fully synthetic clip training","author":"Abed Al Kader Hammoud","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00982"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"issue":"4","key":"ref25","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"Krizhevsky","year":"2009","journal-title":"Handbook of Systemic Autoimmune Diseases"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref28","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref30","first-page":"19730","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01069"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref33","article-title":"Cascade-clip: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref35","article-title":"Llava-next: Improved reasoning","author":"Liu","year":"2024","journal-title":"ocr, and world knowledge"},{"key":"ref36","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref38","article-title":"Tulip: Token-length upgraded clip","author":"Najdenkoska","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02546"},{"key":"ref40","article-title":"Im2text: Describing images using 1 million captioned photographs","volume":"24","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02199"},{"key":"ref43","first-page":"2641","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Bryan","year":"2015"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref45","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet","volume-title":"International conference on machine learning","author":"Recht","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_15"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.365"},{"key":"ref50","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02226"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref55","article-title":"Lotlip: Improving language-image pre-training for long text understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02317"},{"key":"ref57","article-title":"Demystifying clip data","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02600"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-05114-1_58"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01330"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00315"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444980.pdf?arnumber=11444980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:46Z","timestamp":1777611286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01924","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}