{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:13:34Z","timestamp":1770743614185,"version":"3.49.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172398"],"award-info":[{"award-number":["62172398"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402184"],"award-info":[{"award-number":["62402184"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Science and Technology Program","award":["25069470"],"award-info":[{"award-number":["25069470"]}]},{"name":"Guangdong Provincial Fund for Basic and Applied Basic Research - Regional Joint Fund Project","award":["2023B1515120078"],"award-info":[{"award-number":["2023B1515120078"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tvcg.2025.3642641","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:59:13Z","timestamp":1769633953000},"page":"440-450","source":"Crossref","is-referenced-by-count":0,"title":["DKMap: Interactive Exploration of Vision-Language Alignment in Multimodal Embeddings via Dynamic Kernel Enhanced Projection"],"prefix":"10.1109","volume":"32","author":[{"given":"Yilin","family":"Ye","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxi","family":"Ruan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zikun","family":"Deng","sequence":"additional","affiliation":[{"name":"South China University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511122"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2025.3567053"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3333356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2015.2467552"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2020.0961"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2007.70521"},{"key":"ref8","first-page":"123","article-title":"Perplexity-free t-SNE and twice student tt-SNE","volume-title":"Proceedings of European Symposium on Artificial Neural Networks, Computational Intelligence and Ma-chine Learning","author":"De Bodt"},{"issue":"3","key":"ref9","first-page":"429","article-title":"On the adaptive nadaraya-watson kernel regression estimators","volume":"39","author":"Demir","year":"2010","journal-title":"Hacettepe Journal of Mathematics and Statistics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"},{"key":"ref11","first-page":"12429","article-title":"Neuro-Visualizer: A novel auto-encoder-based loss landscape visualization method with an application in knowledge-guided machine learning","volume-title":"Proc. ICML","author":"Elhamod","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3125576"},{"key":"ref13","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. ICML","author":"Esser","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3327168"},{"key":"ref15","first-page":"27092","article-title":"DataComp: In search of the next generation of multimodal datasets","volume-title":"Proc. NIPS","author":"Gadre","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01457"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.11.045"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/1473871611416549"},{"key":"ref19","author":"Grootendorst","year":"2020","journal-title":"Keybert: Minimal keyword extraction with bert."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2020.3045918"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref22","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00708"},{"key":"ref24","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume-title":"Proc. NIPS","author":"Kirstain","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/pacificvis.2011.5742387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5194\/ica-proc-5-10-2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3471551"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/vast.2018.8802454"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687589"},{"key":"ref31","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. NIPS","author":"Liang","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. NIPS","author":"Liu","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02090"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13672"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01592"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2013.65"},{"key":"ref38","article-title":"UMAP: Uniform manifold ap-proximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-00801-7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2018.2846735"},{"key":"ref41","first-page":"135783","article-title":"A concept-based explainability framework for large multimodal models","volume-title":"Proc. NIPS","author":"Parekh","year":"2024"},{"key":"ref42","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. ICLR","author":"Podell","year":"2024"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision. In","volume-title":"Proc. ICML","author":"Radford","year":"2021"},{"issue":"2","key":"ref44","first-page":"3","article-title":"Hierarchi-cal text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref46","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. NIPS","author":"Schuhmann","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2015.7280736"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140919"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3233\/aic-170729"},{"issue":"1","key":"ref50","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"Van Der Maaten","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"issue":"11","key":"ref51","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114794"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3327153"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2017.2701829"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.50"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1051\/itmconf\/20182300037"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01243"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2010.07.001"},{"key":"ref60","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9878-1_4"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3326913"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642185"},{"key":"ref65","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. NIPS","author":"Xu","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0393-x"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2024.04.003"},{"key":"ref68","article-title":"AKRMap: Adaptive kernel regression for trustworthy visualization of cross-modal embeddings","volume-title":"Proc. ICML","author":"Ye","year":"2025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3229023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/mcg.2025.3555122"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3456387"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3641019"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00766"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2024.09.005"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3170531"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591532"},{"key":"ref77","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11373125\/11363926.pdf?arnumber=11363926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T00:33:46Z","timestamp":1770683626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":77,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3642641","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}