{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:37Z","timestamp":1761894697424,"version":"build-2065373602"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210222","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["3D-Contrastive Anchors and Structure Enhancement for Multi-modal Representations"],"prefix":"10.1109","author":[{"given":"Mingkai","family":"Sheng","sequence":"first","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jichao","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref2","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML.","author":"Li","year":"2023"},{"key":"ref3","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref4","first-page":"38728","article-title":"mplug-2: A modularized multi-modal foundation model across text, image and video","volume-title":"ICML.","author":"Haiyang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref6","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"ACL"},{"key":"ref11","first-page":"2425","article-title":"Vqa: Visual question answering","author":"Stanislaw","year":"2015","journal-title":"ICCV"},{"article-title":"Microsoft coco captions: Data collection and evaluation server","year":"2015","author":"Xinlei","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref15","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML.","author":"Chen","year":"2020"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref16"},{"key":"ref17","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML.","author":"Li","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687608"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687739"},{"key":"ref20","first-page":"5238","article-title":"Winoground: Probing vision and language models for visiolinguistic compositionality","author":"Tristan","year":"2022","journal-title":"CVPR"},{"article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","year":"2022","author":"Mert","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"ref23","first-page":"503","article-title":"E2e-vlp: End-to-end vision-language pre-training enhanced by visual learning","author":"Haiyang","year":"2021","journal-title":"ACL"},{"key":"ref24","first-page":"104","article-title":"Uniter: Universal image-text representation learning","volume-title":"ECCV.","author":"Yen-Chun","year":"2020"},{"key":"ref25","first-page":"2592","article-title":"UNIMO: Towards unified-modal understanding and generation via cross-modal contrastive learning","author":"Wei","year":"2021","journal-title":"ACL"},{"key":"ref26","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Hangbo","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref28","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"ICML.","author":"Jaemin","year":"2021"},{"key":"ref29","article-title":"How much can clip benefit vision-and-language tasks?","author":"Shen","year":"2022","journal-title":"ICLR"},{"key":"ref30","first-page":"18166","article-title":"An empirical study of training end-to-end vision-and-language transformers","author":"Zi-Yi","year":"2022","journal-title":"CVPR"},{"key":"ref31","first-page":"740","article-title":"Microsoft coco: Common objects in context","volume-title":"ECCV.","author":"Tsung-Yi","year":"2014"},{"key":"ref32","first-page":"32","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"Ranjay","year":"2017","journal-title":"IJCV"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref34","article-title":"Im2text: Describing images using 1 million captioned photographs","volume":"24","author":"Ordonez","year":"2011","journal-title":"NeurIPS"},{"key":"ref35","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Jiasen","year":"2019","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref37","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1075"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210222.pdf?arnumber=11210222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:58Z","timestamp":1761888838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210222\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210222","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}