{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:23:34Z","timestamp":1784258614827,"version":"3.55.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3339661","type":"journal-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:29:11Z","timestamp":1702495751000},"page":"3156-3168","source":"Crossref","is-referenced-by-count":59,"title":["X2-VLM: All-in-One Pre-Trained Model for Vision-Language Tasks"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1872-7534","authenticated-orcid":false,"given":"Yan","family":"Zeng","sequence":"first","affiliation":[{"name":"ByteDance Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9173-7400","authenticated-orcid":false,"given":"Xinsong","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9628-3487","authenticated-orcid":false,"given":"Hang","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0606-5214","authenticated-orcid":false,"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3269-6992","authenticated-orcid":false,"given":"Jipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4668-3348","authenticated-orcid":false,"given":"Wangchunshu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref3","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref4","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref5","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref6","article-title":"WenLan: Bridging vision and language by large-scale multi-modal pre-training","author":"Huo","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref8","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Adv. Neural Inf. Process. Syst.: Annu. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref9","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref10","first-page":"1","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.: Annu. Conf. Neural Inf. Process. Syst.","author":"Gan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"ref20","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref22","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref23","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00414"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.293"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.315"},{"key":"ref29","first-page":"91","article-title":"Faster R- CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.: Annu. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","article-title":"BEIT V2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01763"},{"key":"ref35","article-title":"VL-BEiT: Generative vision-language pretraining","author":"Bao","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.42"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.119"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref42","article-title":"Violet: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00638"},{"key":"ref44","article-title":"CLIP-VIP: Adapting pre-trained image-text model to video-language representation alignment","author":"Xue","year":"2022"},{"key":"ref45","article-title":"Hunyuan_tvr for text-video retrivial","author":"Min","year":"2022"},{"key":"ref46","article-title":"Zero-shot video question answering via frozen bidirectional language models","author":"Yang","year":"2022"},{"key":"ref47","article-title":"OmniVL: One foundation model for image-language and video-language tasks","author":"Wang","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00397"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref52","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.: 25th Annu. Conf. Neural Inf. Process. Syst.","author":"Ordonez"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref58","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00272"},{"key":"ref60","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.873"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref64","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref67","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","author":"Wang","year":"2021"},{"key":"ref68","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref69","first-page":"13042","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.393"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref72","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00680"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2066"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896494"},{"key":"ref80","article-title":"IGLUE: A benchmark for transfer learning across modalities, tasks, and languages","author":"Bugliarello","year":"2022"},{"key":"ref81","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10356651.pdf?arnumber=10356651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:37:27Z","timestamp":1712691447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10356651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":81,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3339661","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}