{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:15Z","timestamp":1777865295369,"version":"3.51.4"},"reference-count":53,"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\/100009122","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009122","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020806","name":"ANR","doi-asserted-by":"publisher","award":["ANR-21-FAI1-0002-01"],"award-info":[{"award-number":["ANR-21-FAI1-0002-01"]}],"id":[{"id":"10.13039\/100020806","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\/iccv51701.2025.02265","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24434-24444","source":"Crossref","is-referenced-by-count":0,"title":["Large-Scale Pre-Training for Grounded Video Caption Generation"],"prefix":"10.1109","author":[{"given":"Evangelos","family":"Kazakos","sequence":"first","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"PSL Research University,Inria, © Ecole normale sup©erieure, CNRS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref3","article-title":"End-toend object detection with transformers","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Carion","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01743"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01743"},{"key":"ref6","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref8","article-title":"Epic-kitchens visor benchmark: Video segmentations and object relations","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks","author":"Darkhalil","year":"2022"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00623"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2117"},{"key":"ref15","article-title":"Cotracker3: Simpler and better point tracking by pseudo-labelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Largescale pre-training for grounded video caption generation","author":"Kazakos","year":"2025","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01540-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02212"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref21","article-title":"Groma: Localized visual tokenization for grounding multimodal large language models","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_21"},{"key":"ref23","article-title":"Towards generalist robot learning from internet video: A survey","author":"Robert","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref25","article-title":"Scaling open-vocabulary object detection","author":"Minderer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Pg-video-llava: Pixel grounding large videolanguage models","author":"Munasinghe","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01773"},{"key":"ref28","article-title":"GPT-4 technical report","author":"Achiam","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Learning to imitate object interactions from internet videos","author":"Patel","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref33","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ravi","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"ref38","article-title":"Look at what im doing: Self-supervised spatial grounding of narrations in instructional videos","author":"Tan","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref40","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref42","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01789"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54190-7_7"},{"key":"ref46","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/149"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref50","article-title":"BuboGPT: Enabling visual grounding in multi-modal llms","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref52","article-title":"Dense video object captioning from disjoint supervision","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3127238"}],"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\/11444895.pdf?arnumber=11444895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:32Z","timestamp":1777529552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444895\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02265","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}