{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T07:44:20Z","timestamp":1782373460899,"version":"3.54.5"},"reference-count":81,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611454","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"440-447","source":"Crossref","is-referenced-by-count":2,"title":["Incorporating Scene Graphs into Pre-trained Vision-Language Models for Multimodal Open-vocabulary Action Recognition"],"prefix":"10.1109","author":[{"given":"Chao","family":"Wei","sequence":"first","affiliation":[{"name":"Tsinghua University,BNRist, THUAI,Department of Computer Science,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist, THUAI,Department of Computer Science,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534280"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083152"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01227"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/app12010004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref12","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"ref23","article-title":"Language conditioned spatial relation reasoning for 3d object grounding","volume":"abs\/2211.09646","author":"Chen","year":"2022","journal-title":"ArXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref27","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref28","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref29","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref31","article-title":"Coca: Contrastive captioners are image-text foundation models. arxiv 2022","author":"Yu"},{"key":"ref32","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref33","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"},{"key":"ref34","article-title":"Flamingo: a visual language model for few-shot learning, 2022","author":"Alayrac"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref36","article-title":"Multi-modal self-supervision from generalized data transformations","author":"Patrick","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref42","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref45","article-title":"Devise: A deep visual-semantic embedding model","volume":"26","author":"Frome","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref47","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014"},{"key":"ref48","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017"},{"key":"ref49","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume":"33","author":"Alayrac","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref52","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01021"},{"key":"ref56","article-title":"Bringing image scene structure to video via frame-clip consistency of object tokens","volume-title":"Thirty-Sixth Conference on Neural Information Processing Systems","author":"Avraham"},{"key":"ref57","article-title":"What can neural networks reason about?","volume-title":"International Conference on Learning Representations","author":"Xu"},{"key":"ref58","article-title":"Relational deep reinforcement learning","author":"Zambaldi","year":"2018"},{"key":"ref59","article-title":"Learning object detection from captions via textual scene attributes","volume":"abs\/2009.14558","author":"Jerbi","year":"2020","journal-title":"ArXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref62","article-title":"Compositional video synthesis with action graphs","author":"Bar","year":"2021","journal-title":"ICML"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref64","article-title":"Teaching structured vision&language concepts to vision&language models","author":"Doveh","year":"2022"},{"key":"ref65","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"International Conference on Learning Representations","author":"Yuksekgonul"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref68","first-page":"5","article-title":"Openclip","volume":"4","author":"Ilharco","year":"2021","journal-title":"Zenodo"},{"key":"ref69","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref70","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref75","article-title":"Transferring textual knowledge for visual recognition","author":"Wu","year":"2022"},{"key":"ref76","article-title":"Video-text modeling with zero-shot transfer from contrastive captioners","author":"Yan","year":"2022"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506179"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_24"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611454.pdf?arnumber=10611454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:17:59Z","timestamp":1723349879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611454","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}