{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:55:07Z","timestamp":1771613707338,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"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":[],"published-print":{"date-parts":[[2024,5,27]]},"DOI":"10.1109\/fg59268.2024.10581994","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T17:40:08Z","timestamp":1720719608000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["Aligning Actions and Walking to LLM-Generated Textual Descriptions"],"prefix":"10.1109","author":[{"given":"Radu","family":"Chivereanu","sequence":"first","affiliation":[{"name":"National University of Science and Technology Politehnica Bucharest"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Cosma","sequence":"additional","affiliation":[{"name":"National University of Science and Technology Politehnica Bucharest"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy","family":"Catruna","sequence":"additional","affiliation":[{"name":"National University of Science and Technology Politehnica Bucharest"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Razvan","family":"Rughinis","sequence":"additional","affiliation":[{"name":"National University of Science and Technology Politehnica Bucharest"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emilian","family":"Radoi","sequence":"additional","affiliation":[{"name":"National University of Science and Technology Politehnica Bucharest"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"issue":"3","key":"ref2","article-title":"Improving image generation with better captions","volume-title":"Computer Science","volume":"2","author":"Betker","year":"2023"},{"key":"ref3","article-title":"Utilizing chatgpt generated data to retrieve depression symptoms from social media","author":"Bucur","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Gaitpt: Skeletons are all you need for gait recognition","author":"Catruna","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s22186803"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/fg59268.2024.10581944"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.036"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.10293"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"ref12","article-title":"The kinetics human action video dataset","volume":"abs\/1705.06950","author":"Kay","year":"2017","journal-title":"CoRR"},{"key":"ref13","author":"Li","year":"2023","journal-title":"Angle-optimized text embeddings"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.647"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref18","article-title":"Multi-track timeline control for text-driven 3d human motion generation","author":"Petrovich","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref20","author":"Qin","year":"2024","journal-title":"Diffusiongpt: Llm-driven text-to-image generation system"},{"key":"ref21","first-page":"18","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"Jul 2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 8748\u20138763"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4convai-1.5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref25","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Sohn","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref27","author":"Veselovsky","year":"2023","journal-title":"Generating faithful synthetic data with large language models: A case study in computational social science"},{"key":"ref28","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"1324","article-title":"Large language models for healthcare data augmentation: An example on Patient-Trial matching","volume-title":"AMIA Annu Symp Proc","author":"Yuan","year":"2024"},{"key":"ref30","author":"Zhao","year":"2023","journal-title":"A survey of large language models"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref32","article-title":"Large language models for information retrieval: A survey","volume":"abs\/2308.07107","author":"Zhu","year":"2023","journal-title":"CoRR"}],"event":{"name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Istanbul, Turkiye","start":{"date-parts":[[2024,5,27]]},"end":{"date-parts":[[2024,5,31]]}},"container-title":["2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10581880\/10581860\/10581994.pdf?arnumber=10581994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:05:10Z","timestamp":1721279110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10581994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,27]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/fg59268.2024.10581994","relation":{},"subject":[],"published":{"date-parts":[[2024,5,27]]}}}