{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:12Z","timestamp":1781761872906,"version":"3.54.5"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11556982","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Prompt-to-Gesture: Measuring the Capabilities of Image-to-Video Deictic Gesture Generation"],"prefix":"10.1109","author":[{"given":"Hassan","family":"Ali","sequence":"first","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doreen","family":"Jirak","sequence":"additional","affiliation":[{"name":"University of Antwerp,Behavioral Lab,Department of Product Development,Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","author":"Bao","year":"2024"},{"key":"ref2","volume-title":"Video Generation Models as World simulators","author":"Brooks","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.humov.2009.07.003"},{"key":"ref4","article-title":"Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Dai"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616117"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2011.01100.x"},{"key":"ref8","article-title":"Visual Hand Gesture Recognition with Deep Learning: A Comprehensive Review of Methods, Datasets, Challenges and Future Research Directions","author":"Foteinos","year":"2025","journal-title":"arXiv, 2507.04465"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104095"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2025.1721093"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3421992"},{"key":"ref13","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. NIPS\u201917, page 6629-6640","author":"Heusel","year":"2017"},{"key":"ref14","volume-title":"Imagen Video: High Definition Video Generation with Diffusion Models. arXiv, 2210.02303","author":"Ho","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.53"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05109-w"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2023.2180235"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3329370"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref20","first-page":"33","article-title":"Hand Gesture Recognition Systems: A Review of Methods, Datasets, and Emerging Trends","volume":"187","author":"Khan","year":"2025","journal-title":"International Journal of Computer Applications"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687648"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616120"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3656374"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"ref25","volume-title":"Zero-Shot 4D HumanScene Interaction by Video Generation. arXiv, 2412.18600","author":"Li","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01865"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3593428"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01017"},{"key":"ref30","volume-title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models. arXiv, 2402.17177","author":"Liu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61042.2026.00099"},{"key":"ref32","volume-title":"Pointing-Guided Target Estimation via Transformer-Based Attention. Artificial Neural Networks and Machine Learning - ICANN 2025","author":"M\u00f6ller","year":"2025"},{"key":"ref33","article-title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","volume-title":"Workshop on Foundation Models Meet Embodied Agents at CVPR 2025","author":"Patel"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193251"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08645-8_54"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01173-6"},{"key":"ref37","article-title":"Learning Transferable Visual Models from Natural Language Supervision","volume-title":"International Conference on Machine Learning.","author":"Radford"},{"key":"ref38","article-title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","volume-title":"The Eleventh International Conference on Learning Representations","author":"Singer"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref40","volume-title":"Towards Accurate Generative Models of Video: A New Metric & Challenges. arXiv, 1812.01717","author":"Unterthiner","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3570169"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3012092"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128780"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref45","volume-title":"MediaPipe Hands: On-Device Real-time Hand Tracking. arXiv, 2006.10214","author":"Zhang","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3610661.3616552"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00090"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11556982.pdf?arnumber=11556982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:52:17Z","timestamp":1781758337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11556982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11556982","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}