{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:18:11Z","timestamp":1778051891256,"version":"3.51.4"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00298","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3047-3056","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation"],"prefix":"10.1109","author":[{"given":"Huaying","family":"Zhang","sequence":"first","affiliation":[{"name":"OMRON SINIC X Corp.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corp.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tosho","family":"Hirasawa","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corp.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2025.101253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref7","volume-title":"Vision-language-action models for robotics: A review towards real-world applications","author":"Kawaharazuka","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref9","article-title":"Improving llm video understanding with 16 frames per second","author":"Li","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00147"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref12","article-title":"Multi-granularity correspondence learning from long-term noisy videos","volume-title":"Int. Conf. Learn. Represent","author":"Lin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-42682-7_16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02226"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00438"},{"key":"ref19","article-title":"Position: will we run out of data? limits of llm scaling based on humangenerated data","volume-title":"Int. Conf. Machine Learning","author":"Villalobos"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28338"},{"key":"ref21","article-title":"Selftaught evaluators","author":"Wang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34745"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref26","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref27","article-title":"MMEgo: Towards building egocentric multimodal LLMs for video QA","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ye"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492480.pdf?arnumber=11492480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:32:45Z","timestamp":1778049165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00298","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}