{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T03:51:20Z","timestamp":1773114680791,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209469","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA"],"prefix":"10.1109","author":[{"given":"Zijie","family":"Song","sequence":"first","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]},{"given":"Zhenzhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]},{"given":"Yixiao","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01275"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref4","article-title":"Self-chained image-language model for video localization and question answering","volume":"36","author":"Yu","year":"2024","journal-title":"NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29954"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00221"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3097171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243465"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25296"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3303451"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref21","first-page":"2917","article-title":"Revisiting the","author":"Buch","year":"2022","journal-title":"video\" in video-language understanding,\" in CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/94"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref26","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","author":"He","year":"2021","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00261"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01272"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/178"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548035"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"ref32","article-title":"Paxion: Patching action knowledge in video-language foundation models","volume":"36","author":"Wang","year":"2024","journal-title":"NIPS"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209469.pdf?arnumber=11209469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:43:32Z","timestamp":1761889412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209469","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}