{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:14:09Z","timestamp":1780370049650,"version":"3.54.1"},"reference-count":8,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"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":[[2022,7,6]]},"DOI":"10.1109\/icce-taiwan55306.2022.9869188","type":"proceedings-article","created":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T15:41:03Z","timestamp":1662046863000},"page":"453-454","source":"Crossref","is-referenced-by-count":1,"title":["Scene Retrieval in Soccer Videos by Spatial-temporal Attention with Video Vision Transformer"],"prefix":"10.1109","author":[{"given":"Yaozong","family":"Gan","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, Hokkaido University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ren","family":"Togo","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref4","article-title":"A survey of transformers","author":"lin","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"Proceedings of International Conference on Learning Representations (ICLR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143012"},{"key":"ref7","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"0","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446280"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3347318.3355516"}],"event":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","location":"Taipei, Taiwan","start":{"date-parts":[[2022,7,6]]},"end":{"date-parts":[[2022,7,8]]}},"container-title":["2022 IEEE International Conference on Consumer Electronics - Taiwan"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9868970\/9868972\/09869188.pdf?arnumber=9869188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T16:25:00Z","timestamp":1663604700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9869188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":8,"URL":"https:\/\/doi.org\/10.1109\/icce-taiwan55306.2022.9869188","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]}}}