{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T05:20:23Z","timestamp":1774329623564,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFC2009400"],"award-info":[{"award-number":["2021YFC2009400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tcsvt.2022.3212463","type":"journal-article","created":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T19:36:51Z","timestamp":1664998611000},"page":"1454-1467","source":"Crossref","is-referenced-by-count":19,"title":["ERM: Energy-Based Refined-Attention Mechanism for Video Question Answering"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0179-9988","authenticated-orcid":false,"given":"Fuwei","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering and the National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-4412","authenticated-orcid":false,"given":"Ruomei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}]},{"given":"Yuanmao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051756"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051277"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2897604"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2931534"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3320061"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142526"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref14","first-page":"1","article-title":"Learning from inside: Self-driven Siamese sampling and reasoning for video question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Yu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413868"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002667"},{"key":"ref20","first-page":"11863","article-title":"SimAM: A simple, parameter-free attention module for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475620"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093596"},{"key":"ref25","first-page":"1","article-title":"iPerceive: Applying common-sense reasoning to multi-modal dense video captioning and video question answering","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)","author":"Chadha"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463635"},{"key":"ref28","article-title":"Vision GNN: An image is worth graph of nodes","author":"Han","year":"2022","journal-title":"arXiv:2206.00272"},{"key":"ref29","first-page":"1","article-title":"Two-stream spatiotemporal compositional attention network for VideoQA","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Miyanishi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref31","first-page":"1","article-title":"STAR: A benchmark for situated reasoning in real-world videos","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref34","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Zellers"},{"key":"ref35","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv:2111.12681"},{"key":"ref36","article-title":"All in one: Exploring unified video-language pre-training","author":"Wang","year":"2022","journal-title":"arXiv:2203.07303"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3056031"},{"key":"ref38","article-title":"Fastformer: Additive attention can be all you need","author":"Wu","year":"2021","journal-title":"arXiv:2108.09084"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00323"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00936"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185900"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3414-05.2005"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. 28th Conf. Neural Inf. Process. Syst. (NIPS)","author":"Chung"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref53","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00172"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10061510\/09912407.pdf?arnumber=9912407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:53:52Z","timestamp":1705960432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9912407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":58,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3212463","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}