{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T04:04:19Z","timestamp":1751169859825,"version":"3.41.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3581931","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T17:29:19Z","timestamp":1750440559000},"page":"107856-107871","source":"Crossref","is-referenced-by-count":0,"title":["Interaction-Aware Scene Debiasing for Action Recognition"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8696-5687","authenticated-orcid":false,"given":"Randy Cahya","family":"Wihandika","sequence":"first","affiliation":[{"name":"Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6819-4305","authenticated-orcid":false,"given":"Israel","family":"Mendon\u00e7a","sequence":"additional","affiliation":[{"name":"Faculty of Advanced Science and Technology, Kumamoto University, Kumamoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0861-849X","authenticated-orcid":false,"given":"Masayoshi","family":"Aritsugi","sequence":"additional","affiliation":[{"name":"Faculty of Advanced Science and Technology, Kumamoto University, Kumamoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1457843"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/fi14030093"},{"key":"ref12","first-page":"851","article-title":"Why Can\u2019t i dance in the mall? Learning to mitigate scene bias in action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Choi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01823"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190839"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.04.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref18","article-title":"VideoMix: Rethinking data augmentation for video classification","author":"Yun","year":"2020","journal-title":"arXiv:2012.03457"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_14"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"article-title":"Exploring temporally dynamic data augmentation for video recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kim","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01242"},{"key":"ref25","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref27","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3551626.3564941"},{"volume-title":"Detectron2","year":"2019","author":"Wu","key":"ref29"},{"key":"ref30","first-page":"2821","article-title":"Enabling detailed action recognition evaluation through video dataset augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chung"},{"key":"ref31","first-page":"431","article-title":"DEVIAS: Learning disentangled video representations of action and scene for holistic video understanding","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Bae"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/79"},{"key":"ref33","first-page":"5","article-title":"MAC: Mask-augmentation for motion-aware video representation learning","volume-title":"Proc. 33rd Brit. Mach. Vis. Conf. (BMVC)","author":"Akar"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25194"},{"key":"ref35","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341600"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"volume-title":"OpenMMLab\u2019s Next Generation Video Understanding Toolbox and Benchmark","year":"2020","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref47","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11045925.pdf?arnumber=11045925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:27:01Z","timestamp":1751092021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3581931","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}