{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T02:04:38Z","timestamp":1779501878554,"version":"3.53.1"},"reference-count":30,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.patrec.2026.04.019","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T23:38:59Z","timestamp":1776728339000},"page":"58-65","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FGFDL: Frame grouping and feature dissimilarity learning for reverse video recognition"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3070-1479","authenticated-orcid":false,"given":"Xianyi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.patrec.2026.04.019_bib0001","first-page":"1218","article-title":"Timeline editing of objects in video","volume":"19","author":"Lu","year":"2012","journal-title":"IEEE Trans. Vis. Comput. Graph"},{"key":"10.1016\/j.patrec.2026.04.019_bib0002","article-title":"Tenet [Film]","author":"Nolan","year":"2020","journal-title":"Warner Bros"},{"key":"10.1016\/j.patrec.2026.04.019_bib0003","series-title":"2018 IEEE\/CVF Conference on CVPR","first-page":"7794","article-title":"Non-local neural networks","author":"Wang","year":"2018"},{"key":"10.1016\/j.patrec.2026.04.019_bib0004","series-title":"2017 IEEE Conference on CVPR","first-page":"4724","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.patrec.2026.04.019_bib0005","series-title":"2019 IEEE\/CVF ICCV","first-page":"6201","article-title":"Slowfast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"key":"10.1016\/j.patrec.2026.04.019_bib0006","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.patrec.2025.06.010","article-title":"Domain generalization using action sequences for egocentric action recognition","volume":"196","author":"Nasirimajd","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.04.019_bib0007","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.patrec.2024.10.003","article-title":"Visual-guided hierarchical iterative fusion for multi-modal video action recognition","volume":"186","author":"Zhang","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.04.019_bib0008","series-title":"2020 IEEE\/CVF Conference on CVPR","first-page":"200","article-title":"X3D: Expanding architectures for efficient video recognition","author":"Feichtenhofer","year":"2020"},{"key":"10.1016\/j.patrec.2026.04.019_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126617","article-title":"Self-attention-based long temporal sequence modeling method for temporal action detection","volume":"554","author":"Huang","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patrec.2026.04.019_bib0010","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.patrec.2026.04.019_bib0011","series-title":"2021 IEEE\/CVF ICCV","first-page":"6804","article-title":"Multiscale vision transformers","author":"Fan","year":"2021"},{"key":"10.1016\/j.patrec.2026.04.019_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on CVPR","first-page":"12295","article-title":"Visual chirality","author":"Lin","year":"2020"},{"issue":"3","key":"10.1016\/j.patrec.2026.04.019_bib0013","first-page":"3492","article-title":"Mirror detection with the visual chirality cue","volume":"45","author":"Tan","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patrec.2026.04.019_bib0014","series-title":"Proceedings of the IEEE\/CVF ICCV","first-page":"12227","article-title":"Self-supervised pre-training for mirror detection","author":"Lin","year":"2023"},{"key":"10.1016\/j.patrec.2026.04.019_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on CVPR","first-page":"17244","article-title":"Effective video mirror detection with inconsistent motion cues","author":"Warren","year":"2024"},{"key":"10.1016\/j.patrec.2026.04.019_bib0016","series-title":"2021 IEEE International Conference on Image Processing (ICIP)","first-page":"1544","article-title":"Visual chirality meets freehand sketches","author":"Zheng","year":"2021"},{"key":"10.1016\/j.patrec.2026.04.019_bib0017","series-title":"2014 IEEE Conference on CVPR","first-page":"2043","article-title":"Seeing the arrow of time","author":"Pickup","year":"2014"},{"key":"10.1016\/j.patrec.2026.04.019_bib0018","series-title":"2018 IEEE\/CVF Conference on CVPR","first-page":"8052","article-title":"Learning and using the arrow of time","author":"Wei","year":"2018"},{"key":"10.1016\/j.patrec.2026.04.019_bib0019","series-title":"2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)","first-page":"1371","article-title":"Retro-Actions: Learning\u2019Close\u2019by time-Reversing\u2019Open\u2019videos","author":"Price","year":"2019"},{"key":"10.1016\/j.patrec.2026.04.019_bib0020","series-title":"2024 IEEE\/CVF Conference on CVPR","first-page":"14375","article-title":"Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-Language models","author":"Guan","year":"2024"},{"key":"10.1016\/j.patrec.2026.04.019_bib0021","series-title":"Proceedings of the 32Nd ACM International Conference on Multimedia","first-page":"5260","article-title":"Reversed in time: a novel temporal-Emphasized benchmark for cross-Modal video-Text retrieval","author":"Du","year":"2024"},{"key":"10.1016\/j.patrec.2026.04.019_bib0022","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.patrec.2025.07.002","article-title":"Indeepfake: a novel multimodal multilingual indian deepfake video dataset","volume":"197","author":"Das","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.04.019_bib0023","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.patrec.2024.03.025","article-title":"A guided-based approach for deepfake detection: RGB-depth integration via features fusion","volume":"181","author":"Leporoni","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.04.019_bib0024","unstructured":"K. Soomro, A.R. Zamir, M. Shah, UCF101: A dataset of 101 human actions classes from videos in the wild, (2012). arXiv: 1212.0402."},{"key":"10.1016\/j.patrec.2026.04.019_bib0025","unstructured":"W. Kay, J. Carreira, K. Simonyan, B. Zhang, C. Hillier, S. Vijayanarasimhan, F. Viola, T. Green, T. Back, P. Natsev, et al., The kinetics human action video dataset, (2017). arXiv: 1705.06950."},{"key":"10.1016\/j.patrec.2026.04.019_bib0026","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"14901","article-title":"Transformers without normalization","author":"Zhu","year":"2025"},{"issue":"14","key":"10.1016\/j.patrec.2026.04.019_bib0027","doi-asserted-by":"crossref","first-page":"12999","DOI":"10.1109\/JIOT.2023.3257992","article-title":"Temporal transformer networks with self-supervision for action recognition","volume":"10","author":"Zhang","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.patrec.2026.04.019_bib0028","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.neunet.2023.10.047","article-title":"Leveraging spatial residual attention and temporal markov networks for video action understanding","volume":"169","author":"Xu","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.patrec.2026.04.019_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126255","article-title":"STAN: Spatio-Temporal analysis network for efficient video action recognition","volume":"268","author":"Chen","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patrec.2026.04.019_bib0030","unstructured":"C. Contributors, timm_3d: 3D Extensions of PyTorch Image Models, 2023, (https:\/\/github.com\/ZFTurbo\/timm_3d)."}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001406?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001406?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T01:07:24Z","timestamp":1779498444000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526001406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":30,"alternative-id":["S0167865526001406"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.04.019","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FGFDL: Frame grouping and feature dissimilarity learning for reverse video recognition","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.04.019","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}