{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T09:25:44Z","timestamp":1787217944442,"version":"build-2736575974"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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","award":["62501246"],"award-info":[{"award-number":["62501246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114238","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T23:57:07Z","timestamp":1781135827000},"page":"114238","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Cibic: Pixel-free foundation model for robust corrupted image bitstream captioning"],"prefix":"10.1016","volume":"180","author":[{"given":"Junnan","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kejun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanwei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114238_b1","article-title":"A benchmark for multi-lingual vision-language learning in remote sensing image captioning","author":"Wang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114238_b2","article-title":"Promptsr: Cascade prompting for lightweight image super-resolution","author":"Liu","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114238_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111932","article-title":"Instruction-guided fusion of multi-layer visual features in large vision-language models","volume":"170","author":"Li","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114238_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113703","article-title":"Groundcap: A visually grounded image captioning dataset with object and action identification","author":"Oliveira","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114238_b5","doi-asserted-by":"crossref","first-page":"4386","DOI":"10.1109\/TMM.2025.3535367","article-title":"End-to-end deep video compression based on hierarchical temporal context learning","volume":"27","author":"Wu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114238_b6","doi-asserted-by":"crossref","unstructured":"W. Liu, Y. Wang, K.-H. Yap, L.-P. Chau, Bitstream-corrupted jpeg images are restorable: Two-stage compensation and alignment framework for image restoration, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9979\u20139988.","DOI":"10.1109\/CVPR52729.2023.00962"},{"issue":"6","key":"10.1016\/j.patcog.2026.114238_b7","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2017.4251114","article-title":"NAND flash memory forensic analysis and the growing challenge of bit errors","volume":"15","author":"van Zandwijk","year":"2017","journal-title":"IEEE Secur. Priv."},{"key":"10.1016\/j.patcog.2026.114238_b8","unstructured":"A. Tai, S.O. Kanaujia, K. Jamieson, M.J. Freedman, Who\u2019s Afraid of Uncorrectable Bit Errors? Online Recovery of Flash Errors with Distributed Redundancy, in: USENIX Conference on File and Storage Technologies, FAST, 2019."},{"key":"10.1016\/j.patcog.2026.114238_b9","doi-asserted-by":"crossref","first-page":"150872","DOI":"10.1109\/ACCESS.2025.3600320","article-title":"Semantic and technical noise modeling in semantic image communication over wireless channels","volume":"13","author":"Samarathunga","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.114238_b10","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"7949","article-title":"Towards blind bitstream-corrupted video recovery via a visual foundation model-driven framework","author":"Liu","year":"2025"},{"issue":"1","key":"10.1016\/j.patcog.2026.114238_b11","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/s42400-024-00241-9","article-title":"SIFT: Sifting file types\u2014Application of explainable artificial intelligence in cyber forensics","volume":"7","author":"Alam","year":"2024","journal-title":"Cybersecurity"},{"key":"10.1016\/j.patcog.2026.114238_b12","series-title":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","first-page":"1","article-title":"Restoration of bitstream-corrupted images: A mamba-based thumbnail-guided network","author":"Hu","year":"2025"},{"key":"10.1016\/j.patcog.2026.114238_b13","article-title":"Efficient motion-centric CLIP for compressed video action recognition","author":"Zhou","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114238_b14","article-title":"Next-generation image captioning: A survey of methodologies and emerging challenges from transformers to multimodal large language models","volume":"12","author":"Abdulgalil","year":"2025","journal-title":"Nat. Lang. Process. J."},{"key":"10.1016\/j.patcog.2026.114238_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2025.100766","article-title":"Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation","volume":"58","author":"Albadarneh","year":"2025","journal-title":"Comput. Sci. Rev."},{"key":"10.1016\/j.patcog.2026.114238_b16","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume":"162","author":"Li","year":"2022","journal-title":"Proc. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.114238_b17","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.114238_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2026.104440","article-title":"Llmark: Instance-aware foundation model for flood risk assessment","author":"Wu","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.114238_b19","doi-asserted-by":"crossref","first-page":"1305","DOI":"10.1109\/TMM.2024.3521830","article-title":"ByteNet: Rethinking multimedia file fragment classification through visual perspectives","volume":"27","author":"Liu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114238_b20","series-title":"Transactions on Machine Learning Research","article-title":"Bytes are all you need: Transformers operating directly on file bytes","author":"Horton","year":"2024"},{"key":"10.1016\/j.patcog.2026.114238_b21","series-title":"Beyond language models: Byte models are digital world simulators","author":"Wu","year":"2024"},{"issue":"3","key":"10.1016\/j.patcog.2026.114238_b22","doi-asserted-by":"crossref","first-page":"2870","DOI":"10.1109\/TCSVT.2024.3488181","article-title":"High efficiency image compression for large visual-language models","volume":"35","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114238_b23","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.patcog.2026.114238_b24","doi-asserted-by":"crossref","unstructured":"A. Pagnoni, R. Pasunuru, P. Rodriguez, J. Nguyen, B. Muller, et al., Byte Latent Transformer: Patches Scale Better Than Tokens, in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025, pp. 9238\u20139258.","DOI":"10.18653\/v1\/2025.acl-long.453"},{"key":"10.1016\/j.patcog.2026.114238_b25","series-title":"JPEG-LM: LLMs as image generators with canonical codec representations","author":"Han","year":"2024"},{"key":"10.1016\/j.patcog.2026.114238_b26","series-title":"Information technology \u2013 Digital Compression and Coding of Continuous-Tone Still Images: Requirements and Guidelines","author":"International Organization for Standardization","year":"1994"},{"issue":"4","key":"10.1016\/j.patcog.2026.114238_b27","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1145\/103085.103089","article-title":"The JPEG still picture compression standard","volume":"34","author":"Wallace","year":"1991","journal-title":"Commun. ACM"},{"key":"10.1016\/j.patcog.2026.114238_b28","series-title":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","first-page":"2305","article-title":"Optimizing JPEG decoder for bitstream-corrupted image restoration","author":"Jiang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114238_b29","series-title":"USENIX ATC","first-page":"275","article-title":"A memory soft error measurement on production systems.","author":"Li","year":"2007"},{"key":"10.1016\/j.patcog.2026.114238_b30","article-title":"GIT: A generative image-to-text transformer for vision and language","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.114238_b31","series-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114238_b32","doi-asserted-by":"crossref","unstructured":"Z. Chen, J. Wu, W. Wang, W. Su, G. Chen, et al., Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 24185\u201324198.","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"10.1016\/j.patcog.2026.114238_b33","article-title":"GLM-4 based method for automatic construction of content graph","author":"Yang","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.114238_b34","series-title":"Ministral 3","author":"Liu","year":"2026"},{"key":"10.1016\/j.patcog.2026.114238_b35","series-title":"2024 International Conference on Sustainable Communication Networks and Application","first-page":"315","article-title":"Review of recent datasets used in image captioning models","author":"Srivastava","year":"2024"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012033?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012033?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:50:20Z","timestamp":1787215820000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":35,"alternative-id":["S0031320326012033"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114238","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cibic: Pixel-free foundation model for robust corrupted image bitstream captioning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114238","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114238"}}