{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:18:12Z","timestamp":1773137892649,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272100"],"award-info":[{"award-number":["62272100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Consulting Project of Chinese Academy of Engineering","award":["2023-XY-09"],"award-info":[{"award-number":["2023-XY-09"]}]},{"name":"Academy-Locality Cooperation Project of Chinese Academy of Engineering","award":["JS2021ZT05"],"award-info":[{"award-number":["JS2021ZT05"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tmc.2025.3633250","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:43:12Z","timestamp":1763404992000},"page":"5890-5904","source":"Crossref","is-referenced-by-count":0,"title":["Toward an Ultra-Lightweight Text Representation: Causal Convolutional Networks With Feature Self-Enhancement Mechanisms"],"prefix":"10.1109","volume":"25","author":[{"given":"Xiaoyan","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1184-8117","authenticated-orcid":false,"given":"Peng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenqi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref5","first-page":"611","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","volume":"2021","author":"Dosovitskiy","year":"2021"},{"key":"ref6","article-title":"Retentive Network: A successor to transformer for large language models","author":"Sun","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130168"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1477"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"issue":"2024","key":"ref12","first-page":"107984","article-title":"YOLOv10 real-time end-to-end object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Wang","year":"2024"},{"key":"ref13","first-page":"1905","article-title":"PixelCNN models with auxiliary variables for natural image modeling","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Kolesnikov","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref15","article-title":"Fast transformer decoding: One write-head is all you need","author":"Shazeer","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.607"},{"key":"ref18","first-page":"8304","article-title":"cosFormer: Rethinking softmax in attention","volume-title":"Proc. 10th Int. Conf. Learn. Representations","volume":"2022","author":"Qin","year":"2022"},{"key":"ref19","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Katharopoulos","year":"2020"},{"key":"ref20","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"ref21","article-title":"Deepseek-V2: A strong, economical, and efficient mixture-of-experts language model","year":"2024"},{"key":"ref22","first-page":"35549","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","volume":"2024","author":"Dao","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref27","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01309"},{"key":"ref30","article-title":"What matters in transformers? Not all attention is needed","author":"He","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref33","first-page":"10041","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. Mach. Learn. Res.","volume":"235","author":"Dao","year":"2024"},{"key":"ref34","article-title":"Eagle and finch: RWKV with matrix-valued states and dynamic recurrence","author":"Peng","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3483009"},{"key":"ref36","first-page":"62429","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Mach. Learn. Res.","volume":"235","author":"Zhu","year":"2024"},{"key":"ref37","first-page":"61381","article-title":"Vision-RWKV: Efficient and scalable visual perception with RWKV-like architectures","volume-title":"Proc. 13th Int. Conf. Learn. Representations","volume":"2025","author":"Duan","year":"2025"},{"key":"ref38","article-title":"An attention free transformer","author":"Zhai","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref40","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.6"},{"key":"ref42","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Tolstikhin","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106471"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119076"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13732"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00367"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"issue":"140","key":"ref52","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Maas","year":"2011"},{"key":"ref54","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. 29th Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507163"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218990"},{"key":"ref58","first-page":"12","article-title":"Findings of the 2014 workshop on statistical machine translation","volume-title":"Proc. 9th Workshop Stat. Mach. Transl.","author":"Bojar","year":"2014"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-84186-7_31"},{"key":"ref60","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. 33rd Adv. Neural Inf. Proces. Syst.","author":"Yang","year":"2019"},{"key":"ref61","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref62","first-page":"11574","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. 8th Int. Conf. Learn. Representations","volume":"2020","author":"Lan","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1202"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"ref65","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2020"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11423852\/11250752.pdf?arnumber=11250752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:53Z","timestamp":1773086453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11250752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":65,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3633250","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}