{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T10:51:51Z","timestamp":1770893511093,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["U2336212"],"award-info":[{"award-number":["U2336212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272411"],"award-info":[{"award-number":["62272411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects in Zhejiang Province","doi-asserted-by":"publisher","award":["2024C01106"],"award-info":[{"award-number":["2024C01106"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2025.3527046","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T15:04:22Z","timestamp":1736953462000},"page":"14493-14507","source":"Crossref","is-referenced-by-count":2,"title":["DBA: Efficient Transformer With Dynamic Bilinear Low-Rank Attention"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1978-9999","authenticated-orcid":false,"given":"Bosheng","family":"Qin","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-1291","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-3084","authenticated-orcid":false,"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Long range arena: A benchmark for efficient transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tay"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref4","first-page":"1","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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3173131"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref10","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref11","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref12","first-page":"2441","article-title":"Luna: Linear unified nested attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ma"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"ref14","first-page":"1","article-title":"CosFormer: Rethinking softmax in attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Qin"},{"key":"ref15","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Choromanski"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6265-7"},{"issue":"2","key":"ref17","first-page":"189","article-title":"Extensions of Lipschitz maps into a Hilbert space","volume":"26","author":"Lindenstrauss","year":"1984","journal-title":"Contemp. Math."},{"key":"ref18","article-title":"The UEA multivariate time series classification archive, 2018","author":"Bagnall","year":"2018","journal-title":"arXiv:1811.00075"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref20","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref21","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kitaev"},{"key":"ref22","first-page":"9438","article-title":"Sparse Sinkhorn attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tay"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref24","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Press"},{"key":"ref25","article-title":"Sparse attention with learning to hash","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sun"},{"key":"ref26","first-page":"12321","article-title":"You only sample (almost) once: Linear cost self-attention via Bernoulli sampling","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Zeng"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.170"},{"key":"ref28","first-page":"12437","article-title":"PoolingFormer: Long document modeling with pooling attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Zhang"},{"key":"ref29","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. (NeurlPS)","author":"Zaheer"},{"key":"ref30","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref31","first-page":"29449","article-title":"FMMformer: Efficient and flexible transformer via decomposed near-field and far-field attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref32","first-page":"17723","article-title":"Long-short transformer: Efficient transformers for language and vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3341806","article-title":"CrossFormer: A versatile vision transformer hinging on cross-scale attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref34","article-title":"PoNet: Pooling network for efficient token mixing in long sequences","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tan"},{"key":"ref35","article-title":"Random feature attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref36","first-page":"27011","article-title":"Linear complexity randomized self-attention mechanism","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref37","first-page":"2122","article-title":"Skyformer: Remodel self-attention with Gaussian kernel and Nystr\u00f6m method","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.19"},{"key":"ref39","first-page":"22795","article-title":"Stable, fast and accurate: Kernelized attention with relative positional encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref40","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kreuzer"},{"key":"ref41","first-page":"27268","article-title":"FedFormer: Frequency enhanced decomposed transformer for long-term series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref42","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Hua"},{"key":"ref43","first-page":"16595","article-title":"Improving transformers with probabilistic attention keys","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref44","article-title":"DSFormer: Effective compression of text-transformers by dense-sparse weight factorization","author":"Chand","year":"2023","journal-title":"arXiv:2312.13211"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071081"},{"key":"ref46","article-title":"FLuRKA: Fast and accurate unified low-rank & kernel attention","author":"Gupta","year":"2023","journal-title":"arXiv:2306.15799"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-4013"},{"key":"ref48","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"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/1699750.1699759"},{"key":"ref50","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.32470\/CCN.2018.1116-0"},{"key":"ref52","first-page":"24226","article-title":"Flowformer: Linearizing transformers with conservation flows","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Wu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/INFOo11020108"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4020-z"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025541"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref63","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref64","first-page":"17413","article-title":"Scatterbrain: Unifying sparse and low-rank attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref65","first-page":"10183","article-title":"Synthesizer: Rethinking self-attention for transformer models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Tay"},{"key":"ref66","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst","author":"Paszke"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref69","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref70","first-page":"1","article-title":"Albert: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lan"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref75","article-title":"Bilinear attention networks","author":"Kim","year":"2018","journal-title":"arXiv:1805.07932"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"ref77","article-title":"Euclidean-norm-induced schatten-p quasi-norm regularization for low-rank tensor completion and tensor robust principal component analysis","volume":"2023","author":"Fan","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2547180"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_16"},{"key":"ref81","first-page":"20343","article-title":"LAPAR: Linearly-assembled pixel-adaptive regression network for single image super-resolution and beyond","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Li"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1038\/18581"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10843139.pdf?arnumber=10843139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:00:50Z","timestamp":1754503250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10843139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":82,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3527046","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}