{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:28:48Z","timestamp":1730266128105,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191567","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Multi-Resolution Attention with Linear Complexity"],"prefix":"10.1109","author":[{"given":"Yao","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Informatics, LMU Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpu","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Informatics, LMU Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Seidl","sequence":"additional","affiliation":[{"name":"Institute of Informatics, LMU Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Tresp","sequence":"additional","affiliation":[{"name":"Institute of Informatics, LMU Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref2","first-page":"328","article-title":"Universal language model fine-tuning for text classification","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018","volume":"1","author":"Howard"},{"key":"ref3","first-page":"2383","article-title":"SQuAD: 100,000+ questions for machine comprehension of text","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Rajpurkar"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref5","first-page":"4055","article-title":"Image transformer","volume-title":"International Conference on Machine Learning","author":"Parmar","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref7","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Transformer on a diet","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"9438","article-title":"Sparse sinkhorn attention","volume-title":"International Conference on Machine Learning","author":"Tay","year":"2020"},{"key":"ref10","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"article-title":"Reformer: The efficient transformer","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Kitaev","key":"ref12"},{"key":"ref13","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","volume-title":"International Conference on Machine Learning","author":"Katharopoulos","year":"2020"},{"article-title":"Rethinking attention with performers","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Choromanski","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17664"},{"article-title":"Random feature attention","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Peng","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1032"},{"key":"ref18","article-title":"Bp-transformer: Modelling long-range context via binary partitioning","author":"Ye","year":"2019","journal-title":"arXiv preprint"},{"article-title":"Compressive transformers for long-range sequence modelling","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Rae","key":"ref19"},{"article-title":"Long range arena: A benchmark for efficient transformers","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Tay","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.232"},{"key":"ref22","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Fast transformers with clustered attention","volume":"33","author":"Vyas","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1133"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2913184"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.2986926"},{"key":"ref28","article-title":"Hierarchical multi-scale attention for semantic segmentation","author":"Tao","year":"2020","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"285","article-title":"Pyramid attention network for semantic segmentation","volume-title":"British Machine Vision Conference 2018, BMVC 2018","author":"Li"},{"key":"ref30","first-page":"1448","article-title":"Salient object detection with pyramid attention and salient edges","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00360"},{"key":"ref32","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Shazeer","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1580"},{"key":"ref35","first-page":"92","article-title":"ListOps: A diagnostic dataset for latent tree learning","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop","author":"Nangia"},{"key":"ref36","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies","author":"Maas","year":"2011"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/1699750.1699759"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref38"},{"key":"ref39","article-title":"Learning long-range spatial dependencies with horizontal gated recurrent units","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Linsley","year":"2018"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191567.pdf?arnumber=10191567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T15:28:12Z","timestamp":1709306892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191567","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}