{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:34:02Z","timestamp":1763192042815,"version":"3.45.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227612","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages"],"prefix":"10.1109","author":[{"given":"Zhoujie","family":"Qian","sequence":"first","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","key":"ref2"},{"article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning (ICML)","author":"Touvron","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref6","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref8","first-page":"12119","article-title":"LeViT: A vision transformer in ConvNet\u2019s clothing for faster inference","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yu"},{"key":"ref9","first-page":"6298","article-title":"Linformer: Self-attention with linear complexity","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"Rethinking attention with Performers","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Choromanski","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref20","first-page":"1034","article-title":"Token-to-Token Vision Transformers","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Chen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Tan","key":"ref24"},{"article-title":"ConvNeXt V2: Co-designing of self-supervised learning techniques and architectural improvements","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wu","key":"ref25"},{"article-title":"Incorporating Convolution Designs into Visual Transformers","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang","key":"ref26"},{"article-title":"FastViT: A hybrid vision architecture for fast and efficient inference","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Li","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref30","first-page":"10310","article-title":"ConvFormer: Closing the Gap Between CNN and Vision Transformers","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Jiang"},{"key":"ref31","first-page":"12301","article-title":"PiRaMA: Pyramid Range Attention Mechanism for Efficient Vision Transformer","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Peng"},{"article-title":"Faster Attention Is All You Need","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Nguyen","key":"ref32"},{"key":"ref33","first-page":"12347","article-title":"Efficient Attention Mechanism for Vision Transformers Using Low-Rank Decomposition","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Roy"},{"key":"ref34","first-page":"1234","article-title":"EfficientViT: Lightweight Vision Transformers for Resource-Constrained Devices","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Kumar"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227612.pdf?arnumber=11227612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:31:59Z","timestamp":1763191919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227612","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}