{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:39Z","timestamp":1774419999959,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890489","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition"],"prefix":"10.1109","author":[{"given":"Edwin Arkel","family":"Rios","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Jansen Christopher","family":"Yuanda","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Taiwan"}]},{"given":"Vincent Leon","family":"Ghanz","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Taiwan"}]},{"given":"Cheng-Wei","family":"Yu","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Bo-Cheng","family":"Lai","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Min-Chun","family":"Hu","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284405"},{"key":"ref4","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3260883"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3241969"},{"key":"ref10","article-title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","author":"Rao","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref12","article-title":"Learning to Merge Tokens in Vision Transformers","author":"Renggli","year":"2022"},{"key":"ref13","article-title":"Token Merging: Your ViT But Faster","author":"Bolya","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"ref15","article-title":"EViT: Expediting Vision Transformers via Token Reorganizations","author":"Liang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_26"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3370731"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"ref20","article-title":"Vision Transformers Need Registers","author":"Darcet","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00335"},{"key":"ref23","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"ref24","article-title":"ImageNet-21K Pretraining for the Masses","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Ridnik"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref28","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Visualizing the Loss Landscape of Neural Nets","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Li","year":"2018"},{"key":"ref30","article-title":"Towards Understanding the Importance of Shortcut Connections in Residual Networks","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Liu","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref32","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems, ser. NIPS\u201916","author":"Veit"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890489.pdf?arnumber=10890489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:52Z","timestamp":1774416352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890489","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}