{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T15:08:04Z","timestamp":1776697684881,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747591","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3234-3238","source":"Crossref","is-referenced-by-count":61,"title":["A free lunch from ViT: adaptive attention multi-scale fusion Transformer for fine-grained visual recognition"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Peking University,School of Software and Microelectronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Cao","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangcheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Ling","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqian","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"ref11","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref13","article-title":"Multi-branch and Multi-scale Attention Learning for FineGrained Visual Categorization","author":"zhang","year":"2021","journal-title":"MultiMedia Modeling - 27th International Conference MMM 2021"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_13","article-title":"End-to-End Object Detection with Transformers","author":"carion","year":"2020"},{"key":"ref16","article-title":"TransFG: A Transformer Architecture for Fine-grained Recognition","author":"he","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref19","article-title":"Maximum-entropy fine grained classification","volume":"31","author":"dubey","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3020227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.325"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref3","article-title":"Learning Deep Bilinear Transformation for Fine-grained Image Representation","author":"zheng","year":"2019","journal-title":"Annual Conference on Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref8","article-title":"Bird Species Categorization Using Pose Normalized Deep Convolutional Nets","author":"branson","year":"0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref2","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume":"2","author":"khosla","year":"2011","journal-title":"Proc CVPR Workshop on Fine-Grained Visual Categorization (FGVC)"},{"key":"ref9","article-title":"Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition","author":"wei","year":"2016"},{"key":"ref1","article-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"wah","year":"2011","journal-title":"Technical Report CNS-TR-2011-001 California Institute of Technology"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747591.pdf?arnumber=9747591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:59Z","timestamp":1661199119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747591","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}