{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:15:15Z","timestamp":1771697715745,"version":"3.50.1"},"reference-count":24,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp43922.2022.9747484","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"2220-2224","source":"Crossref","is-referenced-by-count":8,"title":["Attention Probe: Vision Transformer Distillation in the Wild"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Mingdeng","family":"Cao","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Shuwei","family":"Shi","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Baoyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}]},{"given":"Yujiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref12","article-title":"Pruning filters for efficient convnets","author":"li","year":"2016","journal-title":"ICLRE"},{"key":"ref13","article-title":"Cnnpack: packing convolutional neural networks in the frequency domain","author":"wang","year":"2016","journal-title":"NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5765"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00636"},{"key":"ref18","article-title":"Data-free knowledge distillation for deep neural networks","author":"lopes","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.31"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ICLRE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref5","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref7","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref2","article-title":"Adder attention for vision transformer","author":"shu","year":"2021","journal-title":"NeurIPS"},{"key":"ref1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref9","article-title":"Uformer: A general u-shaped transformer for image restoration","author":"wang","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"ref21","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"ICLRE"}],"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\/09747484.pdf?arnumber=9747484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:06Z","timestamp":1660594026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747484","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}