{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:35:08Z","timestamp":1773142508313,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097123","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["MTFD: Multi-Teacher Fusion Distillation for Compressed Video Action Recognition"],"prefix":"10.1109","author":[{"given":"JinXin","family":"Guo","sequence":"first","affiliation":[{"name":"Inner Mongolia University,Huhhot,China"}]},{"given":"JiaQiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,Huhhot,China"}]},{"given":"ShaoJie","family":"Li","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,Huhhot,China"}]},{"given":"XiaoJing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,Huhhot,China"}]},{"given":"Ming","family":"Ma","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,Huhhot,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414534"},{"key":"ref15","article-title":"Mm-vit: Multi-modal video transformer for compressed video action recognition","author":"chen","year":"2021","journal-title":"Workshop on Applications of Computer Vision"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2019.101695"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref11","article-title":"Compressed Video Action Recognition","author":"wu","year":"2017","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref33","article-title":"Mobile Video Action Recognition","author":"huo","year":"2019","journal-title":"arXiv Computer Vision and Pattern Recognition"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2004.12.002"},{"key":"ref32","article-title":"IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition","author":"yang","year":"2019","journal-title":"arXiv Computer Vision and Pattern Recognition"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref1","article-title":"Two-Stream Convolutional Networks for Action Recognition in Videos","author":"simonyan","year":"2014","journal-title":"Neural Information Processing Systems"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Learning"},{"key":"ref16","article-title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","author":"wang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2791180"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","article-title":"Distilling the Knowledge in a Neural Network","author":"hinton","year":"2015","journal-title":"arXiv Machine Learning"},{"key":"ref23","article-title":"Compressed video contrastive learning","author":"huo","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref25","article-title":"Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective","author":"zhou","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412213"},{"key":"ref21","article-title":"Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain","author":"battash","year":"2019","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref27","article-title":"Like What You Like: Knowledge Distill via Neuron Selectivity Transfer","author":"huang","year":"2017","journal-title":"arXiv Computer Vision and Pattern Recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01366"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.332"},{"key":"ref4","article-title":"Learning Spatiotemporal Features with 3D Convolutional Networks","author":"tran","year":"2014","journal-title":"International Conference on Computer Vision"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref5","article-title":"Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification","author":"diba","year":"2017","journal-title":"arXiv Computer Vision and Pattern Recognition"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097123.pdf?arnumber=10097123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:39Z","timestamp":1700506899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097123","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}