{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T04:57:14Z","timestamp":1771563434693,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["62173285 and 62103345"],"award-info":[{"award-number":["62173285 and 62103345"]}]},{"name":"the Fujian Provincial Natural Science Foundation of China","award":["2021J011181 and 2020J02160"],"award-info":[{"award-number":["2021J011181 and 2020J02160"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3688867.3690169","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:28:27Z","timestamp":1729708107000},"page":"20-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Spatial and Channel Squeeze & Excitation in Adapting Vision Transformers for Temporal Action Localization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8090-211X","authenticated-orcid":false,"given":"Jianglong","family":"Huang","sequence":"first","affiliation":[{"name":"Xiamen University of Technology, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4472-7298","authenticated-orcid":false,"given":"Chaoqun","family":"Hong","sequence":"additional","affiliation":[{"name":"Xiamen University of Technology, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2079-6133","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiamen University of Technology, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1297-7574","authenticated-orcid":false,"given":"Xuejiao","family":"Li","sequence":"additional","affiliation":[{"name":"Xiamen University of Technology, Xiamen, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings, Part XXVIII 16","author":"Bai Yueran","year":"2020","unstructured":"Yueran Bai, Yingying Wang, Yunhai Tong, Yang Yang, Qiyue Liu, and Junhui Liu. 2020. Boundary content graph neural network for temporal action proposal generation. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXVIII 16. Springer, 121--137."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552458.3556443"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458305.3459598"},{"key":"e_1_3_2_1_7_1","first-page":"16664","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen Shoufa","year":"2022","unstructured":"Shoufa Chen, Chongjian Ge, Zhan Tong, Jiangliu Wang, Yibing Song, Jue Wang, and Ping Luo. 2022. Adaptformer: Adapting vision transformers for scalable visual recognition. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16664--16678.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"e_1_3_2_1_9_1","volume-title":"Comput. Res. Reposit.","volume":"2006","author":"Dima Damen","year":"2020","unstructured":"Damen Dima. 2020. Rescaling egocentric vision. Comput. Res. Reposit., Vol. 2006 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Machine Learning. PMLR, 2793--2803","author":"Dong Yihe","year":"2021","unstructured":"Yihe Dong, Jean-Baptiste Cordonnier, and Andreas Loukas. 2021. Attention is not all you need: Pure attention loses rank doubly exponentially with depth. In International Conference on Machine Learning. PMLR, 2793--2803."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_12_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612278"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"e_1_3_2_1_21_1","volume-title":"Medical Image Computing and Computer Assisted Intervention--MICCAI 2018: 21st International Conference, Granada, Spain, September 16--20","author":"Roy Abhijit Guha","year":"2018","unstructured":"Abhijit Guha Roy, Nassir Navab, and Christian Wachinger. 2018. Concurrent spatial and channel 'squeeze & excitation'in fully convolutional networks. In Medical Image Computing and Computer Assisted Intervention--MICCAI 2018: 21st International Conference, Granada, Spain, September 16--20, 2018, Proceedings, Part I. Springer, 421--429."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548077"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01348"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_21"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103692"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. PMLR, 27378--27394","author":"Zhou Daquan","year":"2022","unstructured":"Daquan Zhou, Zhiding Yu, Enze Xie, Chaowei Xiao, Animashree Anandkumar, Jiashi Feng, and Jose M Alvarez. 2022. Understanding the robustness in vision transformers. In International Conference on Machine Learning. PMLR, 27378--27394."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01326"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2nd International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688867.3690169","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688867.3690169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:34:30Z","timestamp":1755974070000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688867.3690169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":35,"alternative-id":["10.1145\/3688867.3690169","10.1145\/3688867"],"URL":"https:\/\/doi.org\/10.1145\/3688867.3690169","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}