{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:54:56Z","timestamp":1767981296414,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932020, 61702078, 61772108, 61976038, 61772106"],"award-info":[{"award-number":["61932020, 61702078, 61772108, 61976038, 61772106"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612206","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"5070-5078","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Exploring Coarse-to-Fine Action Token Localization and Interaction for Fine-grained Video Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-4288","authenticated-orcid":false,"given":"Baoli","family":"Sun","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5328-3911","authenticated-orcid":false,"given":"Xinchen","family":"Ye","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-9726","authenticated-orcid":false,"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3882-2205","authenticated-orcid":false,"given":"Haojie","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8043-0312","authenticated-orcid":false,"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MultiModal Language Modelling on Knowledge Graphs for Deep Video Understanding. In MM '21: ACM Multimedia, October. 4868--4872","author":"Anand Vishal","year":"2021","unstructured":"Vishal Anand, Raksha Ramesh, Boshen Jin, Ziyin Wang, Xiaoxiao Lei, and Ching-Yung Lin. 2021. MultiModal Language Modelling on Knowledge Graphs for Deep Video Understanding. In MM '21: ACM Multimedia, October. 4868--4872."},{"key":"e_1_3_2_1_2_1","volume-title":"ViViT: A Video Vision Transformer. CoRR","author":"Arnab Anurag","year":"2021","unstructured":"Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lucic, and Cordelia Schmid. 2021. ViViT: A Video Vision Transformer. CoRR, Vol. abs\/2103.15691 (2021)."},{"key":"e_1_3_2_1_3_1","unstructured":"Gedas Bertasius Heng Wang and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding?. In ICML July Virtual Event. 813--824."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_5_1","volume-title":"Action Recognition? A New Model and the Kinetics Dataset","author":"Carreira Jo\u00e3o","unstructured":"Jo\u00e3o Carreira and Andrew Zisserman. 2017. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. In IEEE CVPR, July. 4724--4733."},{"key":"e_1_3_2_1_6_1","unstructured":"Mengzhao Chen Mingbao Lin Ke Li Yunhang Shen Yongjian Wu Fei Chao and Rongrong Ji. 2023. CF-ViT: A General Coarse-to-Fine Method for Vision Transformer. In AAAI February. 8658--8665."},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR Austria May."},{"key":"e_1_3_2_1_8_1","volume-title":"Multiscale Vision Transformers","author":"Fan Haoqi","unstructured":"Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, and Christoph Feichtenhofer. 2021. Multiscale Vision Transformers. In IEEE\/CVF, ICCV, October. 6804--6815."},{"key":"e_1_3_2_1_9_1","volume-title":"Farnoush Rezaei Jafari, Sunando Sengupta, Hamid Reza Vaezi Joze, Eric Sommerlade, Hamed Pirsiavash, and J\u00fcrgen Gall.","author":"Fayyaz Mohsen","year":"2022","unstructured":"Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari, Sunando Sengupta, Hamid Reza Vaezi Joze, Eric Sommerlade, Hamed Pirsiavash, and J\u00fcrgen Gall. 2022. Adaptive Token Sampling for Efficient Vision Transformers. In ECCV, October, Proceedings, Part XI, Vol. 13671. Springer, 396--414."},{"key":"e_1_3_2_1_10_1","volume-title":"SlowFast Networks for Video Recognition","author":"Feichtenhofer Christoph","unstructured":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. 2019. SlowFast Networks for Video Recognition. In IEEE ICCV, October. 6201--6210."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Valentin Gabeur Chen Sun Karteek Alahari and Cordelia Schmid. 2020. Multi-modal Transformer for Video Retrieval. In ECCV August. 214--229.","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_1_12_1","volume-title":"Carl Doersch, and Andrew Zisserman.","author":"Girdhar Rohit","year":"2019","unstructured":"Rohit Girdhar, Jo a o Carreira, Carl Doersch, and Andrew Zisserman. 2019. Video Action Transformer Network. In IEEE CVPR, June. 244--253."},{"key":"e_1_3_2_1_13_1","first-page":"5843","article-title":"The \"Something Something","author":"Goyal Raghav","year":"2017","unstructured":"Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fr\u00fcnd, Peter Yianilos, Moritz Mueller-Freitag, Florian Hoppe, Christian Thurau, Ingo Bax, and Roland Memisevic. 2017. The \"Something Something\" Video Database for Learning and Evaluating Visual Common Sense. In IEEE ICCV, October. 5843--5851.","journal-title":"In IEEE ICCV"},{"key":"e_1_3_2_1_14_1","volume-title":"Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units. CoRR","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units. CoRR, Vol. abs\/1606.08415 (2016)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2946469"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"e_1_3_2_1_17_1","volume-title":"Austin Reiter, and Gregory D. Hager","author":"Lea Colin","year":"2017","unstructured":"Colin Lea, Michael D. Flynn, Ren\u00e9 Vidal, Austin Reiter, and Gregory D. Hager. 2017. Temporal Convolutional Networks for Action Segmentation and Detection. In IEEE CVPR, July. 1003--1012."},{"key":"e_1_3_2_1_18_1","volume-title":"Temporal Deformable Residual Networks for Action Segmentation in Videos","author":"Lei Peng","unstructured":"Peng Lei and Sinisa Todorovic. 2018. Temporal Deformable Residual Networks for Action Segmentation in Videos. In IEEE CVPR, June. 6742--6751."},{"key":"e_1_3_2_1_19_1","unstructured":"Kunchang Li Yali Wang Peng Gao Guanglu Song Yu Liu Hongsheng Li and Yu Qiao. 2022b. UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning. In ICLR Virtual Event April."},{"key":"e_1_3_2_1_20_1","unstructured":"Kunchang Li Yali Wang Peng Gao Guanglu Song Yu Liu Hongsheng Li and Yu Qiao. 2022c. UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning. In ICLR April."},{"key":"e_1_3_2_1_21_1","unstructured":"Kunchang Li Yali Wang Yinan He Yizhuo Li Yi Wang Limin Wang and Yu Qiao. 2023. UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer. In ICLR Virtual Event April."},{"key":"e_1_3_2_1_22_1","first-page":"386","article-title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition. In ECCV, October","volume":"13664","author":"Li Tianjiao","year":"2022","unstructured":"Tianjiao Li, Lin Geng Foo, Qiuhong Ke, Hossein Rahmani, Anran Wang, Jinghua Wang, and Jun Liu. 2022a. Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition. In ECCV, October, Part IV, Vol. 13664. 386--403.","journal-title":"Part IV"},{"key":"e_1_3_2_1_23_1","volume-title":"TEA: Temporal Excitation and Aggregation for Action Recognition","author":"Li Yan","year":"2020","unstructured":"Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, and Limin Wang. 2020. TEA: Temporal Excitation and Aggregation for Action Recognition. In IEEE CVPR, June. 906--915."},{"key":"e_1_3_2_1_24_1","volume-title":"RESOUND: Towards Action Recognition Without Representation Bias. In ECCV, September. 520--535.","author":"Li Yingwei","year":"2018","unstructured":"Yingwei Li, Yi Li, and Nuno Vasconcelos. 2018. RESOUND: Towards Action Recognition Without Representation Bias. In ECCV, September. 520--535."},{"key":"e_1_3_2_1_25_1","unstructured":"Youwei Liang Chongjian Ge Zhan Tong Yibing Song Jue Wang and Pengtao Xie. 2022a. Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations. (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_33"},{"key":"e_1_3_2_1_27_1","volume-title":"TSM: Temporal Shift Module for Efficient Video Understanding","author":"Lin Ji","year":"2019","unstructured":"Ji Lin, Chuang Gan, and Song Han. 2019. TSM: Temporal Shift Module for Efficient Video Understanding. In IEEE ICCV, October. 7082--7092."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416298"},{"key":"e_1_3_2_1_29_1","volume-title":"ICML","author":"Parmar Niki","unstructured":"Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Noam Shazeer, Alexander Ku, and Dustin Tran. 2018. Image Transformer. In ICML, Stockholmsm\u00e4ssan, Stockholm, Sweden, July, Vol. 80. 4052--4061."},{"key":"e_1_3_2_1_30_1","unstructured":"Yongming Rao Wenliang Zhao Benlin Liu Jiwen Lu Jie Zhou and Cho-Jui Hsieh. 2021. DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification. In NeurIPS December virtual. 13937--13949."},{"key":"e_1_3_2_1_31_1","volume-title":"FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding","author":"Shao Dian","unstructured":"Dian Shao, Yue Zhao, Bo Dai, and Dahua Lin. 2020. FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding. In IEEE CVPR, June. 2613--2622."},{"key":"e_1_3_2_1_32_1","volume-title":"The 30th ACM MM, Lisboa, Portugal, October. 4779--4788.","author":"Sun Baoli","unstructured":"Baoli Sun, Xinchen Ye, Tiantian Yan, Zhihui Wang, Haojie Li, and Zhiyong Wang. 2022. Fine-grained Action Recognition with Robust Motion Representation Decoupling and Concentration. In The 30th ACM MM, Lisboa, Portugal, October. 4779--4788."},{"key":"e_1_3_2_1_33_1","volume-title":"Carl Vondrick, Kevin Murphy, and Cordelia Schmid.","author":"Sun Chen","year":"2019","unstructured":"Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy, and Cordelia Schmid. 2019. VideoBERT: A Joint Model for Video and Language Representation Learning. In IEEE ICCV, October. 7463--7472."},{"key":"e_1_3_2_1_34_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS December. 5998--6008."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"e_1_3_2_1_36_1","volume-title":"BEVT: BERT Pretraining of Video Transformers","author":"Wang Rui","year":"2022","unstructured":"Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Yu-Gang Jiang, Luowei Zhou, and Lu Yuan. 2022. BEVT: BERT Pretraining of Video Transformers. In IEEE\/CVF CVPR, New Orleans, LA, USA, June. 14713--14723."},{"key":"e_1_3_2_1_37_1","volume-title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","author":"Wang Wenhai","unstructured":"Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2021b. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions. In IEEE\/CVF, ICCV, Montreal, QC, Canada, October. 548--558."},{"key":"e_1_3_2_1_38_1","volume-title":"End-to-End Video Instance Segmentation With Transformers","author":"Wang Yuqing","unstructured":"Yuqing Wang, Zhaoliang Xu, Xinlong Wang, Chunhua Shen, Baoshan Cheng, Hao Shen, and Huaxia Xia. 2021c. End-to-End Video Instance Segmentation With Transformers. In IEEE CVPR, June. 8741--8750."},{"key":"e_1_3_2_1_39_1","volume-title":"Philipp Kr\u00e4henb\u00fc hl, and Ross B. Girshick","author":"Wu Chao-Yuan","year":"2019","unstructured":"Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Kr\u00e4henb\u00fc hl, and Ross B. Girshick. 2019. Long-Term Feature Banks for Detailed Video Understanding. In IEEE CVPR, June. 284--293."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Saining Xie Chen Sun Jonathan Huang Zhuowen Tu and Kevin Murphy. 2018. Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification. In ECCV September. 318--335.","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_1_41_1","volume-title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","author":"Zeng Wang","unstructured":"Wang Zeng, Sheng Jin, Wentao Liu, Chen Qian, Ping Luo, Wanli Ouyang, and Xiaogang Wang. 2022. Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer. In IEEE\/CVF CVPR, New Orleans, LA, USA, June. 11091--11101."},{"key":"e_1_3_2_1_42_1","volume-title":"Temporal Query Networks for Fine-Grained Video Understanding","author":"Zhang Chuhan","unstructured":"Chuhan Zhang, Ankush Gupta, and Andrew Zisserman. 2021a. Temporal Query Networks for Fine-Grained Video Understanding. In IEEE CVPR, June. 4486--4496."},{"key":"e_1_3_2_1_43_1","volume-title":"VidTr: Video Transformer Without Convolutions","author":"Zhang Yanyi","unstructured":"Yanyi Zhang, Xinyu Li, Chunhui Liu, Bing Shuai, Yi Zhu, Biagio Brattoli, Hao Chen, Ivan Marsic, and Joseph Tighe. 2021b. VidTr: Video Transformer Without Convolutions. In IEEE\/CVF, ICCV, October. 13557--13567."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612206","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:30Z","timestamp":1755821190000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":43,"alternative-id":["10.1145\/3581783.3612206","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612206","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}