{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T17:55:00Z","timestamp":1772819700704,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":95,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475572","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T05:40:18Z","timestamp":1634535618000},"page":"4324-4333","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":46,"title":["Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors"],"prefix":"10.1145","author":[{"given":"Lei","family":"Wang","sequence":"first","affiliation":[{"name":"Australian National University & Data61\/CSIRO, Canberra, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Koniusz","sequence":"additional","affiliation":[{"name":"Data61\/CSIRO & Australian National University, Canberra, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","volume-title":"Object Level Visual Reasoning in Videos","author":"Baradel Fabien","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"e_1_3_2_2_2_1","first-page":"5706","article-title":"Salient Object Detection","volume":"24","author":"Borji Ali","year":"2015","journal-title":"A Benchmark. TIP"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/2586117.2587146"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.143"},{"key":"e_1_3_2_2_5_1","volume-title":"Action Recognition? A New Model and the Kinetics Dataset","author":"Carreira Jo\u00e3o"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2011.09.010"},{"key":"e_1_3_2_2_7_1","volume-title":"Generalized rank pooling for action recognition","author":"Cherian Anoop"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.22"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00234"},{"key":"e_1_3_2_2_10_1","volume-title":"PoTion: Pose MoTion Representation for Action Recognition","author":"Choutas Vasileios"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454225"},{"key":"e_1_3_2_2_12_1","volume-title":"ECCV Workshop. Springer Science Business Media, Prague, Czech Republic, 1--22","author":"Csurka Gabriella","year":"2004"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744047_33"},{"key":"e_1_3_2_2_14_1","volume-title":"Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray.","author":"Damen Dima","year":"2018"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1259587.1259830"},{"key":"e_1_3_2_2_16_1","volume-title":"Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Trevor Darrell, and Kate Saenko.","author":"Donahue Jeff","year":"2015"},{"key":"e_1_3_2_2_17_1","volume-title":"Lars Petersson, and Mehrtash Harandi.","author":"Fang Pengfei","year":"2019"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","volume-title":"SlowFast Networks for Video Recognition","author":"Feichtenhofer Christoph","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157486"},{"key":"e_1_3_2_2_20_1","volume-title":"Wildes","author":"Feichtenhofer Christoph","year":"2017"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","volume-title":"Modeling video evolution for action recognition","author":"Fernando Basura","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045516"},{"key":"e_1_3_2_2_24_1","volume-title":"Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition","author":"Ghadiyaram Deepti","year":"2046"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"e_1_3_2_2_27_1","volume-title":"AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions","author":"Gu Chunhui","year":"2018"},{"key":"e_1_3_2_2_28_1","volume-title":"Wildes","author":"Hadji Isma","year":"2018"},{"key":"e_1_3_2_2_29_1","volume-title":"Girshick","author":"He Kaiming","year":"2017"},{"key":"e_1_3_2_2_30_1","volume-title":"Deep Residual Learning for Image Recognition","author":"He Kaiming"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"e_1_3_2_2_32_1","volume-title":"Torr","author":"Hou Qibin","year":"2017"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1016786"},{"key":"e_1_3_2_2_34_1","volume-title":"On the Burstiness of Visual Elements","author":"J\u00e9gou Herv\u00e9"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_2_37_1","volume-title":"BMCV","author":"Kl\u00e4ser Alexander"},{"key":"e_1_3_2_2_38_1","volume-title":"2016Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons","author":"Koniusz Piotr"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","volume-title":"Soft Assignment of Visual Words as Linear Coordinate Coding and Optimisation of its Reconstruction Error","author":"Koniusz Piotr","DOI":"10.1109\/ICIP.2011.6116129"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","volume-title":"Tensor Representations for Action Recognition","author":"Koniusz Piotr","DOI":"10.1109\/TPAMI.2021.3107160"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2545667"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2012.10.010"},{"key":"e_1_3_2_2_44_1","volume-title":"Few-shot Image and Graph Classification","author":"Koniusz Piotr"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","volume-title":"A Deeper Look at Power Normalizations","author":"Koniusz Piotr","DOI":"10.1109\/CVPR.2018.00605"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413531"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"e_1_3_2_2_49_1","first-page":"295","article-title":"Human Action Recognition Using Multi-Velocity STIPs and Motion Energy Orientation Histogram","volume":"30","author":"Li Chuanzhen","year":"2014","journal-title":"J. Inf. Sci. Eng."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413641"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126534"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350916"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969120"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-3960-y"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888089.1888101"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487591"},{"key":"e_1_3_2_2_59_1","volume-title":"Ryoo","author":"Piergiovanni AJ","year":"2019"},{"key":"e_1_3_2_2_60_1","volume-title":"Real-Time Object Detection","author":"Redmon Joseph"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_2_62_1","volume-title":"EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow","author":"Revaud J\u00e9r\u00f4me"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354909"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_65_1","volume-title":"2020 a. AssembleNet: Assembling Modality Representations via Attention Connections","author":"Ryoo Michael S."},{"key":"e_1_3_2_2_66_1","unstructured":"Michael S. Ryoo AJ Piergiovanni Mingxing Tan and Anelia Angelova. 2020 b. AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures. In ICLR. ICLR Addis Ababa Ethiopia 1--15.  Michael S. Ryoo AJ Piergiovanni Mingxing Tan and Anelia Angelova. 2020 b. AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures. In ICLR. ICLR Addis Ababa Ethiopia 1--15."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"e_1_3_2_2_68_1","volume-title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","author":"Sigurdsson Gunnar A."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2968890"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.5555\/946247.946751"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"e_1_3_2_2_72_1","volume-title":"Rethinking the Inception Architecture for Computer Vision","author":"Szegedy Christian"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367032.3367164"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578744"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.132"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"crossref","volume-title":"Learning Discriminative Video Representations Using Adversarial Perturbations","author":"Wang Jue","DOI":"10.1007\/978-3-030-01225-0_42"},{"key":"e_1_3_2_2_82_1","volume-title":"Analysis and Evaluation of Kinect-based Action Recognition Algorithms. Master's thesis. School of the Computer Science and Software Engineering","author":"Wang Lei"},{"key":"e_1_3_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2925285"},{"key":"e_1_3_2_2_84_1","volume-title":"2019 b. Loss Switching Fusion with Similarity Search for Video Classification","author":"Wang Lei","year":"2019"},{"key":"e_1_3_2_2_85_1","volume-title":"2019 c. Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition With CNNs","author":"Wang Lei"},{"key":"e_1_3_2_2_86_1","volume-title":"Saliency Detection with Recurrent Fully Convolutional Networks","author":"Wang Linzhao"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553516"},{"key":"e_1_3_2_2_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.175"},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"e_1_3_2_2_90_1","volume-title":"Long-Term Feature Banks for Detailed Video Understanding","author":"Wu Chao-Yuan"},{"key":"e_1_3_2_2_91_1","volume-title":"PA3D: Pose-Action 3D Machine for Video Recognition","author":"Yan An"},{"key":"e_1_3_2_2_92_1","doi-asserted-by":"crossref","volume-title":"Local Trinary Patterns for human action recognition","author":"Yeffet Lahav","DOI":"10.1109\/ICCV.2009.5459201"},{"key":"e_1_3_2_2_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350876"},{"key":"e_1_3_2_2_94_1","volume-title":"2019 a. Few-Shot Learning via Saliency-Guided Hallucination of Samples","author":"Zhang Hongguang"},{"key":"e_1_3_2_2_95_1","volume-title":"Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective","author":"Zhang Jing"},{"key":"e_1_3_2_2_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.360"},{"key":"e_1_3_2_2_97_1","volume-title":"Le","author":"Zoph Barret","year":"2018"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475572","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:11Z","timestamp":1750193351000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":95,"alternative-id":["10.1145\/3474085.3475572","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475572","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}