{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:18:52Z","timestamp":1776529132762,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M752365"],"award-info":[{"award-number":["2024M752365"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3696409.3700164","type":"proceedings-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:55:23Z","timestamp":1735379723000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Active Object Segmentation: A New Modality for Egocentric Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9269-1130","authenticated-orcid":false,"given":"Jian","family":"Ma","sequence":"first","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9213-2611","authenticated-orcid":false,"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0324-0344","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8804-6238","authenticated-orcid":false,"given":"Dima","family":"Damen","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, England, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"e_1_3_3_1_4_2","unstructured":"Jinwoo Choi Chen Gao Joseph\u00a0CE Messou and Jia-Bin Huang. 2019. Why can\u2019t i dance in the mall? learning to mitigate scene bias in action recognition. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_3_1_5_2","unstructured":"Dima Damen Hazel Doughty Giovanni\u00a0Maria Farinella Antonino Furnari Jian Ma Evangelos Kazakos Davide Moltisanti Jonathan Munro Toby Perrett Will Price and Michael Wray. 2022. Rescaling Egocentric Vision. International Journal of Computer Vision (IJCV) (2022)."},{"key":"e_1_3_3_1_6_2","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Darkhalil Ahmad","year":"2022","unstructured":"Ahmad Darkhalil, Dandan Shan, Bin Zhu, Jian Ma, Amlan Kar, Richard Ely\u00a0Locke Higgins, Sanja Fidler, David Fouhey, and Dima Damen. 2022. Epic-kitchens visor benchmark: Video segmentations and object relations. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Alban\u00a0Main De\u00a0Boissiere and Rita Noumeir. 2020. Infrared and 3d skeleton feature fusion for rgb-d action recognition. IEEE Access 8 (2020) 168297\u2013168308.","DOI":"10.1109\/ACCESS.2020.3023599"},{"key":"e_1_3_3_1_8_2","unstructured":"Haoqi Fan Yanghao Li Bo Xiong Wan-Yen Lo and Christoph Feichtenhofer. 2020. PySlowFast. https:\/\/github.com\/facebookresearch\/slowfast."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_3_1_10_2","unstructured":"Rohan Ghosh Anupam Gupta Andrei Nakagawa Alcimar Soares and Nitish Thakor. 2019. Spatiotemporal filtering for event-based action recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1903.07067 (2019)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Younggi Hong Min\u00a0Ju Kim Isack Lee and Seok\u00a0Bong Yoo. 2023. Fluxformer: Flow-Guided Duplex Attention Transformer via Spatio-Temporal Clustering for Action Recognition. IEEE Robotics and Automation Letters (2023).","DOI":"10.1109\/LRA.2023.3307285"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_21"},{"key":"e_1_3_3_1_13_2","first-page":"4651","volume-title":"International Conference on Machine Learning","author":"Jaegle Andrew","year":"2021","unstructured":"Andrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals, Andrew Zisserman, and Joao Carreira. 2021. Perceiver: General perception with iterative attention. In International Conference on Machine Learning. PMLR, 4651\u20134664."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.44"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747276"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Youngwook Kim and Taesup Moon. 2015. Human detection and activity classification based on micro-Doppler signatures using deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters 13 1 (2015) 8\u201312.","DOI":"10.1109\/LGRS.2015.2491329"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Dawei Liang and Edison Thomaz. 2019. Audio-based activities of daily living (adl) recognition with large-scale acoustic embeddings from online videos. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 3 1 (2019) 1\u201318.","DOI":"10.1145\/3314404"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Jun Liu Amir Shahroudy Dong Xu Alex\u00a0C Kot and Gang Wang. 2017. Skeleton-based action recognition using spatio-temporal LSTM network with trust gates. IEEE Transactions on Pattern Analysis and Machine Intelligence 40 12 (2017) 3007\u20133021.","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"e_1_3_3_1_20_2","unstructured":"Ze Liu Jia Ning Yue Cao Yixuan Wei Zheng Zhang Stephen Lin and Han Hu. 2021. Video Swin Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.13230 (2021)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_3_3_1_24_2","unstructured":"Gorjan Radevski Marie-Francine Moens and Tinne Tuytelaars. 2021. Revisiting spatio-temporal layouts for compositional action recognition. The British Machine Vision Conference (BMVC) (2021)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.167"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_3_1_27_2","volume-title":"Proceedings of Advances in neural information processing systems","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Proceedings of Advances in neural information processing systems."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727435"},{"key":"e_1_3_3_1_29_2","unstructured":"Fei Wang Yunpeng Song Jimuyang Zhang Jinsong Han and Dong Huang. 2019. Temporal unet: Sample level human action recognition using wifi. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.11953 (2019)."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00199"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00806"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00059"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206288"}],"event":{"name":"MMAsia '24: ACM Multimedia Asia","location":"Auckland New Zealand","acronym":"MMAsia '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 6th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700164","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696409.3700164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:11Z","timestamp":1750295411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":36,"alternative-id":["10.1145\/3696409.3700164","10.1145\/3696409"],"URL":"https:\/\/doi.org\/10.1145\/3696409.3700164","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}