{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T16:00:19Z","timestamp":1772208019742,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"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\/3474085.3475534","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T06:35:51Z","timestamp":1634538951000},"page":"4053-4062","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Cascade Cross-modal Attention Network for Video Actor and Action Segmentation from a Sentence"],"prefix":"10.1145","author":[{"given":"Weidong","family":"Chen","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Guorong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Xinfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Hongyang","family":"Yu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology Chinese Academy of Sciences, Beijing, China"}]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Computing Technology Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5958--5966","author":"Gavrilyuk Kirill","year":"2018","unstructured":"Kirill Gavrilyuk , Amir Ghodrati , Zhenyang Li , and Cees GM Snoek . 2018 . Ac- tor and action video segmentation from a sentence . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5958--5966 . Kirill Gavrilyuk, Amir Ghodrati, Zhenyang Li, and Cees GM Snoek. 2018. Ac- tor and action video segmentation from a sentence. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5958--5966."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_32"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"e_1_3_2_1_13_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev etal 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017).  Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327087"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157129"},{"key":"e_1_3_2_1_23_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Lu Pan","year":"2018","unstructured":"Pan Lu , Hongsheng Li , Wei Zhang , Jianyong Wang , and Xiaogang Wang . 2018 . Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering . In Thirty-Second AAAI Conference on Artificial Intelligence. Pan Lu, Hongsheng Li, Wei Zhang, Jianyong Wang, and Xiaogang Wang. 2018. Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering. In Thirty-Second AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999959"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence.","author":"Ning Ke","year":"2020","unstructured":"Ke Ning , Lingxi Xie , Fei Wu , and Qi Tian . 2020 . Polar Relative Positional Encod- ing for Video-Language Segmentation . In Proceedings of the International Joint Conference on Artificial Intelligence. Ke Ning, Lingxi Xie, Fei Wu, and Qi Tian. 2020. Polar Relative Positional Encod- ing for Video-Language Segmentation. In Proceedings of the International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413850"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"e_1_3_2_1_32_1","volume-title":"J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov.","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai , Shaojie Bai , Paul Pu Liang , J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019 . Multimodal Transformer for Unaligned Multimodal Language Sequences . arXiv preprint arXiv:1906.00295 (2019). Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal Transformer for Unaligned Multimodal Language Sequences. arXiv preprint arXiv:1906.00295 (2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413905"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.336"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.162"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.115"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351063"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"e_1_3_2_1_51_1","unstructured":"Roland S Zimmermann and Julien N Siems. 2018. Faster Training of Mask R-CNN by Focusing on Instance Boundaries. arXiv preprint arXiv:1809.07069 (2018  Roland S Zimmermann and Julien N Siems. 2018. Faster Training of Mask R-CNN by Focusing on Instance Boundaries. arXiv preprint arXiv:1809.07069 (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\/3474085.3475534","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:10Z","timestamp":1750193350000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":51,"alternative-id":["10.1145\/3474085.3475534","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475534","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"}}]}}