{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T07:44:51Z","timestamp":1782287091634,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":52,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072334"],"award-info":[{"award-number":["62072334"]}],"id":[{"id":"10.13039\/501100001809","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\/3581783.3611745","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"709-718","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2470-8110","authenticated-orcid":false,"given":"Lianyu","family":"Hu","sequence":"first","affiliation":[{"name":"Tianjin Univeristy, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4518-2154","authenticated-orcid":false,"given":"Liqing","family":"Gao","sequence":"additional","affiliation":[{"name":"Tianjin Univeristy, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5003-1900","authenticated-orcid":false,"given":"Zekang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin Univeristy, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1788-3746","authenticated-orcid":false,"given":"Chi-Man","family":"Pun","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3809-1086","authenticated-orcid":false,"given":"Wei","family":"Feng","sequence":"additional","affiliation":[{"name":"Tianjin Univeristy, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_41"},{"key":"e_1_3_2_1_4_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van Merri\u00ebnboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.332"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.175"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2889563"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/98"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"e_1_3_2_1_11_1","volume-title":"International workshop on automatic face and gesture recognition","volume":"12","author":"Freeman William T","year":"1995","unstructured":"William T Freeman and Michal Roth. 1995. Orientation histograms for hand gesture recognition. In International workshop on automatic face and gesture recognition, Vol. 12. IEEE Computer Society, Washington, DC, 296--301."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.04.008"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.12.010"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","unstructured":"Andrew Howard Andrey Zhmoginov Liang-Chieh Chen Mark Sandler and Menglong Zhu. 2018. Inverted residuals and linear bottlenecks: Mobile networks for classification detection and segmentation. (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"Tel Aviv","author":"Hu Lianyu","year":"2022","unstructured":"Lianyu Hu, Liqing Gao, Zekang Liu, and Wei Feng. 2022. Temporal lift pooling for continuous sign language recognition. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXV. 511--527."},{"key":"e_1_3_2_1_21_1","volume-title":"Self-Emphasizing Network for Continuous Sign Language Recognition. In Thirty-seventh AAAI conference on artificial intelligence.","author":"Hu Lianyu","year":"2023","unstructured":"Lianyu Hu, Liqing Gao, Zekang Liu, and Wei Feng. 2023. Self-Emphasizing Network for Continuous Sign Language Recognition. In Thirty-seventh AAAI conference on artificial intelligence."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"e_1_3_2_1_23_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5 MB model size. arXiv preprint arXiv:1602.07360","author":"Iandola Forrest N","year":"2016","unstructured":"Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)."},{"key":"e_1_3_2_1_24_1","volume-title":"Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144","author":"Jang Eric","year":"2016","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)."},{"key":"e_1_3_2_1_25_1","volume-title":"Hermann Ney, and Richard Bowden.","author":"Koller Oscar","year":"2019","unstructured":"Oscar Koller, Necati Cihan Camgoz, Hermann Ney, and Richard Bowden. 2019. Weakly supervised learning with multi-stream CNN-LSTM-HMMs to discover sequential parallelism in sign language videos. IEEE transactions on pattern analysis and machine intelligence, Vol. 42, 9 (2019), 2306--2320."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.013"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.412"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.136"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.364"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"e_1_3_2_1_33_1","volume-title":"Adafuse: Adaptive temporal fusion network for efficient action recognition. arXiv preprint arXiv:2102.05775","author":"Meng Yue","year":"2021","unstructured":"Yue Meng, Rameswar Panda, Chung-Ching Lin, Prasanna Sattigeri, Leonid Karlinsky, Kate Saenko, Aude Oliva, and Rogerio Feris. 2021. Adafuse: Adaptive temporal fusion network for efficient action recognition. arXiv preprint arXiv:2102.05775 (2021)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_11"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413931"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00429"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_2_1_39_1","volume-title":"International conference on machine learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"e_1_3_2_1_41_1","volume-title":"Glance and focus: a dynamic approach to reducing spatial redundancy in image classification. arXiv preprint arXiv:2010.05300","author":"Wang Yulin","year":"2020","unstructured":"Yulin Wang, Kangchen Lv, Rui Huang, Shiji Song, Le Yang, and Gao Huang. 2020. Glance and focus: a dynamic approach to reducing spatial redundancy in image classification. arXiv preprint arXiv:2010.05300 (2020)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"e_1_3_2_1_43_1","volume-title":"A dynamic frame selection framework for fast video recognition","author":"Wu Zuxuan","year":"2020","unstructured":"Zuxuan Wu, Hengduo Li, Caiming Xiong, Yu-Gang Jiang, and Larry Steven Davis. 2020. A dynamic frame selection framework for fast video recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)."},{"key":"e_1_3_2_1_44_1","volume-title":"Liteeval: A coarse-to-fine framework for resource efficient video recognition. Advances in neural information processing systems","author":"Wu Zuxuan","year":"2019","unstructured":"Zuxuan Wu, Caiming Xiong, Yu-Gang Jiang, and Larry S Davis. 2019b. Liteeval: A coarse-to-fine framework for resource efficient video recognition. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"e_1_3_2_1_48_1","volume-title":"SF-Net: Structured feature network for continuous sign language recognition. arXiv preprint arXiv:1908.01341","author":"Yang Zhaoyang","year":"2019","unstructured":"Zhaoyang Yang, Zhenmei Shi, Xiaoyong Shen, and Yu-Wing Tai. 2019. SF-Net: Structured feature network for continuous sign language recognition. arXiv preprint arXiv:1908.01341 (2019)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7001"},{"key":"e_1_3_2_1_51_1","volume-title":"Dynamic Resolution Network. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Zhu Mingjian","year":"2021","unstructured":"Mingjian Zhu, Kai Han, Enhua Wu, Qiulin Zhang, Ying Nie, Zhenzhong Lan, and Yunhe Wang. 2021. Dynamic Resolution Network. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 27319--27330. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/e56954b4f6347e897f954495eab16a88-Abstract.html"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00507"}],"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\/3581783.3611745","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:09:26Z","timestamp":1755821366000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":52,"alternative-id":["10.1145\/3581783.3611745","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611745","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"}}]}}