{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:56:50Z","timestamp":1777489010432,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"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":[[2023,4,30]]},"DOI":"10.1145\/3543873.3587592","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"1286-1295","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["DSNet: Efficient Lightweight Model for Video Salient Object Detection for IoT and WoT Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7110-5147","authenticated-orcid":false,"given":"Hemraj","family":"Singh","sequence":"first","affiliation":[{"name":"National Institute of Technology Warangal, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9772-240X","authenticated-orcid":false,"given":"Mridula","family":"Verma","sequence":"additional","affiliation":[{"name":"Institute for Development and Research in Banking Technology, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1677-5321","authenticated-orcid":false,"given":"Ramalingaswamy","family":"Cheruku","sequence":"additional","affiliation":[{"name":"National Institute of Technology Warangal, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2012.6163000"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01961-4"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings, Part XIII 16","author":"Chen Bowen","year":"2020","unstructured":"Bowen Chen, Huan Ling, Xiaohui Zeng, Jun Gao, Ziyue Xu, and Sanja Fidler. 2020. Scribblebox: Interactive annotation framework for video object segmentation. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIII 16, Vol.\u00a016. Springer, UK, 293\u2013310."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3095843"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068644"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2908779"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"e_1_3_2_1_11_1","volume-title":"PSNet: Parallel symmetric network for video salient object detection","author":"Cong Runmin","year":"2022","unstructured":"Runmin Cong, Weiyu Song, Jianjun Lei, Guanghui Yue, Yao Zhao, and Sam Kwong. 2022. PSNet: Parallel symmetric network for video salient object detection. IEEE Transactions on Emerging Topics in Computational Intelligence 5 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6699"},{"key":"e_1_3_2_1_13_1","volume-title":"Cognitive vision inspired object segmentation metric and loss function. SCIENTIA SINICA Informationis 6","author":"Fan Deng-Ping","year":"2021","unstructured":"Deng-Ping Fan, Ge-Peng Ji, Xuebin Qin, and Ming-Ming Cheng. 2021. Cognitive vision inspired object segmentation metric and loss function. SCIENTIA SINICA Informationis 6 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"e_1_3_2_1_15_1","volume-title":"Shifting More Attention to Video Salient Object Detection","author":"Fan Deng-Ping","unstructured":"Deng-Ping Fan, Wenguan Wang, Ming-Ming Cheng, and Jianbing Shen. 2019. Shifting More Attention to Video Salient Object Detection. In IEEE CVPR, Vol.\u00a032. IEEE, Long Beach, CA."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2679898"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6718"},{"key":"e_1_3_2_1_18_1","volume-title":"Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance. arXiv preprint arXiv:2211.05364 10","author":"Hu Chao","year":"2022","unstructured":"Chao Hu and Liqiang Zhu. 2022. Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance. arXiv preprint arXiv:2211.05364 10 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_48"},{"key":"e_1_3_2_1_20_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 34","author":"Iandola N","year":"2016","unstructured":"Forrest\u00a0N Iandola, Song Han, Matthew\u00a0W Moskewicz, Khalid Ashraf, William\u00a0J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 34 (2016)."},{"key":"e_1_3_2_1_21_1","volume-title":"Progressively Normalized Self-Attention Network for Video Polyp Segmentation. arXiv preprint arXiv:2105.08468 24","author":"Ji Ge-Peng","year":"2021","unstructured":"Ge-Peng Ji, Yu-Cheng Chou, Deng-Ping Fan, Geng Chen, Huazhu Fu, Debesh Jha, and Ling Shao. 2021. Progressively Normalized Self-Attention Network for Video Polyp Segmentation. arXiv preprint arXiv:2105.08468 24 (2021)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00488"},{"key":"e_1_3_2_1_23_1","volume-title":"CASNet: A cross-attention siamese network for video salient object detection","author":"Ji Yuzhu","year":"2020","unstructured":"Yuzhu Ji, Haijun Zhang, Zequn Jie, Lin Ma, and QM\u00a0Jonathan Wu. 2020. CASNet: A cross-attention siamese network for video salient object detection. IEEE transactions on neural networks and learning systems 32, 6 (2020), 2676\u20132690."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00916"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Spring48590.2020.9128749"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3145483"},{"key":"e_1_3_2_1_27_1","volume-title":"Tiny-DSOD: Lightweight object detection for resource-restricted usages. arXiv preprint arXiv:1807.11013 29","author":"Li Yuxi","year":"2018","unstructured":"Yuxi Li, Jiuwei Li, Weiyao Lin, and Jianguo Li. 2018. Tiny-DSOD: Lightweight object detection for resource-restricted usages. arXiv preprint arXiv:1807.11013 29 (2018)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3065239"},{"key":"e_1_3_2_1_30_1","volume-title":"Depth-Cooperated Trimodal Network for Video Salient Object Detection. arXiv preprint arXiv:2202.06060 29","author":"Lu Yukang","year":"2022","unstructured":"Yukang Lu, Dingyao Min, Keren Fu, and Qijun Zhao. 2022. Depth-Cooperated Trimodal Network for Video Salient Object Detection. arXiv preprint arXiv:2202.06060 29 (2022), 25."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"e_1_3_2_1_32_1","volume-title":"Transvos: Video object segmentation with transformers. arXiv preprint arXiv:2106.00588 43","author":"Mei Jianbiao","year":"2021","unstructured":"Jianbiao Mei, Mengmeng Wang, Yeneng Lin, Yi Yuan, and Yong Liu. 2021. Transvos: Video object segmentation with transformers. arXiv preprint arXiv:2106.00588 43 (2021)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42835-021-00960-w"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"e_1_3_2_1_35_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019), 8026\u20138037."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2918730"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_13"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings, Part XV 16","author":"Seo Seonguk","year":"2020","unstructured":"Seonguk Seo, Joon-Young Lee, and Bohyung Han. 2020. Urvos: Unified referring video object segmentation network with a large-scale benchmark. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV 16, Vol.\u00a016. Springer, Virtual Event, 208\u2013223."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.09.064"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00579"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"e_1_3_2_1_46_1","volume-title":"Pelee: A real-time object detection system on mobile devices. Advances in neural information processing systems 31","author":"Wang J","year":"2018","unstructured":"Robert\u00a0J Wang, Xiang Li, and Charles\u00a0X Ling. 2018. Pelee: A real-time object detection system on mobile devices. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_47_1","volume-title":"Paying attention to video object pattern understanding","author":"Wang Wenguan","year":"2020","unstructured":"Wenguan Wang, Jianbing Shen, Xiankai Lu, Steven\u00a0CH Hoi, and Haibin Ling. 2020. Paying attention to video object pattern understanding. IEEE transactions on pattern analysis and machine intelligence 43 (2020), 2413 \u2013 2428."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036533"},{"key":"e_1_3_2_1_49_1","volume-title":"Contrastive Video-Language Learning with Fine-grained Frame Sampling. arXiv preprint arXiv:2210.05039 2","author":"Wang Zixu","year":"2022","unstructured":"Zixu Wang, Yujie Zhong, Yishu Miao, Lin Ma, and Lucia Specia. 2022. Contrastive Video-Language Learning with Fine-grained Frame Sampling. arXiv preprint arXiv:2210.05039 2 (2022)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107433"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3070200"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00738"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"e_1_3_2_1_54_1","volume-title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation. arXiv preprint arXiv:2210.09782 36","author":"Yang Zongxin","year":"2022","unstructured":"Zongxin Yang and Yi Yang. 2022. Decoupling Features in Hierarchical Propagation for Video Object Segmentation. arXiv preprint arXiv:2210.09782 36 (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413942"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00866"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00158"},{"key":"e_1_3_2_1_58_1","volume-title":"Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection. arXiv preprint arXiv:2208.03918 30, 10","author":"Zhang Wenbo","year":"2022","unstructured":"Wenbo Zhang, Keren Fu, Zhuo Wang, Ge-Peng Ji, and Qijun Zhao. 2022. Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection. arXiv preprint arXiv:2208.03918 30, 10 (2022)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587592","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3587592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:31:06Z","timestamp":1755819066000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":59,"alternative-id":["10.1145\/3543873.3587592","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3587592","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}