{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:02:01Z","timestamp":1783530121164,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":69,"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":[{"name":"the National Natural Science Foundation of China","award":["61932009"],"award-info":[{"award-number":["61932009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612466","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"3696-3705","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Saliency Prototype for RGB-D and RGB-T Salient Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9664-0218","authenticated-orcid":false,"given":"Zihao","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7266-8179","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2768-1398","authenticated-orcid":false,"given":"Yahong","family":"Han","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, 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.2009.5206596"},{"key":"e_1_3_2_1_2_1","volume-title":"Salient object detection: A survey. Computational visual media","author":"Borji Ali","year":"2019","unstructured":"Ali Borji, Ming-Ming Cheng, Qibin Hou, Huaizu Jiang, and Jia Li. 2019. Salient object detection: A survey. Computational visual media, Vol. 5 (2019), 117--150."},{"key":"e_1_3_2_1_3_1","volume-title":"Salient object detection: A benchmark","author":"Borji Ali","year":"2015","unstructured":"Ali Borji, Ming-Ming Cheng, Huaizu Jiang, and Jia Li. 2015a. Salient object detection: A benchmark. IEEE transactions on image processing, Vol. 24, 12 (2015), 5706--5722."},{"key":"e_1_3_2_1_4_1","volume-title":"Salient object detection: A benchmark","author":"Borji Ali","year":"2015","unstructured":"Ali Borji, Ming-Ming Cheng, Huaizu Jiang, and Jia Li. 2015b. Salient object detection: A benchmark. IEEE transactions on image processing, Vol. 24, 12 (2015), 5706--5722."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3166914"},{"key":"e_1_3_2_1_6_1","volume-title":"Modality-Induced Transfer-Fusion Network for RGB-D and RGB-T Salient Object Detection","author":"Chen Gang","year":"2022","unstructured":"Gang Chen, Feng Shao, Xiongli Chai, Hangwei Chen, Qiuping Jiang, Xiangchao Meng, and Yo-Sung Ho. 2022b. Modality-Induced Transfer-Fusion Network for RGB-D and RGB-T Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16191"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2632856.2632866"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2669880"},{"key":"e_1_3_2_1_10_1","volume-title":"An in depth view of saliency","author":"Ciptadi Arridhana","unstructured":"Arridhana Ciptadi, Tucker Hermans, and James M Rehg. 2013. An in depth view of saliency. Georgia Institute of Technology."},{"key":"e_1_3_2_1_11_1","volume-title":"Does thermal really always matter for RGB-T salient object detection? IEEE Transactions on Multimedia","author":"Cong Runmin","year":"2022","unstructured":"Runmin Cong, Kepu Zhang, Chen Zhang, Feng Zheng, Yao Zhao, Qingming Huang, and Sam Kwong. 2022. Does thermal really always matter for RGB-T salient object detection? IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Karthik Desingh K Madhava Krishna Deepu Rajan and CV Jawahar. 2013. Depth really Matters: Improving Visual Salient Region Detection with Depth.. In BMVC. 1--11.","DOI":"10.5244\/C.27.98"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459296"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"e_1_3_2_1_15_1","volume-title":"Enhanced-alignment measure for binary foreground map evaluation. arXiv preprint arXiv:1805.10421","author":"Fan Deng-Ping","year":"2018","unstructured":"Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, and Ali Borji. 2018. Enhanced-alignment measure for binary foreground map evaluation. arXiv preprint arXiv:1805.10421 (2018)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"e_1_3_2_1_18_1","volume-title":"CNNs-based RGB-D saliency detection via cross-view transfer and multiview fusion","author":"Han Junwei","year":"2017","unstructured":"Junwei Han, Hao Chen, Nian Liu, Chenggang Yan, and Xuelong Li. 2017. CNNs-based RGB-D saliency detection via cross-view transfer and multiview fusion. IEEE transactions on cybernetics, Vol. 48, 11 (2017), 3171--3183."},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR, 597--606","author":"Hong Seunghoon","year":"2015","unstructured":"Seunghoon Hong, Tackgeun You, Suha Kwak, and Bohyung Han. 2015. Online tracking by learning discriminative saliency map with convolutional neural network. In International conference on machine learning. PMLR, 597--606."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3020735"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069812"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069812"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102268"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3185323"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00935"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3180274"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02687-7"},{"key":"e_1_3_2_1_29_1","volume-title":"Tel Aviv","author":"Lee Minhyeok","year":"2022","unstructured":"Minhyeok Lee, Chaewon Park, Suhwan Cho, and Sangyoun Lee. 2022. Spsn: Superpixel prototype sampling network for rgb-d salient object detection. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIX. Springer, 630--647."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062689"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.029"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475601"},{"key":"e_1_3_2_1_36_1","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 454--461","author":"Niu Yuzhen","year":"2012","unstructured":"Yuzhen Niu, Yujie Geng, Xueqing Li, and Feng Liu. 2012. Leveraging stereopsis for saliency analysis. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 454--461."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"e_1_3_2_1_38_1","volume-title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","author":"Pang Youwei","year":"2023","unstructured":"Youwei Pang, Xiaoqi Zhao, Lihe Zhang, and Huchuan Lu. 2023. CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection. IEEE Transactions on Image Processing (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247743"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00735"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00370"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.323"},{"key":"e_1_3_2_1_44_1","volume-title":"A Potential Vision-Based Measurements Technology: Information Flow Fusion Detection Method Using RGB-Thermal Infrared Images","author":"Song Kechen","year":"2023","unstructured":"Kechen Song, Yanqi Bao, Han Wang, Liming Huang, and Yunhui Yan. 2023. A Potential Vision-Based Measurements Technology: Information Flow Fusion Detection Method Using RGB-Thermal Infrared Images. IEEE Transactions on Instrumentation and Measurement (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Multiple graph affinity interactive network and a variable illumination dataset for RGBT image salient object detection","author":"Song Kechen","year":"2022","unstructured":"Kechen Song, Liming Huang, Aojun Gong, and Yunhui Yan. 2022a. Multiple graph affinity interactive network and a variable illumination dataset for RGBT image salient object detection. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"A novel visible-depth-thermal image dataset of salient object detection for robotic visual perception","author":"Song Kechen","year":"2022","unstructured":"Kechen Song, Jie Wang, Yanqi Bao, Liming Huang, and Yunhui Yan. 2022b. A novel visible-depth-thermal image dataset of salient object detection for robotic visual perception. IEEE\/ASME Transactions on Mechatronics (2022)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00146"},{"key":"e_1_3_2_1_48_1","volume-title":"HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection","author":"Tang Bin","year":"2022","unstructured":"Bin Tang, Zhengyi Liu, Yacheng Tan, and Qian He. 2022. HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087412"},{"key":"e_1_3_2_1_50_1","volume-title":"RGBT salient object detection: A large-scale dataset and benchmark","author":"Tu Zhengzheng","year":"2022","unstructured":"Zhengzheng Tu, Yan Ma, Zhun Li, Chenglong Li, Jieming Xu, and Yongtao Liu. 2022. RGBT salient object detection: A large-scale dataset and benchmark. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00032"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1702-6_36"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099120"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105162"},{"key":"e_1_3_2_1_56_1","volume-title":"Saliency-aware video object segmentation","author":"Wang Wenguan","year":"2017","unstructured":"Wenguan Wang, Jianbing Shen, Ruigang Yang, and Fatih Porikli. 2017. Saliency-aware video object segmentation. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 1 (2017), 20--33."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123548"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00092"},{"key":"e_1_3_2_1_59_1","first-page":"8","article-title":"Multi-modal Circulant Fusion for Video-to-Language and Backward","volume":"3","author":"Wu Aming","year":"2018","unstructured":"Aming Wu and Yahong Han. 2018. Multi-modal Circulant Fusion for Video-to-Language and Backward.. In IJCAI, Vol. 3. 8.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00943"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3229640"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241196"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475364"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475240"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_39"},{"key":"e_1_3_2_1_66_1","volume-title":"Tel Aviv","author":"Zhou Jiayuan","year":"2022","unstructured":"Jiayuan Zhou, Lijun Wang, Huchuan Lu, Kaining Huang, Xinchu Shi, and Bocong Liu. 2022. Mvsalnet: Multi-view augmentation for rgb-d salient object detection. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIX. Springer, 270--287."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00464"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3118043"}],"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\/3581783.3612466","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:24Z","timestamp":1755821184000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612466"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":69,"alternative-id":["10.1145\/3581783.3612466","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612466","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"}}]}}