{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T04:48:15Z","timestamp":1773550095344,"version":"3.50.1"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272342, 62306212, and T2422015"],"award-info":[{"award-number":["62272342, 62306212, and T2422015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100006606","name":"Tianjin Natural Science Foundation","doi-asserted-by":"crossref","award":["23JCJQJC00070 and 24PTLYHZ00320"],"award-info":[{"award-number":["23JCJQJC00070 and 24PTLYHZ00320"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Light Field Salient Object Detection (LFSOD) aims to identify visually distinctive regions by leveraging the complementary spatial\u2013angular information inherent in 4D light field imagery. A major challenge lies in modeling angular dependencies and maintaining spatial coherence under sparse supervision. In this article, we propose a weakly supervised network that consists of three interdependent modules. First, the Light Field Division (LFD) module utilizes epipolar geometry to extract direction-aware boundary features, enhancing the encoding of angular disparities. Second, the Light Field Spatial Association (LFSA) module anchors cross-view feature alignment using central-viewpoint annotations, thereby enforcing spatial consistency and mitigating redundant representations. Third, the Light Field Saliency Local Clustering (LFLC) module introduces a joint boundary-appearance modeling strategy that integrates adaptive clustering with error-aware regularization to refine structural predictions. Experiments on three benchmark datasets show that our method consistently outperforms mainstream weakly supervised approaches. It also achieves superior performance compared to several fully supervised methods.<\/jats:p>","DOI":"10.1145\/3788871","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T14:07:04Z","timestamp":1768831624000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Spatial\u2013Angular Representation Learning for Point-Supervised Salient Object Detection in Light Fields"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0450-6881","authenticated-orcid":false,"given":"Xinbo","family":"Geng","sequence":"first","affiliation":[{"name":"Engineering Research Center of Learning-Based Intelligent System (Ministry of Education), Tianjin University of Technology, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2074-0228","authenticated-orcid":false,"given":"Fan","family":"Shi","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Learning-Based Intelligent System (Ministry of Education), Tianjin University of Technology, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4724-5748","authenticated-orcid":false,"given":"Xu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Learning-Based Intelligent System (Ministry of Education), Tianjin University of Technology, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7535-479X","authenticated-orcid":false,"given":"Chen","family":"Jia","sequence":"additional","affiliation":[{"name":"Tianjin University of Technology, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6705-3831","authenticated-orcid":false,"given":"Shengyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tianjin University of Technology, Tianjin, China"}]}],"member":"320","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3290600"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6633"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611982"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3205182"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3169431"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3073689"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235415"},{"key":"e_1_3_1_9_2","unstructured":"Wei Ji Jingjing Li Qi Bi Chuan Guo Jie Liu and Li Cheng. 2022. Promoting saliency from depth: Deep unsupervised RGB-D saliency detection. arXiv:2205.07179. Retrieved from https:\/\/arxiv.org\/abs\/2205.07179"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3115204"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3498331"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.056"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475312"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_36"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285249"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12308"},{"key":"e_1_3_1_17_2","first-page":"11945","article-title":"Joint semantic mining for weakly supervised RGB-D salient object detection","volume":"34","author":"Li Jingjing","year":"2021","unstructured":"Jingjing Li, Wei Ji, Qi Bi, Cheng Yan, Miao Zhang, Yongri Piao, Huchuan Lu, and Li Cheng. 2021. Joint semantic mining for weakly supervised RGB-D salient object detection. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 34, 11945\u201311959.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299158"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.359"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3207605"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676967"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281465"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3493799"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3232209"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275031"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00220"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3234702"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3095512"},{"key":"e_1_3_1_29_2","unstructured":"Yongri Piao Zhengkun Rong Shuang Xu Miao Zhang and Huchuan Lu. 2020. DUT-LFSaliency: Versatile dataset and light field-to-RGB saliency detection. arXiv:2012.15124. Retrieved from https:\/\/arxiv.org\/abs\/2012.15124"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00410"},{"issue":"12","key":"e_1_3_1_31_2","first-page":"3456","article-title":"CATNet: A cascaded and aggregated transformer network for RGB-D salient object detection","volume":"25","author":"Sun Fuming","year":"2023","unstructured":"Fuming Sun, Peng Ren, Bowen Yin, Fasheng Wang, and Haojie Li. 2023. CATNet: A cascaded and aggregated transformer network for RGB-D salient object detection. IEEE Transactions on Multimedia 25, 12 (2023), 3456\u20133468.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202563"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01883"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00711"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25351"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548275"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105403"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00967"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3164550"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20206"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548037"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00038"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16434"},{"key":"e_1_3_1_44_2","unstructured":"Yao Yuan Wutao Liu Pan Gao Qun Dai and Jie Qin. 2024. Unified unsupervised salient object detection via knowledge transfer. arXiv:2404.14759. Retrieved from https:\/\/arxiv.org\/abs\/2404.14759"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2970529"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3107956"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01256"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296581"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475240"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268217"},{"key":"e_1_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Yi Zhang Geng Chen Qian Chen Yujia Sun Yong Xia Olivier Deforges Wassim Hamidouche and Lu Zhang. 2021. Learning synergistic attention for light field salient object detection. arXiv:2104.13916. Retrieved from https:\/\/arxiv.org\/abs\/2104.13916","DOI":"10.5244\/C.35.51"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01655"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3437685"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3203595"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00701"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242775"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12164"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T03:48:24Z","timestamp":1773546504000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788871"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":56,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3788871"],"URL":"https:\/\/doi.org\/10.1145\/3788871","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]},"assertion":[{"value":"2025-06-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}