{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T17:08:56Z","timestamp":1781197736882,"version":"3.54.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T00:00:00Z","timestamp":1771027200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":65,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Jiangsu Provincial Graduate Student Research Innovation Program","award":["SJCX24_0283"],"award-info":[{"award-number":["SJCX24_0283"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62177029"],"award-info":[{"award-number":["62177029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"General Project of Basic Science (Natural Science) Research in Higher Education Institutions in Jiangsu Province","award":["23KJD580002"],"award-info":[{"award-number":["23KJD580002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Scene graph generation aims to detect visual objects and their relationships in images, providing structured representations for visual scene understanding. However, it faces fundamental challenges from extreme long-tail distribution and semantic ambiguities between related predicates. The severe class imbalance\u2014where head classes dominate with abundant samples while tail classes have scarce training instances\u2014creates distinct learning dynamics that existing re-balancing methods fail to address by treating all classes uniformly. We propose Frequency-Adaptive Prototype Learning (FAPL), a unified framework that introduces three key innovations: (1) frequency-aware momentum scheduling that enables head prototypes to stabilize early as knowledge sources while tail prototypes maintain aggressive adaptation to maximize learning from limited samples; (2) pattern-aware supervision that learns semantic confusion patterns between related predicates and adaptively reduces penalties for plausible errors while maintaining full supervision for implausible ones; (3) curriculum learning integration that progressively shifts training emphasis from frequent to rare relationships as the model accumulates semantic understanding. These components form a mutually reinforcing system where early head learning establishes reliable knowledge bases, pattern-aware supervision reduces confusion noise, and curriculum scheduling maximizes tail exploitation. Extensive experiments on Visual Genome, GQA, and Open Images V6 datasets demonstrate that FAPL achieves state-of-the-art performance with substantial improvements over previous best methods: up to 30.3% on Visual Genome, 28.8% on GQA, and 19.9% on Open Images V6, while showing superior generalization capability on recognizing unseen relationship combinations.<\/jats:p>","DOI":"10.1007\/s44443-026-00546-4","type":"journal-article","created":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T11:16:35Z","timestamp":1771067795000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Frequency-adaptive prototype learning for long-tail scene graph generation"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0533-5729","authenticated-orcid":false,"given":"Funing","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YaHong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2750-0315","authenticated-orcid":false,"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,14]]},"reference":[{"key":"546_CR1","volume-title":"Statistical Forecasting for Inventory Control","author":"RG Brown","year":"1959","unstructured":"Brown RG (1959) Statistical Forecasting for Inventory Control. McGraw-Hill, New York"},{"issue":"4","key":"546_CR2","first-page":"512","volume":"32","author":"O \u00c7ift\u00e7i","year":"2024","unstructured":"\u00c7ift\u00e7i O, Soygaz\u0131 F, Tekir S (2024) Enrichment of turkish question answering systems using knowledge graphs. Turk J Electr Eng Comput Sci 32(4):512\u2013531","journal-title":"Turk J Electr Eng Comput Sci"},{"key":"546_CR3","doi-asserted-by":"crossref","unstructured":"Desai A, Wu T-Y, Tripathi S, Vasconcelos N (2021) Learning of visual relations: The devil is in the tails. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 15404\u201315413","DOI":"10.1109\/ICCV48922.2021.01512"},{"key":"546_CR4","doi-asserted-by":"crossref","unstructured":"Dong X, Gan T, Song X, Wu J, Cheng Y, Nie L (2022) Stacked hybrid-attention and group collaborative learning for unbiased scene graph generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 19427\u201319436","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"546_CR5","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep Learning. MIT Press, Cambridge, MA. http:\/\/www.deeplearningbook.org"},{"key":"546_CR6","doi-asserted-by":"crossref","unstructured":"Gordo A, Almaz\u00e1n J, Revaud J, Larlus D (2016) Deep image retrieval: Learning global representations for image search. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision - ECCV 2016. Springer, Cham, pp 241\u2013257","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"546_CR7","doi-asserted-by":"crossref","unstructured":"Guo Y, Gao L, Wang X, Hu Y, Xu X, Lu X, Shen HT, Song J (2021) From general to specific: Informative scene graph generation via balance adjustment. In: Proceedings of the IEEE\/CVF International conference on computer vision (ICCV), pp 16383\u201316392","DOI":"10.1109\/ICCV48922.2021.01607"},{"key":"546_CR8","doi-asserted-by":"publisher","unstructured":"Hossain MZ, Sohel F, Shiratuddin MF, Laga H (2019) A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. 51(6). https:\/\/doi.org\/10.1145\/3295748","DOI":"10.1145\/3295748"},{"key":"546_CR9","doi-asserted-by":"crossref","unstructured":"Hudson DA, Manning CD (2019) Gqa: A new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"546_CR10","doi-asserted-by":"publisher","first-page":"115524","DOI":"10.1016\/j.eswa.2021.115524","volume":"185","author":"Y Imrana","year":"2021","unstructured":"Imrana Y, Xiang Y, Ali L, Abdul-Rauf Z (2021) A bidirectional lstm deep learning approach for intrusion detection. Expert Syst Appl 185:115524. https:\/\/doi.org\/10.1016\/j.eswa.2021.115524","journal-title":"Expert Syst Appl"},{"key":"546_CR11","doi-asserted-by":"crossref","unstructured":"Jeon J, Kim K, Yoon K, Park C (2025) Semantic diversity-aware prototype-based learning for unbiased scene graph generation. In: Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G (eds) Computer Vision - ECCV 2024. Springer, Cham, pp 379\u2013395","DOI":"10.1007\/978-3-031-73113-6_22"},{"key":"546_CR12","doi-asserted-by":"crossref","unstructured":"Johnson J, Krishna R, Stark M, Li L-J, Shamma D, Bernstein M, Fei-Fei L (2015) Image retrieval using scene graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"546_CR13","unstructured":"Kim K, Yoon K, In Y, Moon J, Kim D, Park C (2024) Adaptive self-training framework for fine-grained scene graph generation. arXiv:2401.09786 [cs.CV]"},{"issue":"1","key":"546_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li L-J, Shamma DA et al (2017) Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int J Comput Vision 123(1):32\u201373","journal-title":"Int J Comput Vision"},{"issue":"7","key":"546_CR15","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova A, Rom H, Alldrin N, Uijlings J, Krasin I, Pont-Tuset J, Kamali S, Popov S, Malloci M, Kolesnikov A, Duerig T, Ferrari V (2020) The open images dataset v4. Int J Comput Vision 128(7):1956\u20131981. https:\/\/doi.org\/10.1007\/s11263-020-01316-z","journal-title":"Int J Comput Vision"},{"key":"546_CR16","doi-asserted-by":"crossref","unstructured":"Li R, Zhang S, Wan B, He X (2021) Bipartite graph network with adaptive message passing for unbiased scene graph generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 11109\u201311119","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"546_CR17","doi-asserted-by":"crossref","unstructured":"Li L, Chen G, Xiao J, Yang Y, Wang C, Chen L (2023) Compositional feature augmentation for unbiased scene graph generation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 21685\u201321695","DOI":"10.1109\/ICCV51070.2023.01982"},{"issue":"4","key":"546_CR18","doi-asserted-by":"publisher","first-page":"3145","DOI":"10.1609\/aaai.v38i4.28098","volume":"38","author":"L Li","year":"2024","unstructured":"Li L, Ji W, Wu Y, Li M, Qin Y, Wei L, Zimmermann R (2024) Panoptic scene graph generation with semantics-prototype learning. Proceed AAAI Conf Artif Intell 38(4):3145\u20133153. https:\/\/doi.org\/10.1609\/aaai.v38i4.28098","journal-title":"Proceed AAAI Conf Artif Intell"},{"key":"546_CR19","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.324"},{"key":"546_CR20","doi-asserted-by":"crossref","unstructured":"Lin X, Ding C, Zeng J, Tao D (2020) Gps-net: Graph property sensing network for scene graph generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"546_CR21","doi-asserted-by":"publisher","first-page":"128042","DOI":"10.1016\/j.neucom.2024.128042","volume":"599","author":"R Peng","year":"2024","unstructured":"Peng R, Zhao C, Chen X, Wang Z, Liu Y, Liu Y, Lan X (2024) A causality guided loss for imbalanced learning in scene graph generation. Neurocomputing 599:128042. https:\/\/doi.org\/10.1016\/j.neucom.2024.128042","journal-title":"Neurocomputing"},{"issue":"4","key":"546_CR22","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1137\/0330046","volume":"30","author":"BT Polyak","year":"1992","unstructured":"Polyak BT, Juditsky AB (1992) Acceleration of stochastic approximation by averaging. SIAM J Control Optim 30(4):838\u2013855","journal-title":"SIAM J Control Optim"},{"key":"546_CR23","doi-asserted-by":"crossref","unstructured":"Suhail M, Mittal A, Siddiquie B, Broaddus C, Eledath J, Medioni G, Sigal L (2021) Energy-based learning for scene graph generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 13936\u201313945","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"546_CR24","doi-asserted-by":"publisher","unstructured":"Tang H, He S, Qin J (2025a) Connecting giants: synergistic knowledge transfer of large multimodal models for few-shot learning. In: Proceedings of the thirty-fourth international joint conference on artificial intelligence. IJCAI \u201925. https:\/\/doi.org\/10.24963\/ijcai.2025\/693","DOI":"10.24963\/ijcai.2025\/693"},{"key":"546_CR25","doi-asserted-by":"publisher","unstructured":"Tang H, Li Z, Peng Z, Tang J (2020) Blockmix: Meta regularization and self-calibrated inference for metric-based meta-learning. In: Proceedings of the 28th ACM international conference on multimedia. MM \u201920, pp 610\u2013618. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3394171.3413884","DOI":"10.1145\/3394171.3413884"},{"issue":"3","key":"546_CR26","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.1109\/TPAMI.2024.3511621","volume":"47","author":"H Tang","year":"2025","unstructured":"Tang H, Li Z, Zhang D, He S, Tang J (2025) Divide-and-conquer: Confluent triple-flow network for rgb-t salient object detection. IEEE Trans Pattern Anal Mach Intell 47(3):1958\u20131974. https:\/\/doi.org\/10.1109\/TPAMI.2024.3511621","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"546_CR27","doi-asserted-by":"crossref","unstructured":"Tang K, Niu Y, Huang J, Shi J, Zhang H (2020) Unbiased scene graph generation from biased training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"546_CR28","doi-asserted-by":"publisher","first-page":"108792","DOI":"10.1016\/j.patcog.2022.108792","volume":"130","author":"H Tang","year":"2022","unstructured":"Tang H, Yuan C, Li Z, Tang J (2022) Learning attention-guided pyramidal features for few-shot fine-grained recognition. Pattern Recogn 130:108792. https:\/\/doi.org\/10.1016\/j.patcog.2022.108792","journal-title":"Pattern Recogn"},{"key":"546_CR29","doi-asserted-by":"crossref","unstructured":"Tang K, Zhang H, Wu B, Luo W, Liu W (2019) Learning to compose dynamic tree structures for visual contexts. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"546_CR30","doi-asserted-by":"publisher","first-page":"4173","DOI":"10.1109\/TIP.2022.3181511","volume":"31","author":"L Tao","year":"2022","unstructured":"Tao L, Mi L, Li N, Cheng X, Hu Y, Chen Z (2022) Predicate correlation learning for scene graph generation. IEEE Trans Image Process 31:4173\u20134185. https:\/\/doi.org\/10.1109\/TIP.2022.3181511","journal-title":"IEEE Trans Image Process"},{"key":"546_CR31","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Lu, Polosukhin I (2017) Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30. Curran Associates Inc, ???"},{"key":"546_CR32","doi-asserted-by":"publisher","first-page":"109634","DOI":"10.1016\/j.patcog.2023.109634","volume":"141","author":"Z Wang","year":"2023","unstructured":"Wang Z, Xu X, Luo Y, Wang G, Yang Y (2023a) Hypercomplex context guided interaction modeling for scene graph generation. Pattern Recogn 141:109634. https:\/\/doi.org\/10.1016\/j.patcog.2023.109634","journal-title":"Pattern Recogn"},{"key":"546_CR33","doi-asserted-by":"publisher","unstructured":"Wang J, Zhang C, Huang J, Ren B, Deng Z (2023b) Improving scene graph generation with superpixel-based interaction learning. In: Proceedings of the 31st ACM international conference on multimedia. MM \u201923, pp 1809\u20131820. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3581783.3611889","DOI":"10.1145\/3581783.3611889"},{"key":"546_CR34","doi-asserted-by":"crossref","unstructured":"Wu T, Huang Q, Liu Z, Wang Y, Lin D (2020) Distribution-balanced loss for multi-label classification in long-tailed datasets. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) Computer Vision - ECCV 2020. Springer, Cham, pp 162\u2013178","DOI":"10.1007\/978-3-030-58548-8_10"},{"issue":"9","key":"546_CR35","doi-asserted-by":"publisher","first-page":"9562","DOI":"10.1609\/aaai.v39i9.33036","volume":"39","author":"K Yoon","year":"2025","unstructured":"Yoon K, Kim K, Jeon J, In Y, Kim D, Park C (2025) Ra-sgg: Retrieval-augmented scene graph generation framework via multi-prototype learning. Proceed AAAI Conf Artif Intell 39(9):9562\u20139570. https:\/\/doi.org\/10.1609\/aaai.v39i9.33036","journal-title":"Proceed AAAI Conf Artif Intell"},{"key":"546_CR36","doi-asserted-by":"crossref","unstructured":"Yu J, Chai Y, Wang Y, Hu Y, Wu Q (2021) Cogtree: Cognition tree loss for unbiased scene graph generation. arXiv:2009.07526 [cs.CV]","DOI":"10.24963\/ijcai.2021\/176"},{"key":"546_CR37","doi-asserted-by":"crossref","unstructured":"Zellers R, Yatskar M, Thomson S, Choi Y (2018) Neural motifs: Scene graph parsing with global context. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"546_CR38","doi-asserted-by":"crossref","unstructured":"Zhang H, Kyaw Z, Chang S-F, Chua T-S (2017) Visual translation embedding network for visual relation detection. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 3107\u20133115. https:\/\/doi.org\/10.1109\/CVPR.2017.331","DOI":"10.1109\/CVPR.2017.331"},{"key":"546_CR39","doi-asserted-by":"crossref","unstructured":"Zheng C, Lyu X, Gao L, Dai B, Song J (2023) Prototype-based embedding network for scene graph generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 22783\u201322792","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"546_CR40","doi-asserted-by":"publisher","unstructured":"Zheng C, Lyu X, Guo Y, Zeng P, Song J, Gao L (2022) Learning to generate scene graph from head to tail. In: 2022 IEEE International conference on multimedia and expo (ICME), pp 1\u20136. https:\/\/doi.org\/10.1109\/ICME52920.2022.9859711","DOI":"10.1109\/ICME52920.2022.9859711"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00546-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00546-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00546-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:42:56Z","timestamp":1781196176000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00546-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,14]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["546"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00546-4","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,14]]},"assertion":[{"value":"19 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"132"}}