{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T10:08:46Z","timestamp":1756462126410,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T00:00:00Z","timestamp":1735516800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T00:00:00Z","timestamp":1735516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"the National Science Foundation of China","award":["62272426"],"award-info":[{"award-number":["62272426"]}]},{"name":"the Shanxi Province Science and Technology Major Special Project","award":["202201150401021"],"award-info":[{"award-number":["202201150401021"]}]},{"name":"the Shanxi Province Science and Technology Achievements Transformation Guidance Special Project","award":["202104021301055"],"award-info":[{"award-number":["202104021301055"]}]},{"name":"the Natural Science Foundation of Shanxi Province","award":["202303021211153"],"award-info":[{"award-number":["202303021211153"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s40747-024-01746-z","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:43:37Z","timestamp":1735587817000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Semantic-enhanced panoptic scene graph generation through hybrid and axial attentions"],"prefix":"10.1007","volume":"11","author":[{"given":"Xinhe","family":"Kuang","sequence":"first","affiliation":[]},{"given":"Yuxin","family":"Che","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8387-8633","authenticated-orcid":false,"given":"Huiyan","family":"Han","sequence":"additional","affiliation":[]},{"given":"Yimin","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,30]]},"reference":[{"issue":"1","key":"1746_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2021.3137605","volume":"45","author":"X Chang","year":"2021","unstructured":"Chang X, Ren P, Xu P, Li Z, Chen X, Hauptmann A (2021) A comprehensive survey of scene graphs: generation and application. IEEE Trans Pattern Anal Mach Intell 45(1):1\u201326","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1746_CR2","doi-asserted-by":"crossref","unstructured":"Chaudhuri A, Bhunia AK, Song Y-Z, Dutta A (2023) Data-free sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 12084\u201312093","DOI":"10.1109\/CVPR52729.2023.01163"},{"key":"1746_CR3","doi-asserted-by":"crossref","unstructured":"Zeng Y, Jin Q, Bao T, Li W (2023) Multi-modal knowledge hypergraph for diverse image retrieval. In: Proceedings of the AAAI conference on artificial intelligence, pp 3376\u20133383","DOI":"10.1609\/aaai.v37i3.25445"},{"key":"1746_CR4","doi-asserted-by":"crossref","unstructured":"Koner R, Li H, Hildebrandt M, Das D, Tresp V, G\u00fcnnemann S (2021) Graphhopper: Multi-hop scene graph reasoning for visual question answering. In: The Semantic Web\u2013ISWC 2021: 20th international semantic web conference, ISWC 2021, Virtual Event, October 24\u201328, 2021, Proceedings 20, pp 111\u2013127","DOI":"10.1007\/978-3-030-88361-4_7"},{"key":"1746_CR5","doi-asserted-by":"crossref","unstructured":"Liang C, Wang W, Zhou T, Yang Y (2022) Visual abductive reasoning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15565\u201315575","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"1746_CR6","doi-asserted-by":"crossref","unstructured":"Nooralahzadeh, F., & Sennrich, R. (2023) Improving the cross-lingual generalisation in visual question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 13419\u201313427.","DOI":"10.1609\/aaai.v37i11.26574"},{"issue":"12","key":"1746_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3523-6","volume":"65","author":"J Wang","year":"2022","unstructured":"Wang J, Li Y, Pan Y, Yao T, Tang J, Mei T (2022) Contextual and selective attention networks for image captioning. SCIENCE CHINA Inf Sci 65(12):222103","journal-title":"SCIENCE CHINA Inf Sci"},{"key":"1746_CR8","doi-asserted-by":"crossref","unstructured":"Wang N, Xie J, Luo H, Cheng Q, Wu J, Jia M, Li L (2023) Efficient image captioning for edge devices. In: Proceedings of the AAAI conference on artificial intelligence, pp 2608\u20132616","DOI":"10.1609\/aaai.v37i2.25359"},{"issue":"2","key":"1746_CR9","doi-asserted-by":"publisher","first-page":"5560","DOI":"10.1109\/LRA.2022.3157567","volume":"7","author":"S Amiri","year":"2022","unstructured":"Amiri S, Chandan K, Zhang S (2022) Reasoning with scene graphs for robot planning under partial observability. IEEE Robot Autom Lett 7(2):5560\u20135567","journal-title":"IEEE Robot Autom Lett"},{"key":"1746_CR10","doi-asserted-by":"crossref","unstructured":"Gadre SY, Ehsani K, Song S, Mottaghi R (2022) Continuous scene representations for embodied ai. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14849\u201314859","DOI":"10.1109\/CVPR52688.2022.01443"},{"key":"1746_CR11","doi-asserted-by":"crossref","unstructured":"Yang J, Ang YZ, Guo Z, Zhou K, Zhang W, Liu Z (2022) Panoptic scene graph generation. In: European conference on computer vision, pp 178\u2013196","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"1746_CR12","doi-asserted-by":"crossref","unstructured":"Zhang A, Yao Y, Chen Q, Ji W, Liu Z, Sun M, Chua TS (2022) Fine-grained scene graph generation with data transfer. In: European Conference on Computer Vision, pp 409\u2013424","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"1746_CR13","doi-asserted-by":"crossref","unstructured":"Li L, Ji W, Wu Y, Li M, Qin Y, Wei L, Zimmermann R (2024) Panoptic scene graph generation with semantics-prototype learning. In: Proceedings of the AAAI conference on artificial intelligence, pp 3145\u20133153","DOI":"10.1609\/aaai.v38i4.28098"},{"key":"1746_CR14","doi-asserted-by":"crossref","unstructured":"Xu D, Zhu Y, Choy CB, Fei-Fei L (2017) Scene graph generation by iterative message passing. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5410\u20135419","DOI":"10.1109\/CVPR.2017.330"},{"key":"1746_CR15","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\/CVF conference on computer vision and pattern recognition, pp 5831\u20135840","DOI":"10.1109\/CVPR.2018.00611"},{"key":"1746_CR16","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, pp 6619\u20136628.","DOI":"10.1109\/CVPR.2019.00678"},{"key":"1746_CR17","doi-asserted-by":"crossref","unstructured":"Zareian A, Karaman S, Chang S-F (2020) Bridging knowledge graphs to generate scene graphs. In: Computer Vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIII 16, pp 606\u2013623","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"1746_CR18","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28"},{"key":"1746_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov A, Girshick R, He K, Doll\u00e1r P (2019) Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6399\u20136408","DOI":"10.1109\/CVPR.2019.00656"},{"key":"1746_CR20","doi-asserted-by":"crossref","unstructured":"Teng Y, Wang L (2022) Structured sparse r-cnn for direct scene graph generation. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition, pp 19437\u201319446.","DOI":"10.1109\/CVPR52688.2022.01883"},{"key":"1746_CR21","doi-asserted-by":"crossref","unstructured":"Lorenz, J., Sch\u00f6n, R., Ludwig, K., & Lienhart, R. (2024) A Review and Efficient Implementation of Scene Graph Generation Metrics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2567\u20132575.","DOI":"10.1109\/CVPRW63382.2024.00263"},{"key":"1746_CR22","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, pp 11109\u201311119","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"1746_CR23","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3389\/fncom.2011.00036","volume":"5","author":"FP Battaglia","year":"2011","unstructured":"Battaglia FP, Pennartz CM (2011) The construction of semantic memory: grammar-based representations learned from relational episodic information. Front Comput Neurosci 5:36","journal-title":"Front Comput Neurosci"},{"key":"1746_CR24","doi-asserted-by":"crossref","unstructured":"Liang S, Zhang L, Xie C, Chen L (2024) Causal intervention for panoptic scene graph generation. In: 2024 IEEE international conference on multimedia and expo (ICME), pp 1\u20136","DOI":"10.1109\/ICME57554.2024.10687509"},{"key":"1746_CR25","doi-asserted-by":"crossref","unstructured":"Yang J, Wang C, Liu Z, Wu J, Wang D, Yang L, Cao X (2023) Focusing on flexible masks: A novel framework for panoptic scene graph generation with relation constraints. In: Proceedings of the 31st ACM international conference on multimedia, pp 4209\u20134218","DOI":"10.1145\/3581783.3612544"},{"key":"1746_CR26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3442301","author":"J Wang","year":"2024","unstructured":"Wang J, Wen Z, Li X, Guo Z, Yang J, Liu Z (2024) Pair then relation: pair-net for panoptic scene graph generation. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2024.3442301","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"1746_CR27","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1109\/TPAMI.2023.3268066","volume":"45","author":"Y Cong","year":"2023","unstructured":"Cong Y, Yang MY, Rosenhahn B (2023) Reltr: relation transformer for scene graph generation. IEEE Trans Pattern Anal Mach Intell 45(9):11169\u201311183","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1746_CR28","doi-asserted-by":"crossref","unstructured":"Kirillov A, He K, Girshick R, Rother C, Doll\u00e1r P (2019) Panoptic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9404\u20139413","DOI":"10.1109\/CVPR.2019.00963"},{"key":"1746_CR29","doi-asserted-by":"crossref","unstructured":"Xiong Y, Liao R, Zhao H, Hu R, Bai M, Yumer E, Urtasun R (2019) Upsnet: A unified panoptic segmentation network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8818\u20138826","DOI":"10.1109\/CVPR.2019.00902"},{"key":"1746_CR30","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng B, Schwing A, Kirillov A (2021) Per-pixel classification is not all you need for semantic segmentation. Adv Neural Inf Process Syst 34:17864\u201317875","journal-title":"Adv Neural Inf Process Syst"},{"key":"1746_CR31","first-page":"10326","volume":"34","author":"W Zhang","year":"2021","unstructured":"Zhang W, Pang J, Chen K, Loy CC (2021) K-net: Towards unified image segmentation. Adv Neural Inf Process Syst 34:10326\u201310338","journal-title":"Adv Neural Inf Process Syst"},{"key":"1746_CR32","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1746_CR33","doi-asserted-by":"publisher","DOI":"10.1177\/03611981241258753","author":"X Dong","year":"2024","unstructured":"Dong X, Shi P, Liang T, Yang A (2024) CTAFFNet: CNN\u2013transformer adaptive feature fusion object detection algorithm for complex traffic scenarios. Transp Res Rec. https:\/\/doi.org\/10.1177\/03611981241258753","journal-title":"Transp Res Rec"},{"key":"1746_CR34","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"1746_CR35","unstructured":"Ho J, Kalchbrenner N, Weissenborn D, Salimans T (2019) Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180"},{"key":"1746_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3402143","author":"H Liu","year":"2024","unstructured":"Liu H, Bhanu B (2024) RepSGG: novel representations of entities and relationships for scene graph generation. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2024.3402143","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1746_CR37","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 (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vision 123:32\u201373","journal-title":"Int J Comput Vision"},{"key":"1746_CR38","doi-asserted-by":"crossref","unstructured":"Zhang J, Shih KJ, Elgammal A, Tao A, Catanzaro B (2019) Graphical contrastive losses for scene graph parsing. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11535\u201311543","DOI":"10.1109\/CVPR.2019.01180"},{"key":"1746_CR39","doi-asserted-by":"crossref","unstructured":"Li R, Zhang S, He X (2022) SGTR: end-to-end scene graph generation with transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19486\u201319496","DOI":"10.1109\/CVPR52688.2022.01888"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01746-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-024-01746-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01746-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T20:19:53Z","timestamp":1738268393000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-024-01746-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,30]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["1746"],"URL":"https:\/\/doi.org\/10.1007\/s40747-024-01746-z","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2024,12,30]]},"assertion":[{"value":"11 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2024","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Data used in our study are publicly available, and ethical approval and informed consent were obtained in each original study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent"}}],"article-number":"110"}}