{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:22:53Z","timestamp":1783635773225,"version":"3.55.0"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.knosys.2026.116399","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:17:18Z","timestamp":1781223438000},"page":"116399","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DATR: Depth-aware transformer for hierarchical and fine-grained scene graph generation"],"prefix":"10.1016","volume":"348","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6561-2034","authenticated-orcid":false,"given":"Qinghao","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4871-8234","authenticated-orcid":false,"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7971-748X","authenticated-orcid":false,"given":"Jiaxin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7910-8254","authenticated-orcid":false,"given":"Yuwen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1673-519X","authenticated-orcid":false,"given":"Xuehu","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuohao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1804-9198","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116399_b1","doi-asserted-by":"crossref","unstructured":"T. Liu, R. Li, C. Wang, X. He, Relation-aware hierarchical prompt for open-vocabulary scene graph generation, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2025, pp. 5576\u20135584.","DOI":"10.1609\/aaai.v39i5.32594"},{"key":"10.1016\/j.knosys.2026.116399_b2","first-page":"1","article-title":"Generic scene graph generation model with hierarchical prompt learning","author":"Zhu","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116399_b3","series-title":"36th British Machine Vision Conference 2025, BMVC 2025, Sheffield, UK, November 24-27, 2025","article-title":"REACT: Real-time efficiency and accuracy compromise for tradeoffs in scene graph generation","author":"Neau","year":"2025"},{"key":"10.1016\/j.knosys.2026.116399_b4","series-title":"Scene graph reasoning for visual question answering","author":"Hildebrandt","year":"2020"},{"key":"10.1016\/j.knosys.2026.116399_b5","doi-asserted-by":"crossref","unstructured":"X. Yang, K. Tang, H. Zhang, J. Cai, Auto-encoding scene graphs for image captioning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10685\u201310694.","DOI":"10.1109\/CVPR.2019.01094"},{"key":"10.1016\/j.knosys.2026.116399_b6","doi-asserted-by":"crossref","unstructured":"J. Johnson, R. Krishna, M. Stark, L.-J. Li, D. Shamma, M. Bernstein, L. Fei-Fei, Image retrieval using scene graphs, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2015, pp. 3668\u20133678.","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"10.1016\/j.knosys.2026.116399_b7","doi-asserted-by":"crossref","unstructured":"R. Zellers, M. Yatskar, S. Thomson, Y. Choi, Neural motifs: Scene graph parsing with global context, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 5831\u20135840.","DOI":"10.1109\/CVPR.2018.00611"},{"key":"10.1016\/j.knosys.2026.116399_b8","doi-asserted-by":"crossref","unstructured":"D. Xu, Y. Zhu, C.B. Choy, L. Fei-Fei, Scene graph generation by iterative message passing, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2017, pp. 5410\u20135419.","DOI":"10.1109\/CVPR.2017.330"},{"key":"10.1016\/j.knosys.2026.116399_b9","doi-asserted-by":"crossref","unstructured":"Z. Chen, S. Rezayi, S. Li, More knowledge, less bias: Unbiasing scene graph generation with explicit ontological adjustment, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 4023\u20134032.","DOI":"10.1109\/WACV56688.2023.00401"},{"key":"10.1016\/j.knosys.2026.116399_b10","doi-asserted-by":"crossref","unstructured":"S. Sharifzadeh, S.M. Baharlou, M. Berrendorf, R. Koner, V. Tresp, Improving visual relation detection using depth maps, in: 2020 25th International Conference on Pattern Recognition, ICPR, 2021, pp. 3597\u20133604.","DOI":"10.1109\/ICPR48806.2021.9412945"},{"key":"10.1016\/j.knosys.2026.116399_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106142","article-title":"RDBN: Visual relationship detection with inaccurate RGB-D images","volume":"204","author":"Liu","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116399_b12","series-title":"AAAI","first-page":"3203","article-title":"DepthFM: Fast generative monocular depth estimation with flow matching","author":"Gui","year":"2025"},{"key":"10.1016\/j.knosys.2026.116399_b13","doi-asserted-by":"crossref","unstructured":"R. Li, S. Zhang, X. He, Sgtr: End-to-end scene graph generation with transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19486\u201319496.","DOI":"10.1109\/CVPR52688.2022.01888"},{"issue":"9","key":"10.1016\/j.knosys.2026.116399_b14","doi-asserted-by":"crossref","first-page":"11169","DOI":"10.1109\/TPAMI.2023.3268066","article-title":"Reltr: Relation transformer for scene graph generation","volume":"45","author":"Cong","year":"2023","journal-title":"TPAMI"},{"key":"10.1016\/j.knosys.2026.116399_b15","doi-asserted-by":"crossref","unstructured":"J. Im, J. Nam, N. Park, H. Lee, S. Park, Egtr: Extracting graph from transformer for scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 24229\u201324238.","DOI":"10.1109\/CVPR52733.2024.02287"},{"key":"10.1016\/j.knosys.2026.116399_b16","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.knosys.2026.116399_b17","series-title":"ICLR","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116399_b18","doi-asserted-by":"crossref","unstructured":"Y. Teng, L. Wang, Structured sparse r-cnn for direct scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19437\u201319446.","DOI":"10.1109\/CVPR52688.2022.01883"},{"key":"10.1016\/j.knosys.2026.116399_b19","first-page":"24295","article-title":"Iterative scene graph generation","volume":"35","author":"Khandelwal","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.knosys.2026.116399_b20","doi-asserted-by":"crossref","unstructured":"H. Liu, N. Yan, M. Mortazavi, B. Bhanu, Fully convolutional scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11546\u201311556.","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"10.1016\/j.knosys.2026.116399_b21","series-title":"Hydra-sgg: Hybrid relation assignment for one-stage scene graph generation","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.116399_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103260","article-title":"BCTR: bidirectional conditioning transformer for scene graph generation","author":"Hao","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2026.116399_b23","doi-asserted-by":"crossref","unstructured":"R. Li, S. Zhang, B. Wan, X. He, 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, 2021, pp. 11109\u201311119.","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"10.1016\/j.knosys.2026.116399_b24","doi-asserted-by":"crossref","unstructured":"M. Suhail, A. Mittal, B. Siddiquie, C. Broaddus, J. Eledath, G. Medioni, L. Sigal, Energy-based learning for scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13936\u201313945.","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"10.1016\/j.knosys.2026.116399_b25","doi-asserted-by":"crossref","unstructured":"X. Lin, C. Ding, J. Zeng, D. Tao, Gps-net: Graph property sensing network for scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3746\u20133753.","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"10.1016\/j.knosys.2026.116399_b26","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"8883","article-title":"Enhancing scene graph generation with hierarchical relationships and commonsense knowledge","author":"Jiang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116399_b27","doi-asserted-by":"crossref","unstructured":"K. Tang, H. Zhang, B. Wu, W. Luo, W. Liu, Learning to compose dynamic tree structures for visual contexts, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 6619\u20136628.","DOI":"10.1109\/CVPR.2019.00678"},{"key":"10.1016\/j.knosys.2026.116399_b28","doi-asserted-by":"crossref","unstructured":"J. Yang, J. Lu, S. Lee, D. Batra, D. Parikh, Graph r-cnn for scene graph generation, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 670\u2013685.","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"10.1016\/j.knosys.2026.116399_b29","doi-asserted-by":"crossref","unstructured":"Y. Li, W. Ouyang, B. Zhou, J. Shi, C. Zhang, X. Wang, Factorizable net: an efficient subgraph-based framework for scene graph generation, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 335\u2013351.","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"10.1016\/j.knosys.2026.116399_b30","doi-asserted-by":"crossref","unstructured":"D. Jung, S. Kim, W.H. Kim, M. Cho, Devil\u2019s on the edges: Selective quad attention for scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18664\u201318674.","DOI":"10.1109\/CVPR52729.2023.01790"},{"key":"10.1016\/j.knosys.2026.116399_b31","doi-asserted-by":"crossref","first-page":"21875","DOI":"10.52202\/079017-0688","article-title":"Depth anything v2","volume":"37","author":"Yang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116399_b32","series-title":"Multi-modality driven LoRA for adverse condition depth estimation","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116399_b33","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1109\/TMM.2021.3086618","article-title":"MFFENet: Multiscale feature fusion and enhancement network for RGB\u2013thermal urban road scene parsing","volume":"24","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"10.1016\/j.knosys.2026.116399_b34","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/TITS.2023.3306368","article-title":"EGFNet: Edge-aware guidance fusion network for RGB\u2013thermal urban scene parsing","volume":"25","author":"Dong","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"12","key":"10.1016\/j.knosys.2026.116399_b35","doi-asserted-by":"crossref","first-page":"7096","DOI":"10.1109\/TCSVT.2023.3275314","article-title":"MMSMCNet: Modal memory sharing and morphological complementary networks for RGB-T urban scene semantic segmentation","volume":"33","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.knosys.2026.116399_b36","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/TCSVT.2021.3077058","article-title":"ECFFNet: Effective and consistent feature fusion network for RGB-T salient object detection","volume":"32","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116399_b37","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/TIP.2023.3242775","article-title":"LSNet: Lightweight spatial boosting network for detecting salient objects in RGB-thermal images","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116399_b38","doi-asserted-by":"crossref","first-page":"3027","DOI":"10.1109\/TIP.2023.3275538","article-title":"WaveNet: Wavelet network with knowledge distillation for RGB-T salient object detection","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116399_b39","article-title":"IRFR-net: Interactive recursive feature-reshaping network for detecting salient objects in RGB-D images","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116399_b40","doi-asserted-by":"crossref","first-page":"2192","DOI":"10.1109\/TMM.2021.3077767","article-title":"CCAFNet: Crossflow and cross-scale adaptive fusion network for detecting salient objects in RGB-D images","volume":"24","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116399_b41","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"852","article-title":"Visual relationship detection with language priors","author":"Lu","year":"2016"},{"key":"10.1016\/j.knosys.2026.116399_b42","series-title":"Scene graph generation strategy with co-occurrence knowledge and learnable term frequency","author":"Kim","year":"2024"},{"key":"10.1016\/j.knosys.2026.116399_b43","doi-asserted-by":"crossref","unstructured":"J. Gu, H. Zhao, Z. Lin, S. Li, J. Cai, M. Ling, Scene graph generation with external knowledge and image reconstruction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 1969\u20131978.","DOI":"10.1109\/CVPR.2019.00207"},{"key":"10.1016\/j.knosys.2026.116399_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108300","article-title":"Atom correlation based graph propagation for scene graph generation","volume":"122","author":"Lin","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116399_b45","doi-asserted-by":"crossref","unstructured":"R. Yu, A. Li, V.I. Morariu, L.S. Davis, Visual relationship detection with internal and external linguistic knowledge distillation, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1974\u20131982.","DOI":"10.1109\/ICCV.2017.121"},{"key":"10.1016\/j.knosys.2026.116399_b46","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"606","article-title":"Bridging knowledge graphs to generate scene graphs","author":"Zareian","year":"2020"},{"issue":"11","key":"10.1016\/j.knosys.2026.116399_b47","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet: a lexical database for English","volume":"38","author":"Miller","year":"1995","journal-title":"Commun. ACM"},{"issue":"4","key":"10.1016\/j.knosys.2026.116399_b48","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d","article-title":"Conceptnet\u2014a practical commonsense reasoning tool-kit","volume":"22","author":"Liu","year":"2004","journal-title":"BT Technol. J."},{"key":"10.1016\/j.knosys.2026.116399_b49","doi-asserted-by":"crossref","unstructured":"H.-K. Yang, A.-C. Cheng, K.-W. Ho, T.-J. Fu, C.-Y. Lee, Visual relationship prediction via label clustering and incorporation of depth information, in: Proceedings of the European Conference on Computer Vision Workshops, 2018.","DOI":"10.1007\/978-3-030-11012-3_43"},{"key":"10.1016\/j.knosys.2026.116399_b50","doi-asserted-by":"crossref","unstructured":"C. Zheng, X. Lyu, L. Gao, B. Dai, J. Song, Prototype-based embedding network for scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22783\u201322792.","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"10.1016\/j.knosys.2026.116399_b51","doi-asserted-by":"crossref","unstructured":"K. Tang, Y. Niu, J. Huang, J. Shi, H. Zhang, Unbiased scene graph generation from biased training, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3716\u20133725.","DOI":"10.1109\/CVPR42600.2020.00377"},{"issue":"7","key":"10.1016\/j.knosys.2026.116399_b52","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","article-title":"The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale","volume":"128","author":"Kuznetsova","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116399_b53","doi-asserted-by":"crossref","unstructured":"S. Kundu, S.N. Aakur, IS-GGT: Iterative scene graph generation with generative transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 6292\u20136301.","DOI":"10.1109\/CVPR52729.2023.00609"},{"key":"10.1016\/j.knosys.2026.116399_b54","doi-asserted-by":"crossref","unstructured":"J. Li, Y. Wang, X. Guo, R. Yang, W. Li, Leveraging predicate and triplet learning for scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28369\u201328379.","DOI":"10.1109\/CVPR52733.2024.02680"},{"issue":"12","key":"10.1016\/j.knosys.2026.116399_b55","doi-asserted-by":"crossref","first-page":"8018","DOI":"10.1109\/TPAMI.2024.3402143","article-title":"Repsgg: Novel representations of entities and relationships for scene graph generation","volume":"46","author":"Liu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116399_b56","doi-asserted-by":"crossref","unstructured":"S. Shit, R. Koner, B. Wittmann, J. Paetzold, I. Ezhov, H. Li, J. Pan, S. Sharifzadeh, G. Kaissis, V. Tresp, et al., Relationformer: A unified framework for image-to-graph generation, in: Proceedings of the European Conference on Computer Vision, 2022, pp. 422\u2013439.","DOI":"10.1007\/978-3-031-19836-6_24"},{"key":"10.1016\/j.knosys.2026.116399_b57","doi-asserted-by":"crossref","unstructured":"R. Li, S. Zhang, D. Lin, K. Chen, X. He, From pixels to graphs: Open-vocabulary scene graph generation with vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28076\u201328086.","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"10.1016\/j.knosys.2026.116399_b58","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.knosys.2026.116399_b59","doi-asserted-by":"crossref","unstructured":"J. Zhang, K.J. Shih, A. Elgammal, A. Tao, B. Catanzaro, Graphical contrastive losses for scene graph parsing, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11535\u201311543.","DOI":"10.1109\/CVPR.2019.01180"},{"key":"10.1016\/j.knosys.2026.116399_b60","doi-asserted-by":"crossref","unstructured":"X. Lin, C. Ding, J. Zhang, Y. Zhan, D. Tao, Ru-net: Regularized unrolling network for scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19457\u201319466.","DOI":"10.1109\/CVPR52688.2022.01885"},{"key":"10.1016\/j.knosys.2026.116399_b61","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126011251?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126011251?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:10:03Z","timestamp":1783635003000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126011251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":61,"alternative-id":["S0950705126011251"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116399","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DATR: Depth-aware transformer for hierarchical and fine-grained scene graph generation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116399","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116399"}}