{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T06:01:39Z","timestamp":1780293699875,"version":"3.54.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62522216"],"award-info":[{"award-number":["62522216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402408"],"award-info":[{"award-number":["62402408"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017649","name":"Hong Kong Government","doi-asserted-by":"publisher","award":["General Research Fund (16219025)"],"award-info":[{"award-number":["General Research Fund (16219025)"]}],"id":[{"id":"10.13039\/501100017649","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017649","name":"Hong Kong Government","doi-asserted-by":"publisher","award":["Early Career Scheme (26208924)"],"award-info":[{"award-number":["Early Career Scheme (26208924)"]}],"id":[{"id":"10.13039\/501100017649","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission - Hong Kong","doi-asserted-by":"publisher","award":["ACCESS \u2013 AI Chip Center for Emerging Smart System, InnoHK"],"award-info":[{"award-number":["ACCESS \u2013 AI Chip Center for Emerging Smart System, InnoHK"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","award":["Tencent-WeChat Rhino-Bird Focused Research Program"],"award-info":[{"award-number":["Tencent-WeChat Rhino-Bird Focused Research Program"]}],"id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Scene Graph Generation (SGG) aims to detect all the visual relation triplets &lt;, , &gt; in a given image. With the emergence of various advanced techniques for better utilizing both the intrinsic and extrinsic information in each relation triplet, SGG has achieved great progress over the recent years. However, due to the ubiquitous long-tailed predicate distributions, today\u2019s SGG models are still easily biased to the head predicates. Currently, the most prevalent debiasing solutions for SGG are re-balancing methods,\n                    <jats:italic>e<\/jats:italic>\n                    .\n                    <jats:italic>g<\/jats:italic>\n                    ., changing the distributions of original training samples. In this paper, we argue that all existing re-balancing strategies fail to increase the diversity of the relation triplet features of each predicate, which is critical for robust SGG. To this end, we propose a novel\n                    <jats:bold>M<\/jats:bold>\n                    ulti-level\n                    <jats:bold>C<\/jats:bold>\n                    ompositional\n                    <jats:bold>F<\/jats:bold>\n                    eature\n                    <jats:bold>A<\/jats:bold>\n                    ugmentation (\n                    <jats:bold>MCFA<\/jats:bold>\n                    ) strategy, which aims to mitigate the bias issue from the perspective of increasing the diversity of triplet features. Specifically, we enhance relationship diversity on not only\n                    <jats:italic>feature-level<\/jats:italic>\n                    ,\n                    <jats:italic>i<\/jats:italic>\n                    .\n                    <jats:italic>e<\/jats:italic>\n                    ., replacing the intrinsic or extrinsic visual features of triplets with other correlated samples to create novel feature compositions for tail predicates, but also\n                    <jats:italic>image-level<\/jats:italic>\n                    ,\n                    <jats:italic>i<\/jats:italic>\n                    .\n                    <jats:italic>e<\/jats:italic>\n                    ., manipulating the image to generate brand new visual appearance for triplets. Due to its model-agnostic nature, MCFA can be seamlessly incorporated into various SGG frameworks. Extensive ablations have shown that MCFA achieves a new state-of-the-art performance on the trade-off between different metrics.\n                  <\/jats:p>","DOI":"10.1007\/s11263-026-02855-7","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T05:14:50Z","timestamp":1780290890000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-level Compositional Feature Augmentation for Unbiased Scene Graph Generation"],"prefix":"10.1007","volume":"134","author":[{"given":"Lin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingchen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"2855_CR1","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 (pp. 213\u2013229). ECCV.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2855_CR2","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations (pp. 1597\u20131607). ICML."},{"key":"2855_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Li, L., Wang, W., Quan, R., & Yang, Y. (2024a). General and task-oriented video segmentation. In: European Conference on Computer Vision, Springer, pp 72\u201392.","DOI":"10.1007\/978-3-031-72667-5_5"},{"key":"2855_CR4","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., & Lin, L. (2019b). Knowledge-embedded routing network for scene graph generation. In: CVPR, pp 6163\u20136171.","DOI":"10.1109\/CVPR.2019.00632"},{"key":"2855_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., Zhan, Y., Yu, B., Liu, L., Luo, Y., & Du, B. (2022). Resistance training using prior bias: toward unbiased scene graph generation (pp. 212\u2013220). AAAI.","DOI":"10.1609\/aaai.v36i1.19896"},{"key":"2855_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., He, X., Pu, S., & Chang, S. F. (2019a). Counterfactual critic multi-agent training for scene graph generation. In: ICCV, pp 4613\u20134623.","DOI":"10.1109\/ICCV.2019.00471"},{"key":"2855_CR7","doi-asserted-by":"crossref","unstructured":"Chen, M., Zheng, Z., & Yang, Y. (2024b). Transferring to real-world layouts: A depth-aware framework for scene adaptation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp 399\u2013408.","DOI":"10.1145\/3664647.3681041"},{"key":"2855_CR8","doi-asserted-by":"crossref","unstructured":"Chen, M., Zheng, Z., Yang, Y., & Chua, T. S. (2023). Pipa: Pixel-and patch-wise self-supervised learning for domain adaptative semantic segmentation. Proceedings of the 31st ACM International Conference on Multimedia (pp. 1905\u20131914)","DOI":"10.1145\/3581783.3611708"},{"key":"2855_CR9","doi-asserted-by":"crossref","unstructured":"Chiou, M. J., Ding, H., Yan, H., Wang, C., Zimmermann, R., & Feng, J. (2021). Recovering the unbiased scene graphs from the biased ones. ACM MM.","DOI":"10.1145\/3474085.3475297"},{"key":"2855_CR10","doi-asserted-by":"crossref","unstructured":"Chu, P., Bian, X., Liu, S., L., & H. (2020). Feature space augmentation for long-tailed data (pp. 694\u2013710). ECCV.","DOI":"10.1007\/978-3-030-58526-6_41"},{"key":"2855_CR11","doi-asserted-by":"crossref","unstructured":"Deng, Y., Li, Y., Zhang, Y., Xiang, X., Wang, J., Chen, J., & Ma, J. (2022). Hierarchical memory learning for fine-grained scene graph generation. ECCV.","DOI":"10.1007\/978-3-031-19812-0_16"},{"key":"2855_CR12","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 (pp. 15404\u201315413). ICCV.","DOI":"10.1109\/ICCV48922.2021.01512"},{"key":"2855_CR13","unstructured":"DeVries, T., Taylor, & G. W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv."},{"key":"2855_CR14","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 (pp. 19427\u201319436). CVPR.","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"2855_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Y., Gao, L., Wang, X., Hu, Y., Xu, X., Lu, X., Shen, H. T., & Song, J. (2021). From general to specific: Informative scene graph generation via balance adjustment (pp. 16383\u201316392). ICCV.","DOI":"10.1109\/ICCV48922.2021.01607"},{"key":"2855_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., & Girshick, R. (2019). Lvis: A dataset for large vocabulary instance segmentation (pp. 5356\u20135364). CVPR.","DOI":"10.1109\/CVPR.2019.00550"},{"key":"2855_CR17","doi-asserted-by":"crossref","unstructured":"Hou, Z., Peng, X., Qiao, Y., & Tao, D. (2020). Visual compositional learning for human-object interaction detection (pp. 584\u2013600). ECCV.","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"2855_CR18","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yu, B., Qiao, Y., Peng, X., & Tao, D. (2021). Detecting human-object interaction via fabricated compositional learning (pp. 14646\u201314655). CVPR.","DOI":"10.1109\/CVPR46437.2021.01441"},{"key":"2855_CR19","doi-asserted-by":"crossref","unstructured":"Hudson, D. A., & Manning, C. D. (2019). Gqa: A new dataset for real-world visual reasoning and compositional question answering (pp. 6700\u20136709). CVPR.","DOI":"10.1109\/CVPR.2019.00686"},{"key":"2855_CR20","doi-asserted-by":"crossref","unstructured":"Im, J., Nam, J., Park, N., Lee, H., & Park, S. (2024). Egtr: Extracting graph from transformer for scene graph generation. In: CVPR, pp 24229\u201324238.","DOI":"10.1109\/CVPR52733.2024.02287"},{"key":"2855_CR21","doi-asserted-by":"crossref","unstructured":"Jeon, J., Kim, K., Yoon, K., & Park, C. (2024). Semantic diversity-aware prototype-based learning for unbiased scene graph generation. In: ECCV, Springer, pp 379\u2013395.","DOI":"10.1007\/978-3-031-73113-6_22"},{"key":"2855_CR22","doi-asserted-by":"crossref","unstructured":"Jin, T., Guo, F., Meng, Q., Zhu, S., Xi, X., Wang, W., Mu, Z., & Song, W. (2023). Fast contextual scene graph generation with unbiased context augmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 6302\u20136311)","DOI":"10.1109\/CVPR52729.2023.00610"},{"key":"2855_CR23","doi-asserted-by":"crossref","unstructured":"Kato, K., Li, Y., & Gupta, A. (2018). Compositional learning for human object interaction (pp. 234\u2013251). ECCV.","DOI":"10.1007\/978-3-030-01264-9_15"},{"key":"2855_CR24","unstructured":"Kim, K., Yoon, K., In, Y., Moon, J., Kim, D., & Park, C. (2024). Adaptive self-training framework for fine-grained scene graph generation. In: ICLR."},{"key":"2855_CR25","doi-asserted-by":"crossref","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L. J., & Shamma, D. A. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. IJCV","DOI":"10.1007\/s11263-016-0981-7"},{"key":"2855_CR26","unstructured":"Labs, B. F., Batifol, S., Blattmann, A., Boesel, F., Consul, S., Diagne, C., Dockhorn, T., English, J., English, Z., Esser, P., Kulal, S., Lacey, K., Levi, Y., Li, C., Lorenz, D., M\u00fcller, J., Podell, D., Rombach, R., Saini, H., Sauer, A., Smith, L. (2025). Flux. 1 kontext: Flow matching for in-context image generation and editing in latent space. arXiv:2506.15742."},{"key":"2855_CR27","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, L., Huang, Y., Zhang, Z., Zhang, S., & Xiao, J. (2022a). The devil is in the labels: Noisy label correction for robust scene graph generation. In: CVPR, pp 18869\u201318878.","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"2855_CR28","unstructured":"Li, X., Chen, L., Shao, J., Xiao, S., Zhang, S., & Xiao, J. (2022d). Rethinking the evaluation of unbiased scene graph generation. In: BMVC."},{"key":"2855_CR29","unstructured":"Li, L., Chen, L., Shi, H., Zhang, H., Yang, Y., Liu, W., & Xiao, J. (2022b). Nicest: Noisy label correction and training for robust scene graph generation. arXiv."},{"key":"2855_CR30","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, G., Xiao, J., Yang, Y., Wang, C., & Chen, L. (2023a) Compositional feature augmentation for unbiased scene graph generation. In: ICCV, pp 21685\u201321695.","DOI":"10.1109\/ICCV51070.2023.01982"},{"key":"2855_CR31","doi-asserted-by":"crossref","unstructured":"Li, P., Li, D., Li, W., Gong, S., Fu, Y., & Hospedales, T. M. (2021a) A simple feature augmentation for domain generalization. In: ICCV, pp 8886\u20138895.","DOI":"10.1109\/ICCV48922.2021.00876"},{"key":"2855_CR32","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., & Lee, Y. J. (2023b). Gligen: Open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 22511\u201322521.","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"2855_CR33","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, H., Bai, Q., Zhao, G., Jiang, N., & Yuan, X. (2022c). Ppdl: Predicate probability distribution based loss for unbiased scene graph generation. In: CVPR, pp 19447\u201319456.","DOI":"10.1109\/CVPR52688.2022.01884"},{"key":"2855_CR34","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., Wan, B., & He, X. (2021b). Bipartite graph network with adaptive message passing for unbiased scene graph generation. In: CVPR, pp 11109\u201311119.","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"2855_CR35","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zhang, J., Zhan, Y., & Tao, D. (2022). Ru-net: Regularized unrolling network for scene graph generation (pp. 19457\u201319466). CVPR.","DOI":"10.1109\/CVPR52688.2022.01885"},{"key":"2855_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection (pp. 2117\u20132125). CVPR.","DOI":"10.1109\/CVPR.2017.106"},{"key":"2855_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu., & S. X. (2019). Large-scale long-tailed recognition in an open world (pp. 2537\u20132546). CVPR.","DOI":"10.1109\/CVPR.2019.00264"},{"key":"2855_CR38","doi-asserted-by":"crossref","unstructured":"Liu, L., Sun, S., Zhi, S., Shi, F., Liu, Z., Heikkil\u00e4, J., & Liu, Y. (2025). A causal adjustment module for debiasing scene graph generation.","DOI":"10.1109\/TPAMI.2025.3537283"},{"key":"2855_CR39","doi-asserted-by":"crossref","unstructured":"Lu, C., Krishna, R., Bernstein, M., & Fei-Fei, L. (2016). Visual relationship detection with language priors (pp. 852\u2013869). ECCV.","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"2855_CR40","doi-asserted-by":"crossref","unstructured":"Lu, Y., Rai, H., Chang, J., Knyazev, B., Yu, G., Shekhar, S., Taylor, G. W., & Volkovs, M. (2021). Context-aware scene graph generation with seq2seq transformers (pp. 15931\u201315941). ICCV.","DOI":"10.1109\/ICCV48922.2021.01563"},{"key":"2855_CR41","doi-asserted-by":"crossref","unstructured":"Lyu, X., Gao, L., Guo, Y., Zhao, Z., Huang, H., Shen, H. T., & Song, J. (2022). Fine-grained predicates learning for scene graph generation. CVPR.","DOI":"10.1109\/CVPR52688.2022.01886"},{"key":"2855_CR42","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: Global vectors for word representation. EMNLP, 1532\u20131543.","DOI":"10.3115\/v1\/D14-1162"},{"key":"2855_CR43","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., & Clark, J. (2021). Learning transferable visual models from natural language supervision. International conference on machine learning (pp. 8748\u20138763). PmLR"},{"key":"2855_CR44","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks (pp. 91\u201399). NeurIPS."},{"key":"2855_CR45","doi-asserted-by":"crossref","unstructured":"Sudhakaran, G., Dhami, D. S., Kersting, K., R., & S. (2023). Vision relation transformer for unbiased scene graph generation. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 21882\u201321893)","DOI":"10.1109\/ICCV51070.2023.02000"},{"issue":"10","key":"2855_CR46","doi-asserted-by":"publisher","first-page":"12562","DOI":"10.1109\/TPAMI.2023.3285009","volume":"45","author":"S Sun","year":"2023","unstructured":"Sun, S., Zhi, S., Liao, Q., Heikkil\u00e4, J., & Liu, L. (2023). Unbiased scene graph generation via two-stage causal modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10), 12562\u201312580.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2855_CR47","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., & Zhang, H. (2020). Unbiased scene graph generation from biased training (pp. 3716\u20133725). CVPR.","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"2855_CR48","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 (pp. 6619\u20136628). CVPR.","DOI":"10.1109\/CVPR.2019.00678"},{"key":"2855_CR49","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser. \u0141., & Polosukhin, I. (2017). Attention is all you need."},{"key":"2855_CR50","doi-asserted-by":"crossref","unstructured":"Vigneswaran, R., Law, M. T., Balasubramanian, V. N., & Tapaswi, M. (2021). Feature generation for long-tail classification. ICVGIP, 1\u20139.","DOI":"10.1145\/3490035.3490300"},{"key":"2855_CR51","doi-asserted-by":"crossref","unstructured":"Wei, M., Yuan, C., Yue, X., & Zhong, K. (2020). Hose-net: Higher order structure embedded network for scene graph generation. ACM MM (pp. 1846\u20131854)","DOI":"10.1145\/3394171.3413575"},{"key":"2855_CR52","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C. B., & Fei-Fei, L. (2017). Scene graph generation by iterative message passing (pp. 5410\u20135419). CVPR.","DOI":"10.1109\/CVPR.2017.330"},{"key":"2855_CR53","doi-asserted-by":"crossref","unstructured":"Yan, S., Shen, C., Jin, Z., Huang, J., Jiang, R., Chen, Y., & Hua, X. S. (2020). Pcpl: Predicate-correlation perception learning for unbiased scene graph generation (pp. 265\u2013273). ACM MM.","DOI":"10.1145\/3394171.3413722"},{"key":"2855_CR54","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., et al. (2025). Qwen3 technical report. arXiv:2505.09388."},{"key":"2855_CR55","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Hu, Y., & Wu, Q. (2021). Cogtree: Cognition tree loss for unbiased scene graph generation. IJCAI.","DOI":"10.24963\/ijcai.2021\/176"},{"key":"2855_CR56","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., & Choi, Y. (2018). Neural motifs: Scene graph parsing with global context (pp. 5831\u20135840). CVPR.","DOI":"10.1109\/CVPR.2018.00611"},{"key":"2855_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, R., Hao, Y., Zhang, F., An, G., Song, B., & Wu, D. O. (2025). Human-inspired scene understanding: A grounded cognition method for unbiased scene graph generation.","DOI":"10.1109\/TPAMI.2025.3635152"},{"key":"2855_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S. F., & Chua, T. S. (2017). Visual translation embedding network for visual relation detection (pp. 5532\u20135540). CVPR.","DOI":"10.1109\/CVPR.2017.331"},{"key":"2855_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, A., Yao, Y., Chen, Q., Ji, W., Liu, Z., Sun, M., & Chua, T. S. (2022). Fine-grained scene graph generation with data transfer. ECCV.","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"2855_CR60","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Y., & Y. (2020). Random erasing data augmentation (pp. 13001\u201313008). AAAI.","DOI":"10.1609\/aaai.v34i07.7000"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02855-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02855-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02855-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T05:15:00Z","timestamp":1780290900000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02855-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":60,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2855"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02855-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"18 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"301"}}