{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:29:03Z","timestamp":1773329343603,"version":"3.50.1"},"reference-count":97,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/xxxxxxx","name":"xxxxxxx","doi-asserted-by":"publisher","award":["10117"],"award-info":[{"award-number":["10117"]}],"id":[{"id":"10.13039\/xxxxxxx","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":[[2025,7]]},"DOI":"10.1007\/s11263-025-02365-y","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T20:44:39Z","timestamp":1740429879000},"page":"4196-4219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Informative Scene Graph Generation via Debiasing"],"prefix":"10.1007","volume":"133","author":[{"given":"Lianli","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyu","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Fang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,24]]},"reference":[{"key":"2365_CR1","first-page":"382","volume":"9909","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., & Gould, S. (2016). SPICE: semantic propositional image caption evaluation. European conference on computer vision, 9909, 382\u2013398.","journal-title":"European conference on computer vision"},{"key":"2365_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., & Zhang, L. (2018). Bottom-up and top-down attention for image captioning and visual question answering. IEEE conference on computer vision and pattern recognition (pp. 6077\u20136086).","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2365_CR3","doi-asserted-by":"crossref","unstructured":"Biswas, B.A., & Ji, Q. (2023). Probabilistic debi-asing of scene graphs. IEEE conference on computer vision and pattern recognition (pp. 10429\u201310438).","DOI":"10.1109\/CVPR52729.2023.01005"},{"key":"2365_CR4","unstructured":"Breese, J.S., Heckerman, D., & Kadie, C. (2013). Empirical analysis of predictive algorithms for collaborative filtering. CoRR."},{"key":"2365_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., He, X., Pu, S., & Chang, S. (2019). Counterfactual critic multi-agent training for scene graph gen-eration. IEEE international conference on computer vision (pp. 4612\u20134622).","DOI":"10.1109\/ICCV.2019.00471"},{"key":"2365_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., & Lin, L. (2019). Knowledge-embedded routing network for scene graph generation. IEEE conference on computer vision and pattern recognition (pp. 6163\u20136171).","DOI":"10.1109\/CVPR.2019.00632"},{"key":"2365_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bai, Y., Zhang, W., & Mei, T. (2019). Destruction and construction learning for fine-grained image recognition. IEEE con-ference on computer vision and pattern recognition (pp. 5157\u20135166).","DOI":"10.1109\/CVPR.2019.00530"},{"key":"2365_CR8","doi-asserted-by":"crossref","unstructured":"Cohn-Gordon, R., Goodman, N.D., & Potts, C. (2018). Pragmatically informative image captioning with character-level inference. (pp. 439\u2013443).","DOI":"10.18653\/v1\/N18-2070"},{"issue":"9","key":"2365_CR9","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1109\/TPAMI.2023.3268066","volume":"45","author":"Y Cong","year":"2023","unstructured":"Cong, Y., Yang, M. Y., & Rosenhahn, B. (2023). Reltr: Relation transformer for scene graph generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9), 11169\u201311183.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2365_CR10","doi-asserted-by":"crossref","unstructured":"Denkowski, M.J., & Lavie, A. (2014). Meteor universal: Language specific translation evalua-tion for any target language. Acl workshop (pp. 376\u2013380).","DOI":"10.3115\/v1\/W14-3348"},{"key":"2365_CR11","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. Iccv.","DOI":"10.1109\/ICCV48922.2021.01512"},{"key":"2365_CR12","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. Cvpr.","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"2365_CR13","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., & Huang, W. (2021). Exploring classification equilibrium in long-tailed object detection. Iccv.","DOI":"10.1109\/ICCV48922.2021.00340"},{"key":"2365_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.B. (2015). Fast R-CNN. IEEE international conference on computer vision (pp. 1440\u20131448).","DOI":"10.1109\/ICCV.2015.169"},{"issue":"1","key":"2365_CR15","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"RB Girshick","year":"2016","unstructured":"Girshick, R. B., Donahue, J., Darrell, T., & Malik, J. (2016). Region-based convolutional net-works for accurate object detection and seg-mentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(1), 142\u2013158.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2365_CR16","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., & Ling, M. (2019). Scene graph generation with external knowledge and image reconstruction. IEEE conference on computer vision and pattern recognition (pp. 1969\u20131978).","DOI":"10.1109\/CVPR.2019.00207"},{"key":"2365_CR17","doi-asserted-by":"publisher","first-page":"6730","DOI":"10.1109\/TIP.2021.3097180","volume":"30","author":"W Guo","year":"2021","unstructured":"Guo, W., Zhang, Y., Yang, J., & Yuan, X. (2021). Re-attention for visual question answering. IEEE Transactions on Image Processing, 30, 6730\u20136743.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2365_CR18","doi-asserted-by":"crossref","unstructured":"Guo, Y., Gao, L., Wang, X., Hu, Y., Xu, X., & Lu, X., Song, J. (2021). From general to specific: Informative scene graph generation via balance adjustment. IEEE international conference on computer vision (p. 16383-16392).","DOI":"10.1109\/ICCV48922.2021.01607"},{"key":"2365_CR19","doi-asserted-by":"crossref","unstructured":"Guo, Y., Song, J., Gao, L., & Shen, H.T. (2020). One-shot scene graph generation. Acm international conference on multimedia (pp. 3090\u20133098).","DOI":"10.1145\/3394171.3414025"},{"key":"2365_CR20","doi-asserted-by":"crossref","unstructured":"Gupta, A., Doll\u00e1r, P., & Girshick, R.B. (2019). LVIS: A dataset for large vocabulary instance segmentation. Cvpr.","DOI":"10.1109\/CVPR.2019.00550"},{"key":"2365_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2365_CR22","unstructured":"He, T., Gao, L., Song, J., Cai, J., & Li, Y. (2021). Semantic compositional learning for low-shot scene graph generation. CoRR."},{"key":"2365_CR23","doi-asserted-by":"crossref","unstructured":"He, T., Gao, L., Song, J., & Li, Y. (2022). Towards open-vocabulary scene graph generation with prompt-based finetuning. European conference on computer vision (pp. 56\u201373).","DOI":"10.1007\/978-3-031-19815-1_4"},{"key":"2365_CR24","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/TIP.2022.3224872","volume":"32","author":"T He","year":"2023","unstructured":"He, T., Gao, L., Song, J., & Li, Y. (2023). State-aware compositional learning toward unbiased training for scene graph generation. IEEE Transactions on Image Processing, 32, 43\u201356.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2365_CR25","unstructured":"Herzig, R., Raboh, M., Chechik, G., Berant, J., & Globerson, A. (2018). Mapping images to scene graphs with permutation-invariant structured prediction. Neural information processing systems (pp. 7211\u20137221)."},{"key":"2365_CR26","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. IEEE conference on computer vision and pattern recognition (pp. 6700\u20136709).","DOI":"10.1109\/CVPR.2019.00686"},{"issue":"11","key":"2365_CR27","doi-asserted-by":"publisher","first-page":"3820","DOI":"10.1109\/TPAMI.2020.2992222","volume":"43","author":"Z-S Hung","year":"2020","unstructured":"Hung, Z.-S., Mallya, A., & Lazebnik, S. (2020). Contextual translation embedding for visual relationship detection and scene graph gen-eration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(11), 3820\u20133832.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2365_CR28","doi-asserted-by":"crossref","unstructured":"Johnson, J., Krishna, R., Stark, M., Li, L., Shamma, D.A., Bernstein, M.S., & Li, F. (2015). Image retrieval using scene graphs. IEEE conference on computer vision and pattern recognition (pp. 3668\u20133678).","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"2365_CR29","doi-asserted-by":"crossref","unstructured":"Kan, X., Cui, H., & Yang, C. (2021). Zero-shot scene graph relation prediction through common-sense knowledge integration. N. Oliver, F. P\u00b4erez-Cruz, S. Kramer, J. Read, & J.A. Lozano (Eds.), Pkdd.","DOI":"10.1007\/978-3-030-86520-7_29"},{"key":"2365_CR30","unstructured":"Kan, X., Cui, H., & Yang, C. (2022). Zero-shot predicate prediction for scene graph parsing. Y. Li, X. Yang, X. Huang, Z. Ma, & C. Xu (Eds.), Tmm."},{"key":"2365_CR31","unstructured":"Kim, J., Jun, J., & Zhang, B. (2018). Bilinear attention networks. Neural information processing systems (pp. 1571\u20131581)."},{"key":"2365_CR32","doi-asserted-by":"crossref","unstructured":"Knyazev, B., de Vries, H., Cangea, C., Taylor, G.W., Courville, A.C., & Belilovsky, E. (2021). Generative compositional augmentations for scene graph prediction. Iccv.","DOI":"10.1109\/ICCV48922.2021.01553"},{"issue":"1","key":"2365_CR33","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., & Fei-Fei, L. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision, 123(1), 32\u201373.","journal-title":"International Journal of Computer Vision"},{"key":"2365_CR34","doi-asserted-by":"crossref","unstructured":"Lam, M., Mahasseni, B., & Todorovic, S. (2017). Fine-grained recognition as hsnet search for informative image parts. IEEE conference on computer vision and pattern recognition (pp. 6497\u20136506).","DOI":"10.1109\/CVPR.2017.688"},{"key":"2365_CR35","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, L., Huang, Y., Zhang, Z., Zhang, S., & Xiao, J. (2022). The devil is in the labels: Noisy label correction for robust scene graph generation. Cvpr.","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"2365_CR36","doi-asserted-by":"crossref","unstructured":"Li, R., et al. (2021). Bipartite graph network with adaptive message passing for unbiased scene graph generation. Cvpr.","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"2365_CR37","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., & He, X. (2022). SGTR: end-to-end scene graph generation with trans-former. Cvpr.","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"2365_CR38","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, H., Bai, Q., Zhao, G., Jiang, N., & Yuan, X. (2022). Ppdl: Predicate probability distribution based loss for unbiased scene graph generation. Cvpr.","DOI":"10.1109\/CVPR52688.2022.01884"},{"key":"2365_CR39","doi-asserted-by":"crossref","unstructured":"Li, X., Song, J., Gao, L., Liu, X., Huang, W., He, X., & Gan, C. (2019). Beyond rnns: Positional self-attention with co-attention for video question answering. Association for the advancement of artificial intelligence (pp. 8658\u20138665).","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"2365_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Shi, J., Zhang, C., & Wang, X. (2018). Factorizable net: An effi-cient subgraph-based framework for scene graph generation. European conference on computer vision (Vol. 11205, pp. 346\u2013363).","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"2365_CR41","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, T., Kang, B., Tang, S., Wang, C., Li, J., & Feng, J. (2020). Overcoming classifier imbalance for long-tail object detection with balanced group softmax. Cvpr.","DOI":"10.1109\/CVPR42600.2020.01100"},{"key":"2365_CR42","doi-asserted-by":"crossref","unstructured":"Liang, C., Wu, Z., Huang, W., & Giles, C.L. (2015). Measuring prerequisite relations among concepts. (pp. 1668\u20131674).","DOI":"10.18653\/v1\/D15-1193"},{"key":"2365_CR43","doi-asserted-by":"crossref","unstructured":"Liang, Y., Bai, Y., Zhang, W., Qian, X., Zhu, L., & Mei, T. (2019). Vrr-vg: Refocusing visually-relevant relationships. IEEE international conference on computer vision (pp. 10402\u2013 10411).","DOI":"10.1109\/ICCV.2019.01050"},{"key":"2365_CR44","unstructured":"Lin, D. (1998). An information-theoretic definition of similarity. (pp. 296\u2013304)"},{"key":"2365_CR45","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., & Belongie, S.J. (2017). Feature pyra-mid networks for object detection. IEEE conference on computer vision and pattern recognition (pp. 936\u2013944).","DOI":"10.1109\/CVPR.2017.106"},{"key":"2365_CR46","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S.J., Hays, J., Per-ona, P., Ramanan, D., & . . . Zitnick, C.L. (2014). Microsoft COCO: common objects in context. D.J. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Eds.), European conference on computer vision (Vol. 8693, pp. 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2365_CR47","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., & Tao, D. (2020). Gps-net: Graph property sensing network for scene graph generation. IEEE conference on computer vision and pattern recognition (pp. 3743\u20133752).","DOI":"10.1109\/CVPR42600.2020.00380"},{"issue":"12","key":"2365_CR48","doi-asserted-by":"publisher","first-page":"8018","DOI":"10.1109\/TPAMI.2024.3402143","volume":"46","author":"H Liu","year":"2024","unstructured":"Liu, H., & Bhanu, B. (2024). Repsgg: Novel representations of entities and relationships for scene graph generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 8018\u20138035.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2365_CR49","doi-asserted-by":"crossref","unstructured":"Lu, C., Krishna, R., Bernstein, M.S., & Li, F. (2016). Visual relationship detection with language priors. European conference on computer vision (Vol. 9905, pp. 852\u2013869).","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"2365_CR50","doi-asserted-by":"crossref","unstructured":"Luo, R., Price, B.L., Cohen, S., & Shakhnarovich, G. (2018). Discriminability objective for training descriptive captions. IEEE conference on computer vision and pattern recognition (pp. 6964\u20136974).","DOI":"10.1109\/CVPR.2018.00728"},{"key":"2365_CR51","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":"2365_CR52","doi-asserted-by":"crossref","unstructured":"Lyu, X., Gao, L., Zeng, P., Shen, H.T., & Song, J. (2022). Adaptive fine-grained predicates learning for scene graph generation. TPAMI.","DOI":"10.1109\/CVPR52688.2022.01886"},{"key":"2365_CR53","doi-asserted-by":"crossref","unstructured":"McMahon, D. (2007). Quantum computing explained.","DOI":"10.1002\/9780470181386"},{"key":"2365_CR54","doi-asserted-by":"crossref","unstructured":"Mi, L., & Chen, Z. (2020). Hierarchical graph attention network for visual relationship detection. IEEE conference on computer vision and pattern recognition (pp. 13883\u2013 13892).","DOI":"10.1109\/CVPR42600.2020.01390"},{"key":"2365_CR55","unstructured":"Newell, A., & Deng, J. (2017). Pixels to graphs by associative embedding. Neural information processing systems (pp. 2171\u20132180)."},{"key":"2365_CR56","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W. (2002). Bleu: A method for automatic evalu-ation of machine translation. (pp. 311\u2013318)","DOI":"10.3115\/1073083.1073135"},{"key":"2365_CR57","unstructured":"Pedersen, T. (2010). Information content mea-sures of semantic similarity perform better without sense-tagged text. (pp. 329\u2013332)."},{"key":"2365_CR58","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C.D. (2014). Glove: Global vectors for word representation. (pp. 1532\u20131543).","DOI":"10.3115\/v1\/D14-1162"},{"key":"2365_CR59","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. IEEE conference on computer vision and pattern recognition (pp. 779\u2013788).","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"2365_CR60","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R. B., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2365_CR61","unstructured":"Resnik, P. (1995). Using information content to evaluate semantic similarity in a taxonomy. International joint conference on artificial intelligence (pp. 448\u2013453)."},{"key":"2365_CR62","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1613\/jair.514","volume":"11","author":"P Resnik","year":"1999","unstructured":"Resnik, P. (1999). Semantic similarity in a tax-onomy: An information-based measure and its application to problems of ambiguity in natural language. Journal of Artificial Intelligence Research, 11, 95\u2013130.","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"5","key":"2365_CR63","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1108\/00220410410560582","volume":"60","author":"S Robertson","year":"2004","unstructured":"Robertson, S. (2004). Understanding inverse document frequency: on theoretical arguments for IDF. Journal of documentation, 60(5), 503\u2013520.","journal-title":"Journal of documentation"},{"key":"2365_CR64","unstructured":"Ross, S. (2014). A first course in probability."},{"issue":"5","key":"2365_CR65","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., & Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information Processing and Management, 24(5), 513\u2013523.","journal-title":"Information Processing and Management"},{"key":"2365_CR66","doi-asserted-by":"crossref","unstructured":"Schuster, S., Krishna, R., Chang, A.X., Fei-Fei, L., & Manning, C.D. (2015). Generating semantically precise scene graphs from textual descriptions for improved image retrieval. Emnlp workshop (pp. 70\u201380).","DOI":"10.18653\/v1\/W15-2812"},{"key":"2365_CR67","unstructured":"Seco, N., Veale, T., & Hayes, J. (2004). An intrinsic information content metric for semantic similarity in wordnet. Ecai (pp. 1089\u20131090)."},{"issue":"12","key":"2365_CR68","doi-asserted-by":"publisher","first-page":"5610","DOI":"10.1109\/TIP.2016.2612883","volume":"25","author":"F Shen","year":"2016","unstructured":"Shen, F., Zhou, X., Yang, Y., Song, J., Shen, H. T., & Tao, D. (2016). A fast optimization method for general binary code learning. IEEE Transactions on Image Processing, 25(12), 5610\u20135621.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"7","key":"2365_CR69","doi-asserted-by":"publisher","first-page":"3210","DOI":"10.1109\/TIP.2018.2814344","volume":"27","author":"J Song","year":"2018","unstructured":"Song, J., Zhang, H., Li, X., Gao, L., Wang, M., & Hong, R. (2018). Self-supervised video hashing with hierarchical binary auto-encoder. IEEE Transactions on Image Processing, 27(7), 3210\u20133221.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2365_CR70","doi-asserted-by":"crossref","unstructured":"Suhail, M., Mittal, A., Siddiquie, B., Broaddus, C., Eledath, J., Medioni, G.G., & Sigal, L. (2021). Energy-based learning for scene graph generation. Cvpr.","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"2365_CR71","doi-asserted-by":"crossref","unstructured":"Tan, J., Wang, C., Li, B., Li, Q., Ouyang, W., Yin, C., & Yan, J. (2020). Equalization loss for long-tailed object recognition. Cvpr.","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"2365_CR72","unstructured":"Tang, K. (2020). A scene graph generation codebase in pytorch. (https:\/\/github.com\/KaihuaTang\/Scene-Graph-Benchmark.pytorch)"},{"key":"2365_CR73","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., & Zhang, H. (2020). Unbiased scene graph generation from biased training. IEEE conference on computer vision and pattern recognition (pp. 3713\u20133722).","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"2365_CR74","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. IEEE conference on computer vision and pattern recognition (pp. 6619\u20136628).","DOI":"10.1109\/CVPR.2019.00678"},{"key":"2365_CR75","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., & van den Hengel, A. (2017). Graph-structured representations for visual question answering. IEEE conference on computer vision and pattern recognition (pp. 3233\u20133241).","DOI":"10.1109\/CVPR.2017.344"},{"key":"2365_CR76","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Polosukhin, I. (2017). Attention is all you need. Neural information processing systems (pp. 5998\u2013 6008)."},{"key":"2365_CR77","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Bengio, S., Murphy, K., Parikh, D., & Chechik, G. (2017). Context-aware captions from context-agnostic supervision. IEEE conference on computer vision and pattern recognition (pp. 1070\u20131079).","DOI":"10.1109\/CVPR.2017.120"},{"key":"2365_CR78","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., & Parikh, D. (2015). Cider: Consensus-based image description evaluation. IEEE conference on computer vision and pattern recognition (pp. 4566\u2013 4575).","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2365_CR79","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, W., Zang, Y., Cao, Y., Pang, J., Gong, T., Lin, D. (2021). Seesaw loss for long-tailed instance segmentation. Cvpr.","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"2365_CR80","doi-asserted-by":"crossref","unstructured":"Wang, Y., Morariu, V.I., & Davis, L.S. (2018). Learning a discriminative filter bank within a CNN for fine-grained recognition. IEEE conference on computer vision and pattern recognition (pp. 4148\u20134157).","DOI":"10.1109\/CVPR.2018.00436"},{"key":"2365_CR81","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. IEEE conference on computer vision and pattern recognition (pp. 5987\u20135995).","DOI":"10.1109\/CVPR.2017.634"},{"key":"2365_CR82","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., & Fei-Fei, L. (2017). Scene graph generation by iterative message passing. IEEE conference on computer vision and pattern recognition (pp. 3097\u2013 3106).","DOI":"10.1109\/CVPR.2017.330"},{"key":"2365_CR83","doi-asserted-by":"crossref","unstructured":"Yan, S., Shen, C., Jin, Z., Huang, J., Jiang, R., Chen, Y., & Hua, X. (2020). PCPL: predicate-correlation perception learning for unbiased scene graph generation. Acmmm.","DOI":"10.1145\/3394171.3413722"},{"key":"2365_CR84","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., & Mei, T. (2017). Boosting image captioning with attributes. IEEE international conference on computer vision (pp. 4904\u20134912).","DOI":"10.1109\/ICCV.2017.524"},{"key":"2365_CR85","first-page":"330","volume":"11207","author":"G Yin","year":"2018","unstructured":"Yin, G., Sheng, L., Liu, B., Yu, N., Wang, X., Shao, J., & Loy, C. C. (2018). Zoom-net: Mining deep feature interactions for visual relationship recognition. European conference on computer vision, 11207, 330\u2013347.","journal-title":"European conference on computer vision"},{"key":"2365_CR86","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Wang, Y., Hu, Y., & Wu, Q. (2021). Cogtree: Cognition tree loss for unbi-ased scene graph generation. International joint conference on artificial intelligence (pp. 1274\u20131280).","DOI":"10.24963\/ijcai.2021\/176"},{"key":"2365_CR87","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., & Choi, Y. (2018). Neural motifs: Scene graph parsing with global context. IEEE conference on computer vision and pattern recognition (pp. 5831\u20135840).","DOI":"10.1109\/CVPR.2018.00611"},{"key":"2365_CR88","doi-asserted-by":"crossref","unstructured":"Zeng, P., Gao, L., Lyu, X., Jing, S., & Song, J. (2021). Conceptual and syntactical cross-modal alignment with cross-level consistency for image-text matching. Mm.","DOI":"10.1145\/3474085.3475380"},{"issue":"8","key":"2365_CR89","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.1007\/s11263-020-01353-8","volume":"128","author":"Y Zhan","year":"2020","unstructured":"Zhan, Y., Yu, J., Yu, T., & Tao, D. (2020). Multi-task compositional network for visual relationship detection. International Journal of Computer Vision, 128(8), 2146\u20132165.","journal-title":"International Journal of Computer Vision"},{"key":"2365_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, A., Yao, Y., Chen, Q., Ji, W., Liu, Z., Sun, M., & Chua, T. (2022). Fine-grained scene graph generation with data transfer. Corr.","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"2365_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S., & Chua, T. (2017). Visual translation embedding network for visual relation detection. IEEE conference on computer vision and pattern recognition (pp. 3107\u20133115).","DOI":"10.1109\/CVPR.2017.331"},{"key":"2365_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, M., Yang, Y., Zhang, H., Ji, Y., Shen, H. T., & Chua, T. (2019). More is better: Precise and detailed image captioning using online positive recall and missing concepts mining. IEEE Transactions on Image Processing, 28(1), 32\u201344.","DOI":"10.1109\/TIP.2018.2855415"},{"key":"2365_CR93","doi-asserted-by":"crossref","unstructured":"Zhao, L., Lyu, X., Song, J., & Gao, L. (2021). Guess-which? Visual dialog with attentive memory network. PR.","DOI":"10.1016\/j.patcog.2021.107823"},{"key":"2365_CR94","doi-asserted-by":"crossref","unstructured":"Zhao, S., Sharma, P., Levinboim, T., & Soricut, R. (2019). Informative image captioning with external sources of information. (pp. 6485\u2013 6494).","DOI":"10.18653\/v1\/P19-1650"},{"key":"2365_CR95","doi-asserted-by":"crossref","unstructured":"Zheng, C., Lyu, X., Gao, L., Dai, B., & Song, J. (2023). Prototype-based embedding network for scene graph generation. CVPR.","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"2365_CR96","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zhong, Y., Wang, J., & Ma, A. (2020). Foreground-aware relation network for geospatial object segmentation in high spatial resolution remote sensing imagery. Cvpr.","DOI":"10.1109\/CVPR42600.2020.00415"},{"key":"2365_CR97","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Shi, J., Yang, J., Xu, C., & Li, Y. (2021). Learning to generate scene graph from natural language supervision. IEEE international conference on computer vision (pp. 1803\u20131814).","DOI":"10.1109\/ICCV48922.2021.00184"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02365-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02365-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02365-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T06:00:01Z","timestamp":1749276001000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02365-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,24]]},"references-count":97,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["2365"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02365-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,24]]},"assertion":[{"value":"22 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2025","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 have no other Conflict of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}