{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:12:03Z","timestamp":1783768323827,"version":"3.55.0"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402334"],"award-info":[{"award-number":["62402334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02332-8","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:00:15Z","timestamp":1778047215000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring fine-grained multimodal prompts for visual relation detection with adaptation of VLMs"],"prefix":"10.1007","volume":"32","author":[{"given":"Jin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongshuo","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2332_CR1","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"2332_CR2","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y., Parekh, Z., Pham, H., Le, Q.V., Sung, Y., Li, Z., Duerig, T.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"issue":"9","key":"2332_CR3","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vis. 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"2332_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai, J., Qiao, Y., Li, H.: Tip-adapter: training-free adaption of CLIP for few-shot classification. In: ECCV, pp. 493\u2013510 (2022)","DOI":"10.1007\/978-3-031-19833-5_29"},{"issue":"2","key":"2332_CR5","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., Qiao, Y.: Clip-adapter: Better vision-language models with feature adapters. Int. J. Comput. Vis. 132(2), 581\u2013595 (2024)","journal-title":"Int. J. Comput. Vis."},{"key":"2332_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123221","volume":"246","author":"J Liu","year":"2024","unstructured":"Liu, J., Cui, J., Ye, M., Zhu, X., Tang, S.: Shooting condition insensitive unmanned aerial vehicle object detection. Expert Syst. Appl. 246, 123221 (2024)","journal-title":"Expert Syst. Appl."},{"key":"2332_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124183","volume":"252","author":"Z Yang","year":"2024","unstructured":"Yang, Z., An, G., Zheng, Z., Cao, S., Wang, F.: EPK-CLIP: external and priori knowledge CLIP for action recognition. Expert Syst. Appl. 252, 124183 (2024)","journal-title":"Expert Syst. Appl."},{"key":"2332_CR8","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lu, Y., Li, Q., Tao, X., Guo, Y., Gong, M., Liu, T.: CRIS: clip-driven referring image segmentation. In: CVPR, pp. 11676\u201311685 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"2332_CR9","doi-asserted-by":"crossref","unstructured":"Huang, T., Dong, B., Yang, Y., Huang, X., Lau, R.W.H., Ouyang, W., Zuo, W.: Clip2point: transfer CLIP to point cloud classification with image-depth pre-training. In: ICCV, pp. 22100\u201322110 (2023)","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"2332_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127420","volume":"279","author":"L Zhou","year":"2025","unstructured":"Zhou, L., Mao, J., Xu, X., Li, X., Meng, X.: Generative external knowledge for zero-shot action recognition. Expert Syst. Appl. 279, 127420 (2025)","journal-title":"Expert Syst. Appl."},{"key":"2332_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126296","volume":"268","author":"W Xu","year":"2025","unstructured":"Xu, W., Xu, Y., Miao, Z., Cen, Y., Wan, L., Ma, X.: CroCaps: A CLIP\u2013assisted cross-domain video captioner. Expert Syst. Appl. 268, 126296 (2025)","journal-title":"Expert Syst. Appl."},{"key":"2332_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126974","volume":"276","author":"X Zhao","year":"2025","unstructured":"Zhao, X., Poria, S., Li, X., Chen, Y., Tang, B.: Toward robust multimodal sentiment analysis using multimodal foundational models. Expert Syst. Appl. 276, 126974 (2025)","journal-title":"Expert Syst. Appl."},{"issue":"12","key":"2332_CR13","doi-asserted-by":"publisher","first-page":"12425","DOI":"10.1109\/TCSVT.2024.3437437","volume":"34","author":"G Zhang","year":"2024","unstructured":"Zhang, G., Tang, Y., Zhang, C., Zheng, X., Zhao, Y.: Entity dependency learning network with relation prediction for video visual relation detection. IEEE Trans. Circuits Syst. Video Technol. 34(12), 12425\u201312436 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2332_CR14","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, J., Zhang, P., Li, C., Codella, N., Li, L.H., Zhou, L., Dai, X., Yuan, L., Li, Y., Gao, J.: Regionclip: region-based language-image pretraining. In: CVPR, pp. 16772\u201316782 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"2332_CR15","doi-asserted-by":"crossref","unstructured":"Sun, Z., Fang, Y., Wu, T., Zhang, P., Zang, Y., Kong, S., Xiong, Y., Lin, D., Wang, J.: Alpha-clip: A CLIP model focusing on wherever you want. In: CVPR, pp. 13019\u201313029 (2024)","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"2332_CR16","doi-asserted-by":"crossref","unstructured":"Yang, L., Wang, Y., Li, X., Wang, X., Yang, J.: Fine-grained visual prompting. In: NeurIPS (2023)","DOI":"10.52202\/075280-1086"},{"key":"2332_CR17","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16795\u201316804 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"2332_CR18","doi-asserted-by":"crossref","unstructured":"Gao, J., Ruan, J., Xiang, S., Yu, Z., Ji, K., Xie, M., Liu, T., Fu, Y.: LAMM: label alignment for multi-modal prompt learning. In: AAAI, pp. 1815\u20131823 (2024)","DOI":"10.1609\/aaai.v38i3.27950"},{"key":"2332_CR19","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B., Cardie, C., Belongie, S.J., Hariharan, B., Lim, S.: Visual prompt tuning. In: ECCV, pp. 709\u2013727 (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"2332_CR20","doi-asserted-by":"crossref","unstructured":"Goswami, K., Karanam, S., Udhayanan, P., Joseph, K.J., Srinivasan, B.V.: Copl: Contextual prompt learning for vision-language understanding. In: AAAI, pp. 18090\u201318098 (2024)","DOI":"10.1609\/aaai.v38i16.29766"},{"key":"2332_CR21","doi-asserted-by":"crossref","unstructured":"Li, L., Xiao, J., Chen, G., Shao, J., Zhuang, Y., Chen, L.: Zero-shot visual relation detection via composite visual cues from large language models. In: NeurIPS (2023)","DOI":"10.52202\/075280-2179"},{"key":"2332_CR22","doi-asserted-by":"crossref","unstructured":"Shtedritski, A., Rupprecht, C., Vedaldi, A.: What does CLIP know about a red circle? Visual prompt engineering for VLMs. In: ICCV, pp. 11953\u201311963 (2023)","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"2332_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W., Doll\u00e1r, P., Girshick, R.B.: Segment anything. In: ICCV, pp. 3992\u20134003 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2332_CR24","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. In: ACL, pp. 4582\u20134597 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"2332_CR25","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: EMNLP, pp. 3045\u20133059 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"2332_CR26","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Friedman, D., Chen, D.: Factual probing is [MASK]: learning vs. learning to recall. In: NAACL, pp. 5017\u20135033 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"2332_CR27","doi-asserted-by":"crossref","unstructured":"Miyai, A., Yu, Q., Irie, G., Aizawa, K.: Locoop: Few-shot out-of-distribution detection via prompt learning. In: NeurIPS (2023)","DOI":"10.52202\/075280-3335"},{"key":"2332_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126400","volume":"269","author":"Y Li","year":"2025","unstructured":"Li, Y., Long, S., Wang, S., Zhao, X., Li, Y.: Prompt-induced prototype alignment for few-shot unsupervised domain adaptation. Expert Syst. Appl. 269, 126400 (2025)","journal-title":"Expert Syst. Appl."},{"key":"2332_CR29","doi-asserted-by":"crossref","unstructured":"Dodge, S.F., Karam, L.J.: Understanding how image quality affects deep neural networks. In: QoMEX, pp. 1\u20136 (2016)","DOI":"10.1109\/QoMEX.2016.7498955"},{"key":"2332_CR30","unstructured":"Touvron, H., Martin, L., Stone, K., al.: Llama 2: Open foundation and fine-tuned chat models. arXiv: 2307.09288 (2023)"},{"key":"2332_CR31","unstructured":"Zhang, Z., Zhang, A., Li, M., Smola, A.: Automatic chain of thought prompting in large language models. In: ICLR (2023)"},{"issue":"1","key":"2332_CR32","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., Shamma, D.A., Bernstein, M.S., Fei-Fei, L.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"2332_CR33","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: A new dataset for real-world visual reasoning and compositional question answering. In: CVPR, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"2332_CR34","doi-asserted-by":"crossref","unstructured":"Lu, C., Krishna, R., Bernstein, M.S., Fei-Fei, L.: Visual relationship detection with language priors. In: ECCV, pp. 852\u2013869 (2016)","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"2332_CR35","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Visual relationship detection with internal and external linguistic knowledge distillation. In: ICCV, pp. 1068\u20131076 (2017)","DOI":"10.1109\/ICCV.2017.121"},{"key":"2332_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S., Chua, T.: Visual translation embedding network for visual relation detection. In: CVPR, pp. 3107\u20133115 (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"2332_CR37","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: CVPR, pp. 3097\u20133106 (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"2332_CR38","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: Scene graph parsing with global context. In: CVPR, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"issue":"3","key":"2332_CR39","doi-asserted-by":"publisher","first-page":"1031","DOI":"10.1109\/TCSVT.2020.2990989","volume":"31","author":"N Xu","year":"2021","unstructured":"Xu, N., Liu, A., Wong, Y., Nie, W., Su, Y., Kankanhalli, M.S.: Scene graph inference via multi-scale context modeling. IEEE Trans. Circuits Syst. Video Technol. 31(3), 1031\u20131041 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"2332_CR40","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/TNNLS.2020.2979270","volume":"32","author":"G Ren","year":"2021","unstructured":"Ren, G., Ren, L., Liao, Y., Liu, S., Li, B., Han, J., Yan, S.: Scene graph generation with hierarchical context. IEEE Trans. Neural Netw. Learn. Syst. 32(2), 909\u2013915 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2332_CR41","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: CVPR, pp. 3713\u20133722 (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"2332_CR42","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Wang, Y., Hu, Y., Wu, Q.: Cogtree: Cognition tree loss for unbiased scene graph generation. In: IJCAI, pp. 1274\u20131280 (2021)","DOI":"10.24963\/ijcai.2021\/176"},{"key":"2332_CR43","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, L., Huang, Y., Zhang, Z., Zhang, S., Xiao, J.: The devil is in the labels: Noisy label correction for robust scene graph generation. In: CVPR, pp. 18847\u201318856 (2022)","DOI":"10.1109\/CVPR52688.2022.01830"},{"issue":"3","key":"2332_CR44","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1109\/TCSVT.2023.3297842","volume":"34","author":"C Zheng","year":"2024","unstructured":"Zheng, C., Gao, L., Lyu, X., Zeng, P., El-Saddik, A., Shen, H.T.: Dual-branch hybrid learning network for unbiased scene graph generation. IEEE Trans. Circuits Syst. Video Technol. 34(3), 1743\u20131756 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2332_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127486","volume":"280","author":"N Jung","year":"2025","unstructured":"Jung, N., Choi, C.: Union-redefined prototype network for scene graph generation. Expert Syst. Appl. 280, 127486 (2025)","journal-title":"Expert Syst. Appl."},{"key":"2332_CR46","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Unified vision and language prompt learning. arXiv: 2210.07225 (2022)"},{"key":"2332_CR47","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H.A., Maaz, M., Khan, S.H., Khan, F.S.: Maple: Multi-modal prompt learning. In: CVPR, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"2332_CR48","doi-asserted-by":"crossref","unstructured":"Xin, Y., Du, J., Wang, Q., Yan, K., Ding, S.: Mmap: Multi-modal alignment prompt for cross-domain multi-task learning. In: AAAI, pp. 16076\u201316084 (2024)","DOI":"10.1609\/aaai.v38i14.29540"},{"issue":"7","key":"2332_CR49","doi-asserted-by":"publisher","first-page":"3220","DOI":"10.1109\/TCYB.2025.3567126","volume":"55","author":"Z Wen","year":"2025","unstructured":"Wen, Z., Liu, J., Zhang, H., Zuo, F.: Exploring fine-grained visual-text feature alignment with prompt tuning for domain-adaptive object detection. IEEE Trans. Cybern. 55(7), 3220\u20133233 (2025)","journal-title":"IEEE Trans. Cybern."},{"issue":"9","key":"2332_CR50","doi-asserted-by":"publisher","first-page":"6513","DOI":"10.1007\/s11263-025-02497-1","volume":"133","author":"B Xing","year":"2025","unstructured":"Xing, B., Ying, X., Wang, R., Guo, R.: Multi-modal prompt alignment with fine-grained LLM knowledge for unsupervised domain adaptation. Int. J. Comput. Vis. 133(9), 6513\u20136534 (2025)","journal-title":"Int. J. Comput. Vis."},{"key":"2332_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, X., Liu, X., Wang, D., Gao, Y., Liu, Z.: Scene-adaptive and region-aware multi-modal prompt for open vocabulary object detection. In: CVPR, pp. 16741\u201316750 (2024)","DOI":"10.1109\/CVPR52733.2024.01584"},{"key":"2332_CR52","doi-asserted-by":"crossref","unstructured":"Cho, E., Kim, J., Kim, H.J.: Distribution-aware prompt tuning for vision-language models. In: ICCV, pp. 21947\u201321956 (2023)","DOI":"10.1109\/ICCV51070.2023.02011"},{"key":"2332_CR53","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, J., Zhang, Y., Liu, Y., Tian, X.: Prompt distribution learning. In: CVPR, pp. 5196\u20135205 (2022)","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"2332_CR54","doi-asserted-by":"crossref","unstructured":"Wang, R., Zheng, H., Duan, X., Liu, J., Lu, Y., Wang, T., Xu, S., Zhang, B.: Few-shot learning with visual distribution calibration and cross-modal distribution alignment. In: CVPR, pp. 23445\u201323454 (2023)","DOI":"10.1109\/CVPR52729.2023.02245"},{"key":"2332_CR55","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: LASP: text-to-text optimization for language-aware soft prompting of vision & language models. In: CVPR, pp. 23232\u201323241 (2023)","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"2332_CR56","doi-asserted-by":"crossref","unstructured":"He, S., Liu, K., Ji, G., Zhao, J.: Learning to represent knowledge graphs with gaussian embedding. In: ACM CIKM, pp. 623\u2013632 (2015)","DOI":"10.1145\/2806416.2806502"},{"key":"2332_CR57","doi-asserted-by":"crossref","unstructured":"Xiao, H., Huang, M., Zhu, X.: Transg : A generative model for knowledge graph embedding. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1219"},{"key":"2332_CR58","doi-asserted-by":"crossref","unstructured":"Li, B., Zhou, H., He, J., Wang, M., Yang, Y., Li, L.: On the sentence embeddings from pre-trained language models. In: EMNLP, pp. 9119\u20139130 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"2332_CR59","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: ICML, pp. 9929\u20139939 (2020)"},{"key":"2332_CR60","doi-asserted-by":"crossref","unstructured":"Bhalla, U., Oesterling, A., Srinivas, S., Calmon, F.P., Lakkaraju, H.: Interpreting CLIP with sparse linear concept embeddings (splice). In: NeurIPS (2024)","DOI":"10.52202\/079017-2678"},{"issue":"1","key":"2332_CR61","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/BF02418571","volume":"30","author":"JLWV Jensen","year":"1906","unstructured":"Jensen, J.L.W.V.: Sur les fonctions convexes et les in\u00e9galit\u00e9s entre les valeurs moyennes. Acta Math. 30(1), 175\u2013193 (1906)","journal-title":"Acta Math."},{"issue":"4","key":"2332_CR62","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1214\/aoms\/1177731541","volume":"13","author":"JH Curtiss","year":"1942","unstructured":"Curtiss, J.H.: A note on the theory of moment generating functions. Ann. Math. Stat. 13(4), 430\u2013433 (1942)","journal-title":"Ann. Math. Stat."},{"key":"2332_CR63","unstructured":"Liu, H., Xue, W., Chen, Y., Chen, D., Zhao, X., Wang, K., Hou, L., Li, R., Peng, W.: A survey on hallucination in large vision-language models. arXiv: 2402.00253 (2024)"},{"key":"2332_CR64","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., Lin, L.: Knowledge-embedded routing network for scene graph generation. In: CVPR, pp. 6163\u20136171 (2019)","DOI":"10.1109\/CVPR.2019.00632"},{"key":"2332_CR65","doi-asserted-by":"crossref","unstructured":"Dong, X., Gan, T., Song, X., Wu, J., Cheng, Y., Nie, L.: Stacked hybrid-attention and group collaborative learning for unbiased scene graph generation. In: CVPR, pp. 19405\u201319414 (2022)","DOI":"10.1109\/CVPR52688.2022.01882"},{"issue":"7","key":"2332_CR66","doi-asserted-by":"publisher","first-page":"5295","DOI":"10.1109\/TCSVT.2023.3344569","volume":"34","author":"H Xu","year":"2024","unstructured":"Xu, H., Wang, L., Xu, K., Fu, F., Yin, B., Huang, Q.: A new training data organization form and training mode for unbiased scene graph generation. IEEE Trans. Circuits Syst. Video Technol. 34(7), 5295\u20135305 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2332_CR67","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: CVPR, pp. 6619\u20136628 (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"2332_CR68","doi-asserted-by":"crossref","unstructured":"Chen, G., Li, J., Wang, W.: Scene graph generation with role-playing large language models. In: NeurIPS (2024)","DOI":"10.52202\/079017-4203"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02332-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02332-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02332-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:18:16Z","timestamp":1783765096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02332-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":68,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2332"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02332-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"6 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no Conflict of interest related to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"273"}}