{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:45:59Z","timestamp":1785653159001,"version":"3.56.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-31666-0_6","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:29Z","timestamp":1785649649000},"page":"80-95","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Metapath-Driven Embeddings for Zero-Shot Object State Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9539-8749","authenticated-orcid":false,"given":"Filippos","family":"Gouidis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2467-8727","authenticated-orcid":false,"given":"Konstantinos","family":"Papoutsakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6796-1015","authenticated-orcid":false,"given":"Theodore","family":"Patkos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8230-3192","authenticated-orcid":false,"given":"Antonis","family":"Argyros","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0863-8266","authenticated-orcid":false,"given":"Dimitris","family":"Plexousakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Campbell, D., et al.: Understanding the limits of vision language models through the lens of the binding problem. In: Advances in Neural Information Processing Systems, neurIPS 2024, vol. 37 (2024)","DOI":"10.52202\/079017-3604"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Domingos, P., Richardson, M.: Markov logic: a unifying framework for statistical relational learning. In: Introduction to Statistical Relational Learning, pp. 339\u2013371 (2007)","DOI":"10.7551\/mitpress\/7432.003.0014"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 601\u2013610 (2014)","DOI":"10.1145\/2623330.2623623"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Dong, Y., Chawla, N.V., Swami, A.: Metapath2vec: scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 135\u2013144. ACM (2017)","DOI":"10.1145\/3097983.3098036"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Duan, K., Parikh, D., Crandall, D., Grauman, K.: Discovering localized attributes for fine-grained recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3474\u20133481. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248089"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Fan, S., Zhu, J., Han, X., Shi, C., Hu, L., Ma, B., Li, Y.: Metapath-guided heterogeneous graph neural network for intent recommendation. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2478\u20132486 (2019)","DOI":"10.1145\/3292500.3330673"},{"key":"6_CR7","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Mikolov, T.: DeVise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, pp. 2121\u20132129 (2013)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Gouidis, F., Patkos, T., Argyros, A., Plexousakis, D.: Detecting object states vs detecting objects: a new dataset and a quantitative experimental study. In: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), vol. 5, pp. 590\u2013600 (2022)","DOI":"10.5220\/0010898400003124"},{"key":"6_CR9","first-page":"749","volume":"738","author":"F Gouidis","year":"2024","unstructured":"Gouidis, F., Papoutsakis, K., Patkos, T., Argyros, A., Plexousakis, D.: Exploring the impact of knowledge graphs on zero-shot visual object state classification. Proc. Copyright 738, 749 (2024)","journal-title":"Proc. Copyright"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Gouidis, F., Papantoniou, K., Papoutsakis, K., Patkos, T., Argyros, A., Plexousakis, D.: Fusing domain-specific content from large language models into knowledge graphs for enhanced zero shot object state classification. In: Proceedings of the AAAI Symposium Series, vol. 3, pp. 115\u2013124 (2024)","DOI":"10.1609\/aaaiss.v3i1.31190"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Gouidis, F., Papantoniou, K., Papoutsakis, K., Patkos, T., Argyros, A., Plexousakis, D.: LLM-aided knowledge graph construction for zero-shot visual object state classification. In: 2024 14th International Conference on Pattern Recognition Systems (ICPRS), pp. 1\u20137. IEEE (2024)","DOI":"10.1109\/ICPRS62101.2024.10677802"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Gouidis, F., Papoutsakis, K., Patkos, T., Argyros, A., Plexousakis, D.: Recognizing unseen states of unknown objects by leveraging knowledge graphs. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 8648\u20138659. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00838"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855\u2013864 (2016)","DOI":"10.1145\/2939672.2939754"},{"key":"6_CR14","unstructured":"Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Isola, P., Lim, J.J., Adelson, E.H.: Discovering states and transformations in image collections. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1383\u20131391 (2015)","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"6_CR17","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Kampffmeyer, M., Chen, Y., Liang, X., Wang, H., Zhang, Y., Xing, E.P.: Rethinking knowledge graph propagation for zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11487\u201311496 (2019)","DOI":"10.1109\/CVPR.2019.01175"},{"key":"6_CR19","unstructured":"Kipf, T., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the International Conference on Learning Representations (ICLR) (2017)"},{"key":"6_CR20","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 951\u2013958. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"6_CR22","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, X., Wei, K., Deng, C., Yang, M.: Siamese contrastive embedding network for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9326\u20139335 (2022)","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., Akata, Z.: Open world compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5222\u20135230 (2021)","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"6_CR25","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., Akata, Z.: Learning graph embeddings for open world compositional zero-shot learning. IEEE Trans. Pattern Anal. Mach. Intell. 8828(c), 1\u201315 (2022)"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Marino, K., Salakhutdinov, R., Gupta, A.: The more you know: using knowledge graphs for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2673\u20132681 (2017)","DOI":"10.1109\/CVPR.2017.10"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Tombari, F., Akata, Z.: Learning graph embeddings for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 953\u2013962 (2021)","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"6_CR28","unstructured":"Nayak, N.V., Bach, S.H.: Zero-shot learning with common sense knowledge graphs. Trans. Mach. Learn. Res. (2022)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Ning, W., et al.: Automatic meta-path discovery for effective graph-based recommendation. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 1563\u20131572 (2022)","DOI":"10.1145\/3511808.3557244"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701\u2013710 (2014)","DOI":"10.1145\/2623330.2623732"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Pham, K., et al.: Learning to predict visual attributes in the wild. In: Proceedings of the IEEE\/CVF CVPR, pp. 13018\u201313028 (2021)","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Purushwalkam, S., Nickel, M., Gupta, A., Ranzato, M.: Task-driven modular networks for zero-shot compositional learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3593\u20133602 (2019)","DOI":"10.1109\/ICCV.2019.00369"},{"key":"6_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"6_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","volume-title":"The Semantic Web","author":"M Schlichtkrull","year":"2018","unstructured":"Schlichtkrull, M., Kipf, T.N., Bloem, P., van\u00a0den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 593\u2013607. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93417-4_38"},{"key":"6_CR36","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1038\/s42256-024-00963-y","volume":"7","author":"LM Schulze Buschoff","year":"2025","unstructured":"Schulze Buschoff, L.M., Akata, E., Bethge, M., Schulz, E.: Visual cognition in multimodal large language models. Nature Mach. Intell. 7, 96\u2013106 (2025)","journal-title":"Nature Mach. Intell."},{"issue":"10","key":"6_CR37","doi-asserted-by":"publisher","first-page":"2479","DOI":"10.1109\/TKDE.2013.2297920","volume":"26","author":"C Shi","year":"2014","unstructured":"Shi, C., Hu, B., Zhao, X., Yu, P.S.: HeteSim: a general framework for relevance measure in heterogeneous networks. IEEE Trans. Knowl. Data Eng. 26(10), 2479\u20132492 (2014)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"6_CR38","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/TKDE.2016.2598561","volume":"29","author":"C Shi","year":"2016","unstructured":"Shi, C., Li, Y., Zhang, J., Sun, Y., Philip, S.Y.: A survey of heterogeneous information network analysis. IEEE Trans. Knowl. Data Eng. 29(1), 17\u201337 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"6_CR39","unstructured":"Socher, R., Ganjoo, M., Manning, C.D., Ng, A.: Zero-shot learning through cross-modal transfer. In: Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Speer, R., Chin, J., Havasi, C.: ConceptNet 5.5: an open multilingual graph of general knowledge. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11164"},{"issue":"11","key":"6_CR41","doi-asserted-by":"publisher","first-page":"992","DOI":"10.14778\/3402707.3402736","volume":"4","author":"Y Sun","year":"2011","unstructured":"Sun, Y., Han, J., Yan, X., Yu, P.S., Wu, T.: PathSim: meta path-based top-k similarity search in heterogeneous information networks. Proc. VLDB Endowment 4(11), 992\u20131003 (2011)","journal-title":"Proc. VLDB Endowment"},{"key":"6_CR42","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations, vol. 6, Ithaca (2018)"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Learning conditional attributes for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11197\u201311206 (2023)","DOI":"10.1109\/CVPR52729.2023.01077"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Heterogeneous graph attention network. In: The World Wide Web Conference, pp. 2022\u20132032 (2019)","DOI":"10.1145\/3308558.3313562"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Wang, X., Ye, Y., Gupta, A.: Zero-shot recognition via semantic embeddings and knowledge graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6857\u20136866 (2018)","DOI":"10.1109\/CVPR.2018.00717"},{"key":"6_CR46","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.neunet.2022.05.026","volume":"153","author":"S Yun","year":"2022","unstructured":"Yun, S., et al.: Graph transformer networks: learning meta-path graphs to improve GNNs. Neural Netw. 153, 104\u2013119 (2022)","journal-title":"Neural Netw."},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, C., Song, D., Huang, C., Swami, A., Chawla, N.V.: Heterogeneous graph neural network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 793\u2013803. ACM (2019)","DOI":"10.1145\/3292500.3330961"},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Elhoseiny, M., Liu, B., Peng, X., Elgammal, A.: A generative adversarial approach for zero-shot learning from noisy texts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1004\u20131013 (2018)","DOI":"10.1109\/CVPR.2018.00111"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:34Z","timestamp":1785649654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}