{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T21:09:36Z","timestamp":1788728976477,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376695","type":"print"},{"value":"9783032376701","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"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\/978-3-032-37670-1_13","type":"book-chapter","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:42:41Z","timestamp":1788727361000},"page":"214-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MOTOR: Learning ID-Free Item Representation with\u00a0Token Crossing for\u00a0Embedding-Based Multimodal Recommendation"],"prefix":"10.1007","author":[{"given":"Kangning","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiarui","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianghao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjie","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Cheng, H.T., et al.: Wide & deep learning for recommender systems (2016)","DOI":"10.1145\/2988450.2988454"},{"key":"13_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"issue":"4","key":"13_CR3","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1109\/TPAMI.2013.240","volume":"36","author":"T Ge","year":"2013","unstructured":"Ge, T., He, K., Ke, Q., Sun, J.: Optimized product quantization. IEEE Trans. Pattern Anal. Mach. Intell. 36(4), 744\u2013755 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR4","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Guo, H., Tang, R., Ye, Y., Li, Z., He, X.: Deepfm: a factorization-machine based neural network for ctr prediction (2017)","DOI":"10.24963\/ijcai.2017\/239"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Guo, Z., Li, J., Li, G., Wang, C., Shi, S., Ruan, B.: Lgmrec: local and global graph learning for multimodal recommendation (2023)","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"13_CR7","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":"13_CR8","doi-asserted-by":"crossref","unstructured":"He, R., McAuley, J.: Vbpr: visual bayesian personalized ranking from implicit feedback. In: Proceedings of the AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: Lightgcn: simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 639\u2013648 (2020)","DOI":"10.1145\/3397271.3401063"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Hou, Y., Mu, S., Zhao, W.X., Li, Y., Ding, B., Wen, J.R.: Towards universal sequence representation learning for recommender systems (2022)","DOI":"10.1145\/3534678.3539381"},{"key":"13_CR11","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with gpus (2017)"},{"key":"13_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Text is all you need: learning language representations for sequential recommendation. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD \u201923, pp. 1258\u20131267. Association for Computing Machinery, New York (2023)","DOI":"10.1145\/3580305.3599519"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Lin, G., Meng, Z., Wang, D., Long, Q., Zhou, Y., Xiao, M.: Gume: graphs and user modalities enhancement for long-tail multimodal recommendation (2024)","DOI":"10.1145\/3627673.3679620"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wu, S., Wang, L.: Deepstyle: learning user preferences for visual recommendation. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 841\u2013844 (2017)","DOI":"10.1145\/3077136.3080658"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Alignrec: aligning and training in multimodal recommendations. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pp. 1503\u20131512 (2024)","DOI":"10.1145\/3627673.3679626"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Ni, J., Li, J., McAuley, J.: Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 188\u2013197 (2019)","DOI":"10.18653\/v1\/D19-1018"},{"key":"13_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"13_CR19","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"13_CR20","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2023)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"13_CR22","unstructured":"Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: Bpr: bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012)"},{"key":"13_CR23","doi-asserted-by":"publisher","unstructured":"Shan, R., et al.: An automatic graph construction framework based on large language models for recommendation. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD \u201925, vol. 2, pp. 4806\u20134817. Association for Computing Machinery, New York (2025). https:\/\/doi.org\/10.1145\/3711896.3737192","DOI":"10.1145\/3711896.3737192"},{"key":"13_CR24","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Tao, Z., et al.: Self-supervised learning for multimedia recommendation. IEEE Trans. Multimedia (2022)","DOI":"10.1109\/TMM.2022.3187556"},{"key":"13_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"13_CR27","unstructured":"Wang, Q., Wei, Y., Yin, J., Wu, J., Song, X., Nie, L.: Dualgnn: dual graph neural network for multimedia recommendation. IEEE Trans. Multimedia (2021)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Wang, R., Fu, B., Fu, G., Wang, M.: Deep & cross network for ad click predictions (2017)","DOI":"10.1145\/3124749.3124754"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Wei, Y., Wang, X., Nie, L., He, X., Chua, T.S.: Graph-refined convolutional network for multimedia recommendation with implicit feedback. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 3541\u20133549 (2020)","DOI":"10.1145\/3394171.3413556"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Wei, Y., Wang, X., Nie, L., He, X., Hong, R., Chua, T.S.: Mmgcn: multi-modal graph convolution network for personalized recommendation of micro-video. In: Proceedings of the 27th ACM International Conference on Multimedia (2019)","DOI":"10.1145\/3343031.3351034"},{"key":"13_CR31","unstructured":"Wu, Q., Zhang, H., Gao, X., Yan, J., Zha, H.: Towards open-world recommendation: an inductive model-based collaborative filtering approach. In: International Conference on Machine Learning, pp. 11329\u201311339. PMLR (2021)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Wu, Y., Cao, Q., Shen, H., Tao, S., Cheng, X.: Inmo: a model-agnostic and scalable module for inductive collaborative filtering. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR \u201922, pp. 91\u2013101. Association for Computing Machinery, New York (2022)","DOI":"10.1145\/3477495.3532000"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Yu, P., Tan, Z., Lu, G., Bao, B.K.: Multi-view graph convolutional network for multimedia recommendation. arXiv preprint arXiv:2308.03588 (2023)","DOI":"10.1145\/3581783.3613915"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: Where to go next for recommender systems? id- vs. modality-based recommender models revisited (2023)","DOI":"10.1145\/3539618.3591932"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: DREAM: a dual representation learning framework for multimodal recommendation (2024)","DOI":"10.1137\/1.9781611978032.86"},{"key":"13_CR36","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/978-981-96-1710-4_2","volume-title":"Information Retrieval","author":"K Zhang","year":"2025","unstructured":"Zhang, K., Qin, Y., Su, R., Liu, Y., Zhang, W., Yu, Y.: A dual-aligned model for multimodal recommendation. In: He, X., Ren, Z., Tang, R. (eds.) Information Retrieval, pp. 14\u201327. Springer, Singapore (2025). https:\/\/doi.org\/10.1007\/978-981-96-1710-4_2"},{"key":"13_CR37","unstructured":"Zhou, H., Zhou, X., Zeng, Z., Zhang, L., Shen, Z.: A comprehensive survey on multimodal recommender systems: taxonomy, evaluation, and future directions. arXiv preprint arXiv:2302.04473 (2023)"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, X., Shen, Z.: A tale of two graphs: freezing and denoising graph structures for multimodal recommendation. In: Proceedings of the 31st ACM International Conference on Multimedia, MM \u201923. ACM (2023)","DOI":"10.1145\/3581783.3611943"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Bootstrap latent representations for multi-modal recommendation. In: Proceedings of the ACM Web Conference 2023, pp. 845\u2013854 (2023)","DOI":"10.1145\/3543507.3583251"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37670-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:42:49Z","timestamp":1788727369000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37670-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"ISBN":["9783032376695","9783032376701"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37670-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"assertion":[{"value":"7 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"7 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}