{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:52Z","timestamp":1763202952596,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723469"},{"type":"electronic","value":"9783031723476"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72347-6_8","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:02:55Z","timestamp":1726491775000},"page":"110-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unifying Visual and\u00a0Semantic Feature Spaces with\u00a0Diffusion Models for\u00a0Enhanced Cross-Modal Alignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5718-8366","authenticated-orcid":false,"given":"Yuze","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2971-9478","authenticated-orcid":false,"given":"Zixuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6638-2361","authenticated-orcid":false,"given":"Xiangxian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4682-3268","authenticated-orcid":false,"given":"Jinxing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4151-8290","authenticated-orcid":false,"given":"Yuqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-5659","authenticated-orcid":false,"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0273-5946","authenticated-orcid":false,"given":"Lei","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"8_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1007\/978-3-319-70742-6_37","volume-title":"New Trends in Image Analysis and Processing \u2013 ICIAP 2017","author":"M Bola\u00f1os","year":"2017","unstructured":"Bola\u00f1os, M., Ferr\u00e0, A., Radeva, P.: Food ingredients recognition through multi-label learning. In: Battiato, S., Farinella, G.M., Leo, M., Gallo, G. (eds.) ICIAP 2017. LNCS, vol. 10590, pp. 394\u2013402. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-70742-6_37"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Ngo, C.W.: Deep-based ingredient recognition for cooking recipe retrieval. In: Proceedings of the 24th ACM Multimedia, pp. 32\u201341 (2016)","DOI":"10.1145\/2964284.2964315"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qi, Z., Cao, X., Li, X., Meng, X., Meng, L.: Class-level structural relation modeling and smoothing for visual representation learning. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2964\u20132972 (2023)","DOI":"10.1145\/3581783.3612511"},{"key":"8_CR4","unstructured":"Clark, K., Jaini, P.: Text-to-image diffusion models are zero shot classifiers. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Ding, X., Chen, H., Zhang, X., Han, J., Ding, G.: Repmlpnet: hierarchical vision MLP with re-parameterized locality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 578\u2013587 (2022)","DOI":"10.1109\/CVPR52688.2022.00066"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: Repvgg: making VGG-style convnets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13733\u201313742 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"8_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"8_CR10","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, D., Ye, M.: Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2787\u20132797 (2023)","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4893\u20134902 (2019)","DOI":"10.1109\/CVPR.2019.00503"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Batra, T., Baig, M.H., Ulbricht, D.: Sliced Wasserstein discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10285\u201310295 (2019)","DOI":"10.1109\/CVPR.2019.01053"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Li, A.C., Prabhudesai, M., Duggal, S., Brown, E., Pathak, D.: Your diffusion model is secretly a zero-shot classifier. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2206\u20132217 (2023)","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Ma, H., Li, X., Qi, Z., Meng, L., Meng, X.: Unsupervised contrastive masking for visual haze classification. In: Proceedings of the 2022 International Conference on Multimedia Retrieval, pp. 426\u2013434 (2022)","DOI":"10.1145\/3512527.3531370"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Xie, B., Wu, J., Zhao, Y., Liu, C.H., Ding, Z.: Simultaneous semantic alignment network for heterogeneous domain adaptation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 3866\u20133874 (2020)","DOI":"10.1145\/3394171.3413995"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Meng, L., Wu, L., Li, M., Meng, X.: Dreamfont3d: personalized text-to-3D artistic font generation. In: ACM SIGGRAPH, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657476"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., Zheng, Y., Ma, H., Qi, Z., Meng, X., Meng, L.: Cross-modal learning using privileged information for long-tailed image classification. CVM (2024)","DOI":"10.1007\/s41095-023-0382-0"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Ma, H., et al.: Plug-in diffusion model for sequential recommendation. In: Proceedings of AAAI, pp. 8886\u20138894 (2024)","DOI":"10.1609\/aaai.v38i8.28736"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Ma, H., Xie, R., Meng, L., Yang, Y., Sun, X., Kang, Z.: Seedrec: sememe-based diffusion for sequential recommendation. In: Proceedings of IJCAI, pp.\u00a01\u20139 (2024)","DOI":"10.24963\/ijcai.2024\/251"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Ma, H., Yang, Y., Meng, L., Xie, R., Meng, X.: Multimodal conditioned diffusion model for recommendation, pp. 1733\u20131740 (2024)","DOI":"10.1145\/3589335.3651956"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Martinel, N., Foresti, G.L., Micheloni, C.: Wide-slice residual networks for food recognition. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 567\u2013576. IEEE (2018)","DOI":"10.1109\/WACV.2018.00068"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: Learning using privileged information for food recognition. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 557\u2013565 (2019)","DOI":"10.1145\/3343031.3350870"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"8_CR26","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Peng, X., Wei, Y., Deng, A., Wang, D., Hu, D.: Balanced multimodal learning via on-the-fly gradient modulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8238\u20138247 (2022)","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Qi, Z., Meng, L., Chen, Z., Hu, H., Lin, H., Meng, X.: Cross-silo prototypical calibration for federated learning with non-IID data. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 3099\u20133107 (2023)","DOI":"10.1145\/3581783.3612481"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"8_CR30","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Wang, C., Wu, L., Liu, X., Li, X., Meng, L., Meng, X.: Anything to glyph: artistic font synthesis via text-to-image diffusion model. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201311 (2023)","DOI":"10.1145\/3610548.3618208"},{"key":"8_CR32","unstructured":"Wang, F., Zhou, Y., Wang, S., Vardhanabhuti, V., Yu, L.: Multi-granularity cross-modal alignment for generalized medical visual representation learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 33536\u201333549 (2022)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, X., Liu, Y., Cao, X., Meng, X., Meng, L.: Causal inference for out-of-distribution recognition via sample balancing. CAAI Trans. Intell. Technol. (2024)","DOI":"10.1049\/cit2.12311"},{"key":"8_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1007\/978-3-031-25075-0_36","volume-title":"European Conference on Computer Vision","author":"Y Wang","year":"2022","unstructured":"Wang, Y., et al.: Meta-causal feature learning for out-of-distribution generalization. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13806, pp. 530\u2013545. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25075-0_36"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Qi, Z., Li, X., Liu, J., Meng, X., Meng, L.: Multi-channel attentive weighting of visual frames for multimodal video classification. In: 2023 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2023)","DOI":"10.1109\/IJCNN54540.2023.10192036"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Xie, C.W., Wu, J., Zheng, Y., Pan, P., Hua, X.S.: Token embeddings alignment for cross-modal retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4555\u20134563 (2022)","DOI":"10.1145\/3503161.3548107"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. In: BMVC (2016)","DOI":"10.5244\/C.30.87"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72347-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T06:15:00Z","timestamp":1732774500000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72347-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723469","9783031723476"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72347-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}