{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:01:29Z","timestamp":1743073289375,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620609"},{"type":"electronic","value":"9789819620616"}],"license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2061-6_25","type":"book-chapter","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T05:46:44Z","timestamp":1735537604000},"page":"338-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MDT-Net: A Mask Decoder Tuning Strategy for\u00a0CLIP-Based Zero-Shot 3D Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0300-0772","authenticated-orcid":false,"given":"Hao","family":"Yan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4247-6210","authenticated-orcid":false,"given":"Jing","family":"Bai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Bai, J., Yuan, T., Fan, Y.: ZS3D-Net: zero-shot classification network for 3D models. J. Comput.-Aided Des. Comput. Graph. 34, 1118\u20131126 (2022)","DOI":"10.3724\/SP.J.1089.2022.19173"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: TransZero++: cross attribute-guided transformer for zero-shot learning. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3229526"},{"issue":"1","key":"25_CR3","first-page":"330","volume":"36","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: TransZero: attribute-guided transformer for zero-shot learning. Proc. AAAI Conf. Artif. Intell. 36(1), 330\u2013338 (2022)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Cheraghian, A., Rahman, S., Campbell, D., Petersson, L.: Mitigating the hubness problem for zero-shot learning of 3D objects. In: 30th British Machine Vision Conference 2019, p.\u00a041. BMVA Press (2019)","DOI":"10.23919\/MVA.2019.8758063"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Cheraghian, A., Rahman, S., Petersson, L.: Zero-shot learning of 3D point cloud objects. In: 2019 16th International Conference on Machine Vision Applications, pp.\u00a01\u20136 (2019)","DOI":"10.23919\/MVA.2019.8758063"},{"key":"25_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2019)"},{"key":"25_CR7","unstructured":"Fan, Y., Bai, J., Shao, H., Peng, B.: DFG-ZS3D: discriminative feature-guided zero-shot learning of 3D model classification. J. Comput.-Aided Des. Comput. Graph. (2024)"},{"issue":"11","key":"25_CR8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Guo, Z., et al.: CALIP: zero-shot enhancement of clip with parameter-free attention. In: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Press (2023)","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Huang, T., et al.: Clip2Point: transfer clip to point cloud classification with image-depth pre-training. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22100\u201322110 (2023)","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"25_CR11","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: 2nd International Conference on Learning Representations, ICLR (2014)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Li, S., Sun, L., Li, Q.: CLIP-ReID: exploiting vision-language model for image re-identification without concrete text labels. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1405\u20131413 (2023)","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, J., Zhang, J., Huang, K.: Discriminative learning of latent features for zero-shot recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7463\u20137471 (2018)","DOI":"10.1109\/CVPR.2018.00779"},{"key":"25_CR14","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1109\/JSTARS.2022.3229062","volume":"16","author":"G Liang","year":"2023","unstructured":"Liang, G., Zhao, X., Zhao, J., Zhou, F.: MVCNN: a deep learning-based ocean-land waveform classification network for single-wavelength LiDAR bathymetry. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 16, 656\u2013674 (2023)","journal-title":"IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens."},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Goal-oriented gaze estimation for zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3794\u20133803 (2021)","DOI":"10.1109\/CVPR46437.2021.00379"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7076\u20137086 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"25_CR17","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: International Conference on Learning Representations, ICLR (2023)"},{"key":"25_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Siddiqi, K., Zhang, J., Macrini, D., Shokoufandeh, A., Bouix, S., Dickinson, S.: Retrieving articulated 3-D models using medial surfaces. Mach. Vis. Appl. 19, 261\u2013275 (2008)","DOI":"10.1007\/s00138-007-0097-8"},{"key":"25_CR20","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912\u20131920 (2015)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5542\u20135551 (2018)","DOI":"10.1109\/CVPR.2018.00581"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Xian, Y., Sharma, S., Schiele, B., Akata, Z.: F-VAEGAN-D2: a feature generating framework for any-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10275\u201310284 (2019)","DOI":"10.1109\/CVPR.2019.01052"},{"key":"25_CR23","doi-asserted-by":"publisher","unstructured":"Xie, G.S., et al.: Region graph embedding network for zero-shot learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12349, pp. 562\u2013580. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_33","DOI":"10.1007\/978-3-030-58548-8_33"},{"key":"25_CR24","unstructured":"Xu, W., Xian, Y., Wang, J., Schiele, B., Akata, Z.: Attribute prototype network for zero-shot learning. In: Advances in Neural Information Processing Systems, pp. 21969\u201321980 (2020)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Yu, Y., Ji, Z., Han, J., Zhang, Z.: Episode-based prototype generating network for zero-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 14032\u201314041 (2020)","DOI":"10.1109\/CVPR42600.2020.01405"},{"key":"25_CR26","doi-asserted-by":"publisher","unstructured":"Zhang, J., Siddiqi, K., Macrini, D., Shokoufandeh, A., Dickinson, S.: Retrieving articulated 3-D models using medial surfaces and their graph spectra. In: Rangarajan, A., Vemuri, B., Yuille, A.L. (eds.) Proceedings of the 5th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 285\u2013300. EMMCVPR 2005. Springer, Cham (2005). https:\/\/doi.org\/10.1007\/11585978_19","DOI":"10.1007\/11585978_19"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: PointClip: point cloud understanding by clip. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8542\u20138552 (2022)","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"25_CR28","doi-asserted-by":"publisher","unstructured":"Zhao, S., et al.: Exploiting unlabeled data with vision and language models for object detection. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13669, pp. 159\u2013175. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_10","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: PointCLIP V2: prompting CLIP and GPT for powerful 3D open-world learning. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2639\u20132650. IEEE Computer Society, Los Alamitos, CA, USA, October 2023","DOI":"10.1109\/ICCV51070.2023.00249"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2061-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T06:06:07Z","timestamp":1735538767000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2061-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"ISBN":["9789819620609","9789819620616"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2061-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,31]]},"assertion":[{"value":"31 December 2024","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","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}