{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:07:16Z","timestamp":1742944036218,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819743988"},{"type":"electronic","value":"9789819743995"}],"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\/978-981-97-4399-5_15","type":"book-chapter","created":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T16:01:52Z","timestamp":1720281712000},"page":"153-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DiffMoCa: Diffusion Model Based Multi-modality Cut and\u00a0Paste"],"prefix":"10.1007","author":[{"given":"Junjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaojin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fusheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,7]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","key":"15_CR1","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"15_CR2","first-page":"2672","volume":"27","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural. Inf. Process. Syst. 27, 2672\u20132680 (2014)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)","key":"15_CR3"},{"unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)","key":"15_CR4"},{"doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","key":"15_CR5","DOI":"10.1109\/CVPR.2019.00453"},{"doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","key":"15_CR6","DOI":"10.1109\/CVPR42600.2020.00813"},{"doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.\u00a01\u20138. IEEE (2018)","key":"15_CR7","DOI":"10.1109\/IROS.2018.8594049"},{"issue":"1","key":"15_CR8","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from RGB-D data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","key":"15_CR9","DOI":"10.1109\/CVPR.2018.00102"},{"doi-asserted-by":"crossref","unstructured":"Qi, L., Jiang, L., Liu, S., Shen, X., Jia, J.: Amodal instance segmentation with KINS dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3014\u20133023 (2019)","key":"15_CR10","DOI":"10.1109\/CVPR.2019.00313"},{"unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)","key":"15_CR11"},{"doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","key":"15_CR12","DOI":"10.1109\/CVPR52688.2022.01042"},{"unstructured":"Rout, L., Raoof, N., Daras, G., Caramanis, C., Dimakis, A., Shakkottai, S.: Solving linear inverse problems provably via posterior sampling with latent diffusion models. Adv. Neural Inf. Process. Syst. 36 (2024)","key":"15_CR13"},{"doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Zhou, Y., Tuzel, O.: MVX-Net: multimodal VoxelNet for 3d object detection. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7276\u20137282. IEEE (2019)","key":"15_CR14","DOI":"10.1109\/ICRA.2019.8794195"},{"unstructured":"Tong, W., et al.: 3d data augmentation for driving scenes on camera. arXiv preprint arXiv:2303.10340 (2023)","key":"15_CR15"},{"doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: PointPainting: sequential fusion for 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134612 (2020)","key":"15_CR16","DOI":"10.1109\/CVPR42600.2020.00466"},{"doi-asserted-by":"crossref","unstructured":"Wang, Z., Jia, K.: Frustum ConvNet: sliding frustums to aggregate local point-wise features for amodal 3d object detection. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1742\u20131749. IEEE (2019)","key":"15_CR17","DOI":"10.1109\/IROS40897.2019.8968513"},{"doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","key":"15_CR18","DOI":"10.1109\/ICCV51070.2023.00355"},{"unstructured":"Zhang, W., Wang, Z., Loy, C.C.: Exploring data augmentation for multi-modality 3d object detection. arXiv preprint arXiv:2012.12741 (2020)","key":"15_CR19"},{"unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492 (2019)","key":"15_CR20"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-4399-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T16:04:02Z","timestamp":1720281842000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-4399-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819743988","9789819743995"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-4399-5_15","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":"7 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISNN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Weihai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"11 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isnn2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/isnn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}