{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:24:55Z","timestamp":1780392295920,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62302415"],"award-info":[{"award-number":["62302415"]}]},{"DOI":"10.13039\/501100010040","name":"Taishan Scholar Project of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202306079"],"award-info":[{"award-number":["tsqn202306079"]}],"id":[{"id":"10.13039\/501100010040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471278"],"award-info":[{"award-number":["62471278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2022A1515110692, 2024A1515012822"],"award-info":[{"award-number":["2022A1515110692, 2024A1515012822"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755151","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"9822-9831","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2249-3264","authenticated-orcid":false,"given":"Xiufeng","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2939-4686","authenticated-orcid":false,"given":"Ka Chun","family":"Cheung","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center, NVIDIA, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0972-4008","authenticated-orcid":false,"given":"Runmin","family":"Cong","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4958-9237","authenticated-orcid":false,"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center, NVIDIA, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0161-0367","authenticated-orcid":false,"given":"Renjie","family":"Wan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_2_2_2_1","volume-title":"Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images. arXiv preprint arXiv:2403.14627","author":"Chen Yuedong","year":"2024","unstructured":"Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, and Jianfei Cai. 2024. Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images. arXiv preprint arXiv:2403.14627 (2024)."},{"key":"e_1_3_2_2_3_1","volume-title":"V3d: Video diffusion models are effective 3d generators. arXiv preprint arXiv:2403.06738","author":"Chen Zilong","year":"2024","unstructured":"Zilong Chen, YikaiWang, FengWang, ZhengyiWang, and Huaping Liu. 2024. V3d: Video diffusion models are effective 3d generators. arXiv preprint arXiv:2403.06738 (2024)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_2_2_5_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR) (2021)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_8_1","volume-title":"Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems NeurIPS (2020)."},{"key":"e_1_3_2_2_9_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Hong Yicong","year":"2023","unstructured":"Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2023. LRM: Large Reconstruction Model for Single Image to 3D. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_10_1","volume-title":"European Conference on Computer Vision. Springer, 438--454","author":"Wan Renjie","year":"2024","unstructured":"Xiufeng Huang, Ka Chun Cheung, Simon See, and Renjie Wan. 2024. Geometrysticker: Enabling ownership claim of recolorized neural radiance fields. In European Conference on Computer Vision. Springer, 438--454."},{"key":"e_1_3_2_2_11_1","first-page":"33037","article-title":"Gaussianmarker: Uncertainty-aware copyright protection of 3d gaussian splatting","volume":"37","author":"Wan Renjie","year":"2024","unstructured":"Xiufeng Huang, Ruiqi Li, Yiu-ming Cheung, Ka Chun Cheung, Simon See, and Renjie Wan. 2024. Gaussianmarker: Uncertainty-aware copyright protection of 3d gaussian splatting. Advances in Neural Information Processing Systems 37 (2024), 33037--33060.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_12_1","volume-title":"Mv-adapter: Multi-view consistent image generation made easy. arXiv preprint arXiv:2412.03632","author":"Huang Zehuan","year":"2024","unstructured":"Zehuan Huang, Yuan-Chen Guo, Haoran Wang, Ran Yi, Lizhuang Ma, Yan-Pei Cao, and Lu Sheng. 2024. Mv-adapter: Multi-view consistent image generation made easy. arXiv preprint arXiv:2412.03632 (2024)."},{"key":"e_1_3_2_2_13_1","volume-title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics (ToG)","author":"Kerbl Bernhard","year":"2023","unstructured":"Bernhard Kerbl, Georgios Kopanas, Thomas Leimk\u00fchler, and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics (ToG) (2023)."},{"key":"e_1_3_2_2_14_1","volume-title":"Neural point catacaustics for novel-view synthesis of reflections. ACM Transactions on Graphics (TOG)","author":"Kopanas Georgios","year":"2022","unstructured":"Georgios Kopanas, Thomas Leimk\u00fchler, Gilles Rainer, Cl\u00e9ment Jambon, and George Drettakis. 2022. Neural point catacaustics for novel-view synthesis of reflections. ACM Transactions on Graphics (TOG) (2022)."},{"key":"e_1_3_2_2_15_1","volume-title":"European Conference on Computer Vision (ECCV).","author":"Leroy Vincent","year":"2024","unstructured":"Vincent Leroy, Yohann Cabon, and J\u00e9r\u00f4me Revaud. 2024. Grounding Image Matching in 3D with MASt3R. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_16_1","first-page":"87934","article-title":"Variational multi-scale representation for estimating uncertainty in 3d gaussian splatting","volume":"37","author":"Li Ruiqi","year":"2024","unstructured":"Ruiqi Li and Yiu-ming Cheung. 2024. Variational multi-scale representation for estimating uncertainty in 3d gaussian splatting. Advances in Neural Information Processing Systems 37 (2024), 87934--87958.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00126"},{"key":"e_1_3_2_2_18_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Wan Renjie","year":"2023","unstructured":"Ziyuan Luo, Qing Guo, Ka Chun Cheung, Simon See, and Renjie Wan. 2023. CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_2_20_1","volume-title":"The nerf signature: Codebook-aided watermarking for neural radiance fields","author":"Luo Ziyuan","year":"2025","unstructured":"Ziyuan Luo, Anderson Rocha, Boxin Shi, Qing Guo, Haoliang Li, and Renjie Wan. 2025. The nerf signature: Codebook-aided watermarking for neural radiance fields. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_2_2_22_1","volume-title":"Ravi Ramamoorthi, Ren Ng, and Abhishek Kar.","author":"Mildenhall Ben","year":"2019","unstructured":"Ben Mildenhall, Pratul P Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, and Abhishek Kar. 2019. Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM Transactions on Graphics (ToG) (2019)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_2_24_1","volume-title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. ACM Transactions on Graphics (ToG)","author":"M\u00fcller Thomas","year":"2022","unstructured":"Thomas M\u00fcller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. ACM Transactions on Graphics (ToG) (2022)."},{"key":"e_1_3_2_2_25_1","volume-title":"ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field. In The Conference on Artificial Intelligence (AAAI).","author":"Ni Zhangkai","year":"2024","unstructured":"Zhangkai Ni, Peiqi Yang, Wenhan Yang, Hanli Wang, Lin Ma, and Sam Kwong. 2024. ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field. In The Conference on Artificial Intelligence (AAAI)."},{"key":"e_1_3_2_2_26_1","volume-title":"Point-e: A system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751","author":"Nichol Alex","year":"2022","unstructured":"Alex Nichol, Heewoo Jun, Prafulla Dhariwal, Pamela Mishkin, and Mark Chen. 2022. Point-e: A system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751 (2022)."},{"key":"e_1_3_2_2_27_1","volume-title":"U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection. Pattern Recognition","author":"Qin Xuebin","year":"2020","unstructured":"Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar Zaiane, and Martin Jagersand. 2020. U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection. Pattern Recognition (2020)."},{"key":"e_1_3_2_2_28_1","volume-title":"Vision Transformers for Dense Prediction. ArXiv preprint","author":"Ranftl Ren\u00e9","year":"2021","unstructured":"Ren\u00e9 Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. 2021. Vision Transformers for Dense Prediction. ArXiv preprint (2021)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_30_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems (NeurIPS) (2022)."},{"key":"e_1_3_2_2_31_1","volume-title":"Zero123: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110","author":"Shi Ruoxi","year":"2023","unstructured":"Ruoxi Shi, Hansheng Chen, Zhuoyang Zhang, Minghua Liu, Chao Xu, Xinyue Wei, Linghao Chen, Chong Zeng, and Hao Su. 2023. Zero123: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)."},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Shi Ruoxi","year":"2024","unstructured":"Ruoxi Shi, XinyueWei, ChengWang, and Hao Su. 2024. ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_33_1","volume-title":"Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512","author":"Shi Yichun","year":"2023","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, and Xiao Yang. 2023. Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512 (2023)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1179352.1141964"},{"key":"e_1_3_2_2_35_1","first-page":"119361","article-title":"Geometry cloak: Preventing tgs-based 3d reconstruction from copyrighted images","volume":"37","author":"Wan Renjie","year":"2024","unstructured":"Qi Song, Ziyuan Luo, Ka Chun Cheung, Simon See, and Renjie Wan. 2024. Geometry cloak: Preventing tgs-based 3d reconstruction from copyrighted images. Advances in Neural Information Processing Systems 37 (2024), 119361--119385.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of European Conference on Computer Vision (ECCV).","author":"Wan Renjie","year":"2024","unstructured":"Qi Song, Ziyuan Luo, Ka Chun Cheung, Simon See, and Renjie Wan. 2024. Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model. In Proceedings of European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"e_1_3_2_2_38_1","volume-title":"Ba-net: Dense bundle adjustment network. arXiv preprint arXiv:1806.04807","author":"Tang Chengzhou","year":"2018","unstructured":"Chengzhou Tang and Ping Tan. 2018. Ba-net: Dense bundle adjustment network. arXiv preprint arXiv:1806.04807 (2018)."},{"key":"e_1_3_2_2_39_1","volume-title":"European Conference on Computer Vision (ECCV).","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Zhaoxi Chen, Xiaokang Chen, Tengfei Wang, Gang Zeng, and Ziwei Liu. 2024. LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_40_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2024. Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_41_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems NeurIPS","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems NeurIPS (2017)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"e_1_3_2_2_43_1","volume-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation. arXiv preprint arXiv:2312.02201","author":"Wang Peng","year":"2023","unstructured":"Peng Wang and Yichun Shi. 2023. Imagedream: Image-prompt multi-view diffusion for 3d generation. arXiv preprint arXiv:2312.02201 (2023)."},{"key":"e_1_3_2_2_44_1","volume-title":"Pf-lrm: Pose-free large reconstruction model for joint pose and shape prediction. arXiv preprint arXiv:2311.12024","author":"Wang Peng","year":"2023","unstructured":"Peng Wang, Hao Tan, Sai Bi, Yinghao Xu, Fujun Luan, Kalyan Sunkavalli, Wenping Wang, Zexiang Xu, and Kai Zhang. 2023. Pf-lrm: Pose-free large reconstruction model for joint pose and shape prediction. arXiv preprint arXiv:2311.12024 (2023)."},{"key":"e_1_3_2_2_45_1","volume-title":"IBRNet: Learning Multi-View Image-Based Rendering. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Wang Qianqian","year":"2021","unstructured":"Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul Srinivasan, Howard Zhou, Jonathan T. Barron, Ricardo Martin-Brualla, Noah Snavely, and Thomas Funkhouser. 2021. IBRNet: Learning Multi-View Image-Based Rendering. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01037"},{"key":"e_1_3_2_2_48_1","volume-title":"European Conference on Computer Vision. Springer, 143--163","author":"Xu Chao","year":"2024","unstructured":"Chao Xu, Ang Li, Linghao Chen, Yulin Liu, Ruoxi Shi, Hao Su, and Minghua Liu. 2024. Sparp: Fast 3d object reconstruction and pose estimation from sparse views. In European Conference on Computer Vision. Springer, 143--163."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"e_1_3_2_2_50_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Xu Yinghao","year":"2024","unstructured":"Yinghao Xu, Zifan Shi, Wang Yifan, Sida Peng, Ceyuan Yang, Yujun Shen, and Wetzstein Gordon. 2024. GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation. European Conference on Computer Vision (ECCV) (2024)."},{"key":"e_1_3_2_2_51_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Xu Yinghao","year":"2024","unstructured":"Yinghao Xu, Hao Tan, Fujun Luan, Sai Bi, PengWang, Jiahao Li, Zifan Shi, Kalyan Sunkavalli, Gordon Wetzstein, Zexiang Xu, et al. 2024. Dmv3d: Denoising multiview diffusion using 3d large reconstruction model. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_52_1","volume-title":"No pose, no problem: Surprisingly simple 3d gaussian splats from sparse unposed images. arXiv preprint arXiv:2410.24207","author":"Ye Botao","year":"2024","unstructured":"Botao Ye, Sifei Liu, Haofei Xu, Xueting Li, Marc Pollefeys, Ming-Hsuan Yang, and Songyou Peng. 2024. No pose, no problem: Surprisingly simple 3d gaussian splats from sparse unposed images. arXiv preprint arXiv:2410.24207 (2024)."},{"key":"e_1_3_2_2_53_1","volume-title":"Differentiable surface splatting for point-based geometry processing. ACM Transactions on Graphics (TOG)","author":"Yifan Wang","year":"2019","unstructured":"Wang Yifan, Felice Serena, Shihao Wu, Cengiz \u00d6ztireli, and Olga Sorkine- Hornung. 2019. Differentiable surface splatting for point-based geometry processing. ACM Transactions on Graphics (TOG) (2019)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_2_55_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Zhang Kai","year":"2024","unstructured":"Kai Zhang, Sai Bi, Hao Tan, Yuanbo Xiangli, Nanxuan Zhao, Kalyan Sunkavalli, and Zexiang Xu. 2024. GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting. European Conference on Computer Vision (ECCV) (2024)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2001.964490"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:56:48Z","timestamp":1765310208000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755151","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755151","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}