{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:05:17Z","timestamp":1783530317451,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037, U22B2051, U23A20383, 62176222, 62176223, 62176226, 62072386, 62072387, 62072389, 62002305, 62272401"],"award-info":[{"award-number":["U21B2037, U22B2051, U23A20383, 62176222, 62176223, 62176226, 62072386, 62072387, 62072389, 62002305, 62272401"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0118201"],"award-info":[{"award-number":["2022ZD0118201"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2022J06001"],"award-info":[{"award-number":["2022J06001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680852","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"5328-5337","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4325-6858","authenticated-orcid":false,"given":"Yansong","family":"Qu","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4139-7950","authenticated-orcid":false,"given":"Shaohui","family":"Dai","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2932-8953","authenticated-orcid":false,"given":"Xinyang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3873-3860","authenticated-orcid":false,"given":"Jianghang","family":"Lin","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7645-9606","authenticated-orcid":false,"given":"Liujuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0800-0609","authenticated-orcid":false,"given":"Shengchuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_2_1_2_1","unstructured":"Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill and et al. 2021. On the opportunities and risks of foundation models. ArXiv preprint Vol. abs\/2108.07258 (2021). https:\/\/arxiv.org\/abs\/2108.07258"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00500"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00603"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00023"},{"key":"e_1_3_2_1_10_1","first-page":"3403","article-title":"Geo-neus: Geometry-consistent neural implicit surfaces learning for multi-view reconstruction","volume":"35","author":"Fu Qiancheng","year":"2022","unstructured":"Qiancheng Fu, Qingshan Xu, Yew Soon Ong, and Wenbing Tao. 2022. Geo-neus: Geometry-consistent neural implicit surfaces learning for multi-view reconstruction. Advances in Neural Information Processing Systems, Vol. 35 (2022), 3403--3416.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"e_1_3_2_1_13_1","volume-title":"Streetsurf: Extending multi-view implicit surface reconstruction to street views. arXiv preprint arXiv:2306.04988","author":"Guo Jianfei","year":"2023","unstructured":"Jianfei Guo, Nianchen Deng, Xinyang Li, Yeqi Bai, Botian Shi, Chiyu Wang, Chenjing Ding, Dongliang Wang, and Yikang Li. 2023. Streetsurf: Extending multi-view implicit surface reconstruction to street views. arXiv preprint arXiv:2306.04988 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"e_1_3_2_1_15_1","volume-title":"Istr: End-to-end instance segmentation with transformers. arXiv preprint arXiv:2105.00637","author":"Hu Jie","year":"2021","unstructured":"Jie Hu, Liujuan Cao, Yao Lu, ShengChuan Zhang, Yan Wang, Ke Li, Feiyue Huang, Ling Shao, and Rongrong Ji. 2021. Istr: End-to-end instance segmentation with transformers. arXiv preprint arXiv:2105.00637 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01709"},{"key":"e_1_3_2_1_17_1","volume-title":"ISTR: Mask-Embedding-Based Instance Segmentation Transformer","author":"Hu Jie","year":"2024","unstructured":"Jie Hu, Yao Lu, Shengchuan Zhang, and Liujuan Cao. 2024. ISTR: Mask-Embedding-Based Instance Segmentation Transformer. IEEE Transactions on Image Processing (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"NeRF-DetS: Enhancing Multi-View 3D Object Detection with Sampling-adaptive Network of Continuous NeRF-based Representation. arXiv preprint arXiv:2404.13921","author":"Huang Chi","year":"2024","unstructured":"Chi Huang, Xinyang Li, Shengchuan Zhang, Liujuan Cao, and Rongrong Ji. 2024. NeRF-DetS: Enhancing Multi-View 3D Object Detection with Sampling-adaptive Network of Continuous NeRF-based Representation. arXiv preprint arXiv:2404.13921 (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_21_1","volume-title":"LERF: Language Embedded Radiance Fields. In International Conference on Computer Vision (ICCV).","author":"Kim Chung","year":"2023","unstructured":"Justin* Kerr, Chung Min* Kim, Ken Goldberg, Angjoo Kanazawa, and Matthew Tancik. 2023. LERF: Language Embedded Radiance Fields. In International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_23_1","first-page":"23311","article-title":"Decomposing nerf for editing via feature field distillation","volume":"35","author":"Kobayashi Sosuke","year":"2022","unstructured":"Sosuke Kobayashi, Eiichi Matsumoto, and Vincent Sitzmann. 2022. Decomposing nerf for editing via feature field distillation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23311--23330.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Language-driven Semantic Segmentation. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Li Boyi","year":"2022","unstructured":"Boyi Li, Kilian Q. Weinberger, Serge J. Belongie, Vladlen Koltun, and Ren\u00e9 Ranftl. 2022. Language-driven Semantic Segmentation. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=RriDjddCLN"},{"key":"e_1_3_2_1_25_1","volume-title":"Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion. arXiv preprint arXiv:2405.09874","author":"Li Xinyang","year":"2024","unstructured":"Xinyang Li, Zhangyu Lai, Linning Xu, Jianfei Guo, Liujuan Cao, Shengchuan Zhang, Bo Dai, and Rongrong Ji. 2024. Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion. arXiv preprint arXiv:2405.09874 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text. arXiv preprint arXiv:2406.17601","author":"Li Xinyang","year":"2024","unstructured":"Xinyang Li, Zhangyu Lai, Linning Xu, Yansong Qu, Liujuan Cao, Shengchuan Zhang, Bo Dai, and Rongrong Ji. 2024. Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text. arXiv preprint arXiv:2406.17601 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding. ArXiv preprint","author":"Liao Guibiao","year":"2024","unstructured":"Guibiao Liao, Kaichen Zhou, Zhenyu Bao, Kanglin Liu, and Qing Li. 2024. OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding. ArXiv preprint, Vol. abs\/2402.04648 (2024). https:\/\/arxiv.org\/abs\/2402.04648"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28127"},{"key":"e_1_3_2_1_29_1","first-page":"53433","article-title":"Weakly supervised 3d open-vocabulary segmentation","volume":"36","author":"Liu Kunhao","year":"2023","unstructured":"Kunhao Liu, Fangneng Zhan, Jiahui Zhang, Muyu Xu, Yingchen Yu, Abdulmotaleb El Saddik, Christian Theobalt, Eric Xing, and Shijian Lu. 2023. Weakly supervised 3d open-vocabulary segmentation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 53433--53456.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","first-page":"53433","article-title":"d. Weakly supervised 3d open-vocabulary segmentation","volume":"36","author":"Liu Kunhao","year":"2023","unstructured":"Kunhao Liu, Fangneng Zhan, Jiahui Zhang, Muyu Xu, Yingchen Yu, Abdulmotaleb El Saddik, Christian Theobalt, Eric Xing, and Shijian Lu. 2023 d. Weakly supervised 3d open-vocabulary segmentation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 53433--53456.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_32_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. ArXiv preprint Vol. abs\/2303.05499 (2023). https:\/\/arxiv.org\/abs\/2303.05499"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_13"},{"key":"e_1_3_2_1_34_1","volume-title":"Conference on Robot Learning. PMLR, 1610--1620","author":"Lu Shiyang","year":"2023","unstructured":"Shiyang Lu, Haonan Chang, Eric Pu Jing, Abdeslam Boularias, and Kostas Bekris. 2023. Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data. In Conference on Robot Learning. PMLR, 1610--1620."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_36_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), Vol. 41, 4 (2022), 1--15."},{"key":"e_1_3_2_1_37_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. ArXiv preprint Vol. abs\/2304.07193 (2023). https:\/\/arxiv.org\/abs\/2304.07193"},{"key":"e_1_3_2_1_38_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. ArXiv preprint","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. ArXiv preprint, Vol. abs\/2209.14988 (2022). https:\/\/arxiv.org\/abs\/2209.14988"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00732"},{"key":"e_1_3_2_1_40_1","volume-title":"LangSplat: 3D Language Gaussian Splatting. ArXiv preprint","author":"Qin Minghan","year":"2023","unstructured":"Minghan Qin, Wanhua Li, Jiawei Zhou, Haoqian Wang, and Hanspeter Pfister. 2023. LangSplat: 3D Language Gaussian Splatting. ArXiv preprint, Vol. abs\/2312.16084 (2023). https:\/\/arxiv.org\/abs\/2312.16084"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00104"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01407"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592426"},{"key":"e_1_3_2_1_45_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan et al. 2024. Grounded sam: Assembling open-world models for diverse visual tasks. ArXiv preprint Vol. abs\/2401.14159 (2024). https:\/\/arxiv.org\/abs\/2401.14159"},{"key":"e_1_3_2_1_46_1","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv: 2112.10752 [cs.CV]"},{"key":"e_1_3_2_1_47_1","volume-title":"Leslie Pack Kaelbling, and Phillip Isola","author":"Shen William","year":"2023","unstructured":"William Shen, Ge Yang, Alan Yu, Jansen Wong, Leslie Pack Kaelbling, and Phillip Isola. 2023. Distilled feature fields enable few-shot language-guided manipulation. ArXiv preprint, Vol. abs\/2308.07931 (2023). https:\/\/arxiv.org\/abs\/2308.07931"},{"key":"e_1_3_2_1_48_1","volume-title":"Aligning and Prompting Everything All at Once for Universal Visual Perception. ArXiv preprint","author":"Shen Yunhang","year":"2023","unstructured":"Yunhang Shen, Chaoyou Fu, Peixian Chen, Mengdan Zhang, Ke Li, Xing Sun, Yunsheng Wu, Shaohui Lin, and Rongrong Ji. 2023. Aligning and Prompting Everything All at Once for Universal Visual Perception. ArXiv preprint, Vol. abs\/2312.02153 (2023). https:\/\/arxiv.org\/abs\/2312.02153"},{"key":"e_1_3_2_1_49_1","volume-title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding. ArXiv preprint","author":"Shi Jin-Chuan","year":"1848","unstructured":"Jin-Chuan Shi, Miao Wang, Hao-Bin Duan, and Shao-Hua Guan. 2023. Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding. ArXiv preprint, Vol. abs\/2311.18482 (2023). https:\/\/arxiv.org\/abs\/2311.18482"},{"key":"e_1_3_2_1_50_1","unstructured":"Julian Straub Thomas Whelan Lingni Ma Yufan Chen Erik Wijmans Simon Green Jakob J Engel Raul Mur-Artal Carl Ren Shobhit Verma et al. 2019. The Replica dataset: A digital replica of indoor spaces. ArXiv preprint Vol. abs\/1906.05797 (2019). https:\/\/arxiv.org\/abs\/1906.05797"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"e_1_3_2_1_52_1","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Wang Peng","year":"2021","unstructured":"Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 27171--27183. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/e41e164f7485ec4a28741a2d0ea41c74-Abstract.html"},{"key":"e_1_3_2_1_53_1","first-page":"1966","article-title":"Hf-neus: Improved surface reconstruction using high-frequency details","volume":"35","author":"Wang Yiqun","year":"2022","unstructured":"Yiqun Wang, Ivan Skorokhodov, and Peter Wonka. 2022. Hf-neus: Improved surface reconstruction using high-frequency details. Advances in Neural Information Processing Systems, Vol. 35 (2022), 1966--1978.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_54_1","volume-title":"WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections. arXiv preprint arXiv:2406.02407","author":"Wang Yuze","year":"2024","unstructured":"Yuze Wang, Junyi Wang, and Yue Qi. 2024. WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections. arXiv preprint arXiv:2406.02407 (2024)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592276"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"e_1_3_2_1_57_1","volume-title":"Gaussian grouping: Segment and edit anything in 3d scenes. ArXiv preprint","author":"Ye Mingqiao","year":"2023","unstructured":"Mingqiao Ye, Martin Danelljan, Fisher Yu, and Lei Ke. 2023. Gaussian grouping: Segment and edit anything in 3d scenes. ArXiv preprint, Vol. abs\/2312.00732 (2023). https:\/\/arxiv.org\/abs\/2312.00732"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings, Part II 14","author":"Yu Licheng","year":"2016","unstructured":"Licheng Yu, Patrick Poirson, Shan Yang, Alexander C Berg, and Tamara L Berg. 2016. Modeling context in referring expressions. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part II 14. Springer, 69--85."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"e_1_3_2_1_60_1","volume-title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields. ArXiv preprint","author":"Zhou Shijie","year":"2023","unstructured":"Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, and Achuta Kadambi. 2023. Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields. ArXiv preprint, Vol. abs\/2312.03203 (2023). https:\/\/arxiv.org\/abs\/2312.03203"},{"key":"e_1_3_2_1_61_1","volume-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. In 9th International Conference on Learning Representations, ICLR 2021","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680852","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680852"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":61,"alternative-id":["10.1145\/3664647.3680852","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680852","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}