{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:05:09Z","timestamp":1765339509529,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"name":"National Science Fund for Distinguished Young Scholars","award":["No.62025603"],"award-info":[{"award-number":["No.62025603"]}]},{"name":"the National Natural Science Foundation of China","award":["No. U21B2037, No. U22B2051, No. U23A20383, No. U21A20472, No. 62176222, No. 62176223, No. 62176226, No. 62072386, No. 62072387, No. 62072389, No. 62002305, No. 62272401"],"award-info":[{"award-number":["No. U21B2037, No. U22B2051, No. U23A20383, No. U21A20472, No. 62176222, No. 62176223, No. 62176226, No. 62072386, No. 62072387, No. 62072389, No. 62002305, No. 62272401"]}]},{"name":"the Natural Science Foundation of Fujian Province of China","award":["No. 2021J06003, No.2022J06001"],"award-info":[{"award-number":["No. 2021J06003, No.2022J06001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754874","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"9444-9453","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SynergyAmodal: Deocclude Anything with Text Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2932-8953","authenticated-orcid":false,"given":"Xinyang","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5907-5749","authenticated-orcid":false,"given":"Chengjie","family":"Yi","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2820-8529","authenticated-orcid":false,"given":"JiaWei","family":"Lai","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1764-1894","authenticated-orcid":false,"given":"Mingbao","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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4325-6858","authenticated-orcid":false,"given":"Yansong","family":"Qu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Open-World Amodal Appearance Completion. ArXiv preprint","author":"Ao Jiayang","year":"2024","unstructured":"Jiayang Ao, Yanbei Jiang, Qiuhong Ke, and Krista A Ehinger. 2024a. Open-World Amodal Appearance Completion. ArXiv preprint, Vol. abs\/2411.13019 (2024). https:\/\/arxiv.org\/abs\/2411.13019"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00035"},{"key":"e_1_3_2_2_3_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. ArXiv preprint Vol. abs\/2311.15127 (2023). https:\/\/arxiv.org\/abs\/2311.15127"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00234"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827342"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_2_7_1","volume-title":"Monet: Unsupervised scene decomposition and representation. ArXiv preprint","author":"Burgess Christopher P","year":"2019","unstructured":"Christopher P Burgess, Loic Matthey, Nicholas Watters, Rishabh Kabra, Irina Higgins, Matt Botvinick, and Alexander Lerchner. 2019. Monet: Unsupervised scene decomposition and representation. ArXiv preprint, Vol. abs\/1901.11390 (2019). https:\/\/arxiv.org\/abs\/1901.11390"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00547"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00643"},{"key":"e_1_3_2_2_11_1","volume-title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations. In 8th International Conference on Learning Representations, ICLR 2020","author":"Engelcke Martin","year":"2020","unstructured":"Martin Engelcke, Adam R. Kosiorek, Oiwi Parker Jones, and Ingmar Posner. 2020. GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=BkxfaTVFwH"},{"key":"e_1_3_2_2_12_1","volume-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024a. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=FPnUhsQJ5B"},{"key":"e_1_3_2_2_13_1","volume-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024b. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=FPnUhsQJ5B"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00146"},{"key":"e_1_3_2_2_15_1","volume-title":"Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger (Eds.). 2672-2680. https:\/\/proceedings.neurips.cc\/paper\/2014\/hash\/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","volume":"2433","author":"Greff Klaus","year":"2019","unstructured":"Klaus Greff, Rapha\u00ebl Lopez Kaufman, Rishabh Kabra, Nick Watters, Christopher Burgess, Daniel Zoran, Loic Matthey, Matthew Botvinick, and Alexander Lerchner. 2019. Multi-Object Representation Learning with Iterative Variational Inference. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 2424-2433. http:\/\/proceedings.mlr.press\/v97\/greff19a.html"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_2_18_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 6626-6637. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/8a1d694707eb0fefe65871369074926d-Abstract.html"},{"key":"e_1_3_2_2_19_1","volume-title":"Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"e_1_3_2_2_20_1","volume-title":"Elucidating the Design Space of Diffusion-Based Generative Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. 2022. Elucidating the Design Space of Diffusion-Based Generative Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/a98846e9d9cc01cfb87eb694d946ce6b-Abstract-Conference.html"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_2_2_22_1","volume-title":"ZIM: Zero-Shot Image Matting for Anything. ArXiv preprint","author":"Kim Beomyoung","year":"2024","unstructured":"Beomyoung Kim, Chanyong Shin, Joonhyun Jeong, Hyungsik Jung, Se-Yun Lee, Sewhan Chun, Dong-Hyun Hwang, and Joonsang Yu. 2024. ZIM: Zero-Shot Image Matting for Anything. ArXiv preprint, Vol. abs\/2411.00626 (2024). https:\/\/arxiv.org\/abs\/2411.00626"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1023713602895"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_25_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02053"},{"key":"e_1_3_2_2_28_1","volume-title":"RORem: Training a Robust Object Remover with Human-in-the-Loop. ArXiv preprint","author":"Li Ruibin","year":"2025","unstructured":"Ruibin Li, Tao Yang, Song Guo, and Lei Zhang. 2025. RORem: Training a Robust Object Remover with Human-in-the-Loop. ArXiv preprint, Vol. abs\/2501.00740 (2025). https:\/\/arxiv.org\/abs\/2501.00740"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02148"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-016-0055-3"},{"key":"e_1_3_2_2_31_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_2_32_1","volume-title":"Variational Amodal Object Completion. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Ling Huan","year":"2020","unstructured":"Huan Ling, David Acuna, Karsten Kreis, Seung Wook Kim, and Sanja Fidler. 2020. Variational Amodal Object Completion. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/bacadc62d6e67d7897cef027fa2d416c-Abstract.html"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657409"},{"key":"e_1_3_2_2_35_1","volume-title":"TACO: Taming Diffusion for in-the-wild Video Amodal Completion. https:\/\/arxiv.org\/abs\/2503.12049","author":"Lu Ruijie","year":"2025","unstructured":"Ruijie Lu, Yixin Chen, Yu Liu, Jiaxiang Tang, Junfeng Ni, Diwen Wan, Gang Zeng, and Siyuan Huang. 2025. TACO: Taming Diffusion for in-the-wild Video Amodal Completion. https:\/\/arxiv.org\/abs\/2503.12049"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"e_1_3_2_2_38_1","volume-title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=aBsCjcPu_tE"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10246-w"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00377"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00819"},{"key":"e_1_3_2_2_42_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=FjNys5c7VyY"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00313"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00374"},{"key":"e_1_3_2_2_45_1","volume-title":"Hierarchical text-conditional image generation with clip latents. ArXiv preprint","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. ArXiv preprint, Vol. abs\/2204.06125 (2022). https:\/\/arxiv.org\/abs\/2204.06125"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. 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, 8821-8831. http:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"e_1_3_2_2_47_1","volume-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.). 91-99. https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/14bfa6bb14875e45bba028a21ed38046-Abstract.html"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_49_1","first-page":"488","volume-title":"Zurich","author":"Silberman Nathan","year":"2014","unstructured":"Nathan Silberman, Lior Shapira, Ran Gal, and Pushmeet Kohli. 2014. A contour completion model for augmenting surface reconstructions. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part III 13. Springer, 488-503."},{"key":"e_1_3_2_2_50_1","volume-title":"Denoising Diffusion Implicit Models. In 9th International Conference on Learning Representations, ICLR 2021","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02115"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"e_1_3_2_2_53_1","unstructured":"Tianhao Wu Chuanxia Zheng Frank Guan Andrea Vedaldi and Tat-Jen Cham. 2025. Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images. https:\/\/arxiv.org\/abs\/2503.13439"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00869"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00771"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02645"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00384"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157036"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01517-0"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00369"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.320"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:02:02Z","timestamp":1765339322000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754874"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":64,"alternative-id":["10.1145\/3746027.3754874","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754874","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"}}]}}