{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:06:03Z","timestamp":1784228763178,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science Foundation","award":["IIS-2404180"],"award-info":[{"award-number":["IIS-2404180"]}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["2022-0-00871"],"award-info":[{"award-number":["2022-0-00871"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811186","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MAOAM: Unified Object and Material Selection with Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1901-4157","authenticated-orcid":false,"given":"Jaden","family":"Park","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, Madison, Wisconsin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6219-3747","authenticated-orcid":false,"given":"Valentin","family":"Deschaintre","sequence":"additional","affiliation":[{"name":"Adobe Research, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5099-8145","authenticated-orcid":false,"given":"Jason","family":"Kuen","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0187-4602","authenticated-orcid":false,"given":"Kangning","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe, San Jose, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9655-2138","authenticated-orcid":false,"given":"Iliyan","family":"Georgiev","sequence":"additional","affiliation":[{"name":"Adobe Research, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8066-6835","authenticated-orcid":false,"given":"Krishna Kumar","family":"Singh","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9863-1270","authenticated-orcid":false,"given":"Yong Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA and University of Wisconsin-Madison, Madison, Wisconsin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2610-4831","authenticated-orcid":false,"given":"Michael","family":"Fischer","sequence":"additional","affiliation":[{"name":"Adobe Research, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et\u00a0al. 2025a. Qwen3-vl technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.13923 (2025)."},{"key":"e_1_3_3_2_3_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang Humen Zhong Yuanzhi Zhu Mingkun Yang Zhaohai Li Jianqiang Wan Pengfei Wang Wei Ding Zheren Fu Yiheng Xu Jiabo Ye Xi Zhang Tianbao Xie Zesen Cheng Hang Zhang Zhibo Yang Haiyang Xu and Junyang Lin. 2025b. Qwen2.5-VL Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.13923 (2025)."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"e_1_3_3_2_5_1","unstructured":"Mu Cai Reuben Tan Jianrui Zhang Bocheng Zou Kai Zhang Feng Yao Fangrui Zhu Jing Gu Yiwu Zhong Yuzhang Shang Yao Dou Jaden Park Jianfeng Gao Yong\u00a0Jae Lee and Jianwei Yang. 2024b. TemporalBench: Towards Fine-grained Temporal Understanding for Multimodal Video Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.10818 (2024)."},{"key":"e_1_3_3_2_6_1","unstructured":"Nicolas Carion Laura Gustafson Yuan-Ting Hu Shoubhik Debnath Ronghang Hu Didac Suris Chaitanya Ryali Kalyan\u00a0Vasudev Alwala Haitham Khedr Andrew Huang Jie Lei Tengyu Ma Baishan Guo Arpit Kalla Markus Marks Joseph Greer Meng Wang Peize Sun Roman R\u00e4dle Triantafyllos Afouras Effrosyni Mavroudi Katherine Xu Tsung-Han Wu Yu Zhou Liliane Momeni Rishi Hazra Shuangrui Ding Sagar Vaze Francois Porcher Feng Li Siyuan Li Aishwarya Kamath Ho\u00a0Kei Cheng Piotr Doll\u00e1r Nikhila Ravi Kate Saenko Pengchuan Zhang and Christoph Feichtenhofer. 2025. SAM 3: Segment Anything with Concepts. arxiv:https:\/\/arXiv.org\/abs\/2511.16719\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2511.16719"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_3_2_9_1","unstructured":"Bowen Cheng Alex Schwing and Alexander Kirillov. 2021. Per-pixel classification is not all you need for semantic segmentation. Advances in neural information processing systems 34 (2021) 17864\u201317875."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","unstructured":"Valentin Deschaintre Julia Guerrero-Viu Diego Gutierrez Tamy Boubekeur and Belen Masia. 2023. The Visual Language of Fabrics. ACM Trans. Graph. 42 4 Article 50 (jul 2023) 15\u00a0pages. 10.1145\/3592391","DOI":"10.1145\/3592391"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV69130.2026.00172"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"J. Guerrero-Viu M. Fischer I. Georgiev E. Garces D. Gutierrez B. Masia and V. Deschaintre. 2025. Fine-Grained Spatially Varying Material Selection in Images. ACM Transactions on Graphics (Proc. SIGGRAPH Asia) (2025).","DOI":"10.1145\/3763332"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00872"},{"key":"e_1_3_3_2_14_1","unstructured":"Shiu-hong Kao Yu-Wing Tai and Chi-Keung Tang. 2025. Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.07503 (2025)."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"crossref","unstructured":"Lei Ke Mingqiao Ye Martin Danelljan Yu-Wing Tai Chi-Keung Tang Fisher Yu et\u00a0al. 2023. Segment anything in high quality. Advances in Neural Information Processing Systems 36 (2023) 29914\u201329934.","DOI":"10.52202\/075280-1303"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023a. Segment Anything. arXiv:https:\/\/arXiv.org\/abs\/2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"e_1_3_3_2_20_1","unstructured":"Yuqi Liu Bohao Peng Zhisheng Zhong Zihao Yue Fanbin Lu Bei Yu and Jiaya Jia. 2025. Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.06520 (2025)."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","unstructured":"Shervin Minaee Yuri Boykov Fatih Porikli Antonio Plaza Nasser Kehtarnavaz and Demetri Terzopoulos. 2022. Image Segmentation Using Deep Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 7 (2022). 10.1109\/TPAMI.2021.3059968","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00374"},{"key":"e_1_3_3_2_26_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"e_1_3_3_2_28_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson Eric Mintun Junting Pan Kalyan\u00a0Vasudev Alwala Nicolas Carion Chao-Yuan Wu Ross Girshick Piotr Doll\u00e1r and Christoph Feichtenhofer. 2024. SAM 2: Segment Anything in Images and Videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.00714 (2024). https:\/\/arxiv.org\/abs\/2408.00714"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","unstructured":"Prafull Sharma Julien Philip Micha\u00ebl Gharbi Bill Freeman Fredo Durand and Valentin Deschaintre. 2023. Materialistic: Selecting Similar Materials in Images. ACM Trans. Graph. 42 4 Article 154 (jul 2023). 10.1145\/3592390","DOI":"10.1145\/3592390"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02087"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Zou Xueyan Zi-Yi Dou Jianwei Yang Zhe Gan Linjie Li Chunyuan Li Xiyang Dai Jianfeng Wang Lu Yuan Nanyun Peng Lijuan Wang Yong\u00a0Jae Lee and Jianfeng Gao. 2023a. Generalized Decoding for Pixel Image and Language. CVPR (2023).","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Zou Xueyan Jianwei Yang Hao Zhang Feng Li Linjie Li Jianfeng Wang Lijuan Wang Jianfeng Gao and Yong\u00a0Jae Lee. 2023b. Segment Everything Everywhere All at Once. NeurIPS (2023).","DOI":"10.52202\/075280-0868"},{"key":"e_1_3_3_2_34_1","unstructured":"Jianwei Yang Hao Zhang Feng Li Xueyan Zou Chunyuan Li and Jianfeng Gao. 2023. Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.11441 (2023)."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Jingfeng Yao Xinggang Wang Shusheng Yang and Baoyuan Wang. 2024. Vitmatte: Boosting image matting with pre-trained plain vision transformers. Information Fusion 103 (2024) 102091.","DOI":"10.1016\/j.inffus.2023.102091"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_3_2_37_1","unstructured":"Haobo Yuan Xiangtai Li Tao Zhang Yueyi Sun Zilong Huang Shilin Xu Shunping Ji Yunhai Tong Lu Qi Jiashi Feng et\u00a0al. 2025. Sa2va: Marrying sam2 with llava for dense grounded understanding of images and videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.04001 (2025)."},{"key":"e_1_3_3_2_38_1","unstructured":"Yuxuan Zhang Tianheng Cheng Lianghui Zhu Rui Hu Lei Liu Heng Liu Longjin Ran Xiaoxin Chen Wenyu Liu and Xinggang Wang. 2024. Evf-sam: Early vision-language fusion for text-prompted segment anything model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.20076 (2024)."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3799902.3811186","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:19:12Z","timestamp":1784225952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811186"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":38,"alternative-id":["10.1145\/3799902.3811186","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811186","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}