{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:24Z","timestamp":1755825024943,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"NTU","award":["113L900902 & 114L893104"],"award-info":[{"award-number":["113L900902 & 114L893104"]}]},{"name":"National Science and Technology Council, Taiwan","award":["NSTC 113-2634-F-006-002, 112-2221-E-002-182-MY3, 113-2634-F-002-003"],"award-info":[{"award-number":["NSTC 113-2634-F-006-002, 112-2221-E-002-182-MY3, 113-2634-F-002-003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733484","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"2028-2032","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6575-9987","authenticated-orcid":false,"given":"Li-Cheng","family":"Shen","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8298-7966","authenticated-orcid":false,"given":"Jih-Kang","family":"Hsieh","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8330-0491","authenticated-orcid":false,"given":"Wei-Hua","family":"Li","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2959-2471","authenticated-orcid":false,"given":"Chu-Song","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966."},{"key":"e_1_3_2_1_2_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. 2025. Qwen2.5-VL Technical Report. arXiv:2502.13923."},{"key":"e_1_3_2_1_3_1","volume-title":"Piotr Dollar, and C. Lawrence Zitnick","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollar, and C. Lawrence Zitnick. 2015. Microsoft COCO Captions: Data Collection and Evaluation Server. arXiv:1504.00325."},{"key":"e_1_3_2_1_4_1","volume-title":"UNITER: UNiversal Image-TExt Representation Learning. In European Conference on Computer Vision. Springer-Verlag","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. UNITER: UNiversal Image-TExt Representation Learning. In European Conference on Computer Vision. Springer-Verlag, Berlin, Heidelberg, 104--120."},{"key":"e_1_3_2_1_5_1","volume-title":"Open-Vocabulary Panoptic Segmentation Using Bert Pre-Training of Vision-Language Multiway Transformer Model. In 2024 IEEE International Conference on Image Processing (ICIP). 2494--2500","author":"Chen Yi-Chia","year":"2024","unstructured":"Yi-Chia Chen, Wei-Hua Li, and Chu-Song Chen. 2024a. Open-Vocabulary Panoptic Segmentation Using Bert Pre-Training of Vision-Language Multiway Transformer Model. In 2024 IEEE International Conference on Image Processing (ICIP). 2494--2500."},{"key":"e_1_3_2_1_6_1","volume-title":"European Conference on Computer Vision, Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.). Springer Nature Switzerland, Cham, 323--340","author":"Chen Yi-Chia","year":"2024","unstructured":"Yi-Chia Chen, Wei-Hua Li, Cheng Sun, Yu-Chiang Frank Wang, and Chu-Song Chen. 2024b. SAM4MLLM: Enhance Multi-Modal Large Language Model for\u00a0Referring Expression Segmentation. In European Conference on Computer Vision, Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.). Springer Nature Switzerland, Cham, 323--340."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"volume-title":"VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference.","author":"Faghri Fartash","key":"e_1_3_2_1_8_1","unstructured":"Fartash Faghri, David J. Fleet, J. Kiros, and S. Fidler. 2018. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference."},{"key":"e_1_3_2_1_9_1","volume-title":"Marc' Aurelio Ranzato, and Tomas Mikolov","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc' Aurelio Ranzato, and Tomas Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In Advances in Neural Information Processing Systems, Vol. 26. Curran Associates, Inc."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In Proceedings of the 38th International Conference on Machine Learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning. PMLR, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In Proceedings of the 38th International Conference on Machine Learning. PMLR, 5583--5594."},{"key":"e_1_3_2_1_13_1","volume-title":"Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4015--4026","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick. 2023. Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4015--4026."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"e_1_3_2_1_15_1","volume-title":"Stacked Cross Attention for Image-Text Matching. In European Conference on Computer Vision. Springer-Verlag","author":"Lee Kuang-Huei","year":"2018","unstructured":"Kuang-Huei Lee, Xi Chen, Gang Hua, Houdong Hu, and Xiaodong He. 2018. Stacked Cross Attention for Image-Text Matching. In European Conference on Computer Vision. Springer-Verlag, Berlin, Heidelberg, 212--228."},{"key":"e_1_3_2_1_16_1","volume-title":"Object-Centric Open-Vocabulary Image Retrieval with Aggregated Features. In British Machine Vision Conference.","author":"Levi Hila","year":"2023","unstructured":"Hila Levi, Guy Heller, Dan Levi, and Ethan Fetaya. 2023. Object-Centric Open-Vocabulary Image Retrieval with Aggregated Features. In British Machine Vision Conference."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_18_1","volume-title":"Universal Multimodal Retrieval with Multimodal LLMs. In The Thirteenth International Conference on Learning Representations.","author":"Lin Sheng-Chieh","year":"2025","unstructured":"Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi, Jimmy Lin, Bryan Catanzaro, and Wei Ping. 2025. Universal Multimodal Retrieval with Multimodal LLMs. In The Thirteenth International Conference on Learning Representations."},{"volume-title":"European Conference on Computer Vision, David Fleet, Tomas Pajdla","author":"Lin Tsung-Yi","key":"e_1_3_2_1_19_1","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 European Conference on Computer Vision, David Fleet, Tomas Pajdla, Bernt Schiele, and Tinne Tuytelaars (Eds.). Springer International Publishing, Cham, 740--755."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"e_1_3_2_1_21_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning. PMLR, 8748--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. PMLR, 8748--8763."},{"key":"e_1_3_2_1_26_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Ravi Nikhila","year":"2025","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 Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollar, and Christoph Feichtenhofer. 2025. SAM 2: Segment Anything in Images and Videos. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01253"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00248"},{"key":"e_1_3_2_1_31_1","first-page":"79095","article-title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","volume":"36","author":"Xie Chi","year":"2023","unstructured":"Chi Xie, Zhao Zhang, Yixuan Wu, Feng Zhu, Rui Zhao, and Shuang Liang. 2023. Described Object Detection: Liberating Object Detection with Flexible Expressions. In Advances in Neural Information Processing Systems, Vol. 36. 79095--79107.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"e_1_3_2_1_33_1","volume-title":"LISA: An Improved Baseline for Reasoning Segmentation with Large Language Model. arXiv:2312.17240.","author":"Yang Senqiao","year":"2024","unstructured":"Senqiao Yang, Tianyuan Qu, Xin Lai, Zhuotao Tian, Bohao Peng, Shu Liu, and Jiaya Jia. 2024. LISA: An Improved Baseline for Reasoning Segmentation with Large Language Model. arXiv:2312.17240."},{"key":"e_1_3_2_1_34_1","article-title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research (July 2022).","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_2_1_35_1","volume-title":"Berg","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 European Conference on Computer Vision, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International Publishing, Cham, 69--85."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:05:41Z","timestamp":1755749141000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733484"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":37,"alternative-id":["10.1145\/3731715.3733484","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733484","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}