{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:15:17Z","timestamp":1783696517564,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"name":"New Generation Artificial Intelligence-National Science and Technology Major Project","award":["2025ZD0123301"],"award-info":[{"award-number":["2025ZD0123301"]}]},{"name":"the National Natural Science Foundation of China (NSFC)","award":["62302486"],"award-info":[{"award-number":["62302486"]}]},{"name":"the National Natural Science Foundation of China (NSFC)","award":["62441229"],"award-info":[{"award-number":["62441229"]}]},{"name":"the Innovation Project of ICT CAS","award":["E361140"],"award-info":[{"award-number":["E361140"]}]},{"name":"the Strategic Priority Research Program of the CAS","award":["XDB0680102"],"award-info":[{"award-number":["XDB0680102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809695","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"156-166","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3768-714X","authenticated-orcid":false,"given":"Jiahan","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0345-7771","authenticated-orcid":false,"given":"Da","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1144-1298","authenticated-orcid":false,"given":"Hengran","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7869-8213","authenticated-orcid":false,"given":"Yinqiong","family":"Cai","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1246-1740","authenticated-orcid":false,"given":"Lixin","family":"Su","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4926-3357","authenticated-orcid":false,"given":"Daiting","family":"Shi","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-4999","authenticated-orcid":false,"given":"Keping","family":"Bi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katie Millican Malcolm Reynolds Roman Ring Eliza Rutherford Serkan Cabi Tengda Han Zhitao Gong Sina Samangooei Marianne Monteiro Jacob Menick Sebastian Borgeaud Andrew Brock Aida Nematzadeh Sahand Sharifzadeh Mikolaj Binkowski Ricardo Barreira Oriol Vinyals Andrew Zisserman and Karen Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. arXiv:2204.14198 [cs.CV] https:\/\/arxiv.org\/abs\/2204.14198","DOI":"10.52202\/068431-1723"},{"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 [cs.CV] https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_3_1","unstructured":"Parishad BehnamGhader Vaibhav Adlakha Marius Mosbach Dzmitry Bahdanau Nicolas Chapados and Siva Reddy. 2024. LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders. arXiv:2404.05961 [cs.CL] https:\/\/arxiv.org\/abs\/2404.05961"},{"key":"e_1_3_2_1_4_1","unstructured":"Ali Borji. 2020. ObjectNet Dataset: Reanalysis and Correction. arXiv:2004.02042 [cs.CV] https:\/\/arxiv.org\/abs\/2004.02042"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Yingshan Chang Mridu Narang Hisami Suzuki Guihong Cao Jianfeng Gao and Yonatan Bisk. 2022. WebQA: Multihop and Multimodal QA. arXiv:2109.00590 [cs.CL] https:\/\/arxiv.org\/abs\/2109.00590","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"e_1_3_2_1_7_1","unstructured":"Haonan Chen Hong Liu Yuping Luo Liang Wang Nan Yang Furu Wei and Zhicheng Dou. 2025. MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings. arXiv:2506.23115 [cs.CV] https:\/\/arxiv.org\/abs\/2506.23115"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Haonan Chen Liang Wang Nan Yang Yutao Zhu Ziliang Zhao Furu Wei and Zhicheng Dou. 2025. mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data. arXiv:2502.08468 [cs.CV] https:\/\/arxiv.org\/abs\/2502.08468","DOI":"10.18653\/v1\/2025.findings-acl.433"},{"key":"e_1_3_2_1_9_1","unstructured":"Jiahan Chen Da Li and Keping Bi. 2025. LifeIR at the NTCIR-18 Lifelog-6 Task. arXiv:2505.20987 [cs.IR] https:\/\/arxiv.org\/abs\/2505.20987"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Yan Fang Jingtao Zhan Qingyao Ai Jiaxin Mao Weihang Su Jia Chen and Yiqun Liu. 2024. Scaling Laws For Dense Retrieval. arXiv:2403.18684 [cs.IR] https:\/\/arxiv.org\/abs\/2403.18684","DOI":"10.1145\/3626772.3657743"},{"key":"e_1_3_2_1_11_1","unstructured":"Manuel Faysse Hugues Sibille Tony Wu Bilel Omrani Gautier Viaud C\u00e9line Hudelot and Pierre Colombo. 2025. ColPali: Efficient Document Retrieval with Vision Language Models. arXiv:2407.01449 [cs.IR] https:\/\/arxiv.org\/abs\/2407.01449"},{"key":"e_1_3_2_1_12_1","unstructured":"Tiancheng Gu Kaicheng Yang Ziyong Feng Xingjun Wang Yanzhao Zhang Dingkun Long Yingda Chen Weidong Cai and Jiankang Deng. 2025. Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs. arXiv:2504.17432 [cs.CV] https:\/\/arxiv.org\/abs\/2504.17432"},{"key":"e_1_3_2_1_13_1","unstructured":"Tiancheng Gu Kaicheng Yang Kaichen Zhang Xiang An Ziyong Feng Yueyi Zhang Weidong Cai Jiankang Deng and Lidong Bing. 2025. UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning. arXiv:2510.13515 [cs.CV] https:\/\/arxiv.org\/abs\/2510.13515"},{"key":"e_1_3_2_1_14_1","unstructured":"Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Doll\u00e1r and Ross Girshick. 2021. Masked Autoencoders Are Scalable Vision Learners. arXiv:2111.06377 [cs.CV] https:\/\/arxiv.org\/abs\/2111.06377"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.181"},{"key":"e_1_3_2_1_16_1","unstructured":"Ting Jiang Minghui Song Zihan Zhang Haizhen Huang Weiwei Deng Feng Sun Qi Zhang Deqing Wang and Fuzhen Zhuang. 2024. E5-V: Universal Embeddings with Multimodal Large Language Models. arXiv:2407.12580 [cs.CL] https:\/\/arxiv.org\/abs\/2407.12580"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Ziyan Jiang Rui Meng Xinyi Yang Semih Yavuz Yingbo Zhou and Wenhu Chen. 2025. VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks. arXiv:2410.05160 [cs.CV] https:\/\/arxiv.org\/abs\/2410.05160","DOI":"10.36227\/techrxiv.175624545.56457516\/v1"},{"key":"e_1_3_2_1_18_1","unstructured":"Zhibin Lan Liqiang Niu Fandong Meng Jie Zhou and Jinsong Su. 2025. LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning. arXiv:2503.04812 [cs.CV] https:\/\/arxiv.org\/abs\/2503.04812"},{"key":"e_1_3_2_1_19_1","unstructured":"Da Li Yuxiao Luo Keping Bi Jiafeng Guo Wei Yuan Biao Yang Yan Wang Fan Yang Tingting Gao and Guorui Zhou. 2026. Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding. arXiv:2511.08480 [cs.CV] https:\/\/arxiv.org\/abs\/2511.08480"},{"key":"e_1_3_2_1_20_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arXiv:2201.12086 [cs.CV] https:\/\/arxiv.org\/abs\/2201.12086","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arXiv:2201.12086 [cs.CV] https:\/\/arxiv.org\/abs\/2201.12086"},{"key":"e_1_3_2_1_21_1","volume-title":"Shafiq Joty, Caiming Xiong, and Steven Hoi.","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare, Shafiq Joty, Caiming Xiong, and Steven Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. arXiv:2107.07651 [cs.CV] https:\/\/arxiv.org\/abs\/2107.07651"},{"key":"e_1_3_2_1_22_1","unstructured":"Mingxin Li Yanzhao Zhang Dingkun Long Keqin Chen Sibo Song Shuai Bai Zhibo Yang Pengjun Xie An Yang Dayiheng Liu Jingren Zhou and Junyang Lin. 2026. Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking. arXiv:2601.04720 [cs.CL] https:\/\/arxiv.org\/abs\/2601.04720"},{"key":"e_1_3_2_1_23_1","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie Lubomir Bourdev Ross Girshick James Hays Pietro Perona Deva Ramanan C. Lawrence Zitnick and Piotr Doll\u00e1r. 2015. Microsoft COCO: Common Objects in Context. arXiv:1405.0312 [cs.CV] https:\/\/arxiv.org\/abs\/1405.0312"},{"key":"e_1_3_2_1_24_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. arXiv:2304.08485 [cs.CV] https:\/\/arxiv.org\/abs\/2304.08485"},{"key":"e_1_3_2_1_25_1","volume-title":"Dimosthenis Karatzas, Ernest Valveny, and C. V Jawahar.","author":"Mathew Minesh","year":"2021","unstructured":"Minesh Mathew, Viraj Bagal, Rub\u00e8n P\u00e9rez Tito, Dimosthenis Karatzas, Ernest Valveny, and C. V Jawahar. 2021. InfographicVQA. arXiv:2104.12756 [cs.CV] https:\/\/arxiv.org\/abs\/2104.12756"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Minesh Mathew Dimosthenis Karatzas and C. V. Jawahar. 2021. DocVQA: A Dataset for VQA on Document Images. arXiv:2007.00398 [cs.CV] https:\/\/arxiv.org\/abs\/2007.00398","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_27_1","unstructured":"Rui Meng Ziyan Jiang Ye Liu Mingyi Su Xinyi Yang Yuepeng Fu Can Qin Zeyuan Chen Ran Xu Caiming Xiong Yingbo Zhou Wenhu Chen and Semih Yavuz. 2025. VLM2Vec-V2: Advancing Multimodal Embedding for Videos Images and Visual Documents. arXiv:2507.04590 [cs.CV] https:\/\/arxiv.org\/abs\/2507.04590"},{"key":"e_1_3_2_1_28_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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. arXiv:2103.00020 [cs.CV] https:\/\/arxiv.org\/ abs\/2103.00020"},{"key":"e_1_3_2_1_29_1","unstructured":"Christoph Schuhmann Richard Vencu Romain Beaumont Robert Kaczmarczyk Clayton Mullis Aarush Katta Theo Coombes Jenia Jitsev and Aran Komatsuzaki. 2021. LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs. arXiv:2111.02114 [cs.CV] https:\/\/arxiv.org\/abs\/2111.02114"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Dustin Schwenk Apoorv Khandelwal Christopher Clark Kenneth Marino and Roozbeh Mottaghi. 2022. A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge. arXiv:2206.01718 [cs.CV] https:\/\/arxiv.org\/abs\/2206.01718","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"e_1_3_2_1_31_1","volume-title":"Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, Olivier H\u00e9naff, Jeremiah Harmsen, Andreas Steiner, and Xiaohua Zhai.","author":"Tschannen Michael","year":"2025","unstructured":"Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, Olivier H\u00e9naff, Jeremiah Harmsen, Andreas Steiner, and Xiaohua Zhai. 2025. SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features. arXiv:2502.14786 [cs.CV] https:\/\/arxiv.org\/abs\/2502.14786"},{"key":"e_1_3_2_1_32_1","unstructured":"Aaron van den Oord Yazhe Li and Oriol Vinyals. 2019. Representation Learning with Contrastive Predictive Coding. arXiv:1807.03748 [cs.LG] https:\/\/arxiv.org\/ abs\/1807.03748"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Zhen Wang Xu Shan Xiangxie Zhang and Jie Yang. 2022. N24News: A New Dataset for Multimodal News Classification. arXiv:2108.13327 [cs.CL] https:\/\/arxiv.org\/abs\/2108.13327","DOI":"10.63317\/5c2xbka7swxq"},{"key":"e_1_3_2_1_34_1","unstructured":"Cong Wei Yang Chen Haonan Chen Hexiang Hu Ge Zhang Jie Fu Alan Ritter and Wenhu Chen. 2023. UniIR: Training and Benchmarking Universal Multimodal Information Retrievers. arXiv:2311.17136 [cs.CV] https:\/\/arxiv.org\/abs\/2311.17136"},{"key":"e_1_3_2_1_35_1","volume-title":"Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback. arXiv:1905.12794 [cs.CV] https:\/\/arxiv.org\/abs\/1905.12794","author":"Wu Hui","year":"2020","unstructured":"Hui Wu, Yupeng Gao, Xiaoxiao Guo, Ziad Al-Halah, Steven Rennie, Kristen Grauman, and Rogerio Feris. 2020. Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback. arXiv:1905.12794 [cs.CV] https:\/\/arxiv.org\/abs\/1905.12794"},{"key":"e_1_3_2_1_36_1","unstructured":"Chunyu Xie Bin Wang Fanjing Kong Jincheng Li Dawei Liang Gengshen Zhang Dawei Leng and Yuhui Yin. 2025. FG-CLIP: Fine-Grained Visual and Textual Alignment. arXiv:2505.05071 [cs.CV] https:\/\/arxiv.org\/abs\/2505.05071"},{"key":"e_1_3_2_1_37_1","volume-title":"FILIP: Fine-grained Interactive Language-Image Pre-Training. arXiv:2111.07783 [cs.CV] https:\/\/arxiv.org\/abs\/2111.07783","author":"Yao Lewei","year":"2021","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021. FILIP: Fine-grained Interactive Language-Image Pre-Training. arXiv:2111.07783 [cs.CV] https:\/\/arxiv.org\/abs\/2111.07783"},{"key":"e_1_3_2_1_38_1","unstructured":"Jiahui Yu Zirui Wang Vijay Vasudevan Legg Yeung Mojtaba Seyedhosseini and Yonghui Wu. 2022. CoCa: Contrastive Captioners are Image-Text Foundation Models. arXiv:2205.01917 [cs.CV] https:\/\/arxiv.org\/abs\/2205.01917"},{"key":"e_1_3_2_1_39_1","unstructured":"Hengran Zhang Keping Bi Jiafeng Guo Xiaojie Sun Shihao Liu Daiting Shi Dawei Yin and Xueqi Cheng. 2025. Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling. arXiv:2504.05216 [cs.IR] https:\/\/arxiv.org\/abs\/2504.05216"},{"key":"e_1_3_2_1_40_1","volume-title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv:2412.16855 [cs.CL] https:\/\/arxiv.org\/abs\/2412.16855","author":"Zhang Xin","year":"2025","unstructured":"Xin Zhang, Yanzhao Zhang, Wen Xie, Mingxin Li, Ziqi Dai, Dingkun Long, Pengjun Xie, Meishan Zhang, Wenjie Li, and Min Zhang. 2025. GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv:2412.16855 [cs.CL] https:\/\/arxiv.org\/abs\/2412.16855"},{"key":"e_1_3_2_1_41_1","volume-title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval. arXiv:2406.04292 [cs.IR] https:\/\/arxiv.org\/abs\/2406.04292","author":"Zhou Junjie","year":"2024","unstructured":"Junjie Zhou, Zheng Liu, Shitao Xiao, Bo Zhao, and Yongping Xiong. 2024. VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval. arXiv:2406.04292 [cs.IR] https:\/\/arxiv.org\/abs\/2406.04292"},{"key":"e_1_3_2_1_42_1","unstructured":"Deyao Zhu Jun Chen Xiaoqian Shen Xiang Li and Mohamed Elhoseiny. 2023. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv:2304.10592 [cs.CV] https:\/\/arxiv.org\/abs\/2304.10592"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:46:14Z","timestamp":1783694774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":42,"alternative-id":["10.1145\/3805712.3809695","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809695","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"}}]}}