{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:31:54Z","timestamp":1780511514455,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["No.:62276155, No.:62376137"],"award-info":[{"award-number":["No.:62276155, No.:62376137"]}]},{"name":"China National University Student Innovation & Entrepreneurship Development Program","award":["No.:202410422071"],"award-info":[{"award-number":["No.:202410422071"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755366","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:15Z","timestamp":1761375255000},"page":"6113-6122","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0365-8553","authenticated-orcid":false,"given":"Zhiwei","family":"Chen","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-8286","authenticated-orcid":false,"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5136-159X","authenticated-orcid":false,"given":"Zixu","family":"Li","sequence":"additional","affiliation":[{"name":"School of software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7724-5662","authenticated-orcid":false,"given":"Zhiheng","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-4197","authenticated-orcid":false,"given":"Xuemeng","family":"Song","sequence":"additional","affiliation":[{"name":"School of Data Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27977"},{"key":"e_1_3_2_1_2_1","unstructured":"Guanwen Xie Jingzehua Xu Yimian Ding Zhi Zhang Shuai Zhang and Yi Li. 2025. Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions. arXiv:2503.00527 [cs.RO] https:\/\/arxiv.org\/abs\/2503.00527"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680774"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3395568"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2024.102308"},{"key":"e_1_3_2_1_6_1","first-page":"1","article-title":"DUDB: deep unfolding-based dual-branch feature fusion network for pan-sharpening remote sensing images","volume":"62","author":"Tao Hailin","year":"2023","unstructured":"Hailin Tao, Jinjiang Li, Zhen Hua, and Fan Zhang. 2023. DUDB: deep unfolding-based dual-branch feature fusion network for pan-sharpening remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, Vol. 62 (2023), 1-17.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0369-x"},{"key":"e_1_3_2_1_8_1","volume-title":"Development and application of a monte carlo tree search algorithm for simulating da vinci code game strategies. arXiv preprint arXiv:2403.10720","author":"Zhang Ye","year":"2024","unstructured":"Ye Zhang, Mengran Zhu, Kailin Gui, Jiayue Yu, Yong Hao, and Haozhan Sun. 2024b. Development and application of a monte carlo tree search algorithm for simulating da vinci code game strategies. arXiv preprint arXiv:2403.10720 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02205-5"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449986"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01443"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32541"},{"key":"e_1_3_2_1_16_1","volume-title":"Emerging Cutting-Edge Developments in Intelligent Traffic and Transportation Systems","author":"Li Xiwen","unstructured":"Xiwen Li, Tristalee Mangin, Surojit Saha, Rehman Mohammed, Evan Blanchard, Dillon Tang, Henry Poppe, Ouk Choi, Kerry Kelly, and Ross Whitaker. 2024. Real-time idling vehicles detection using combined audio-visual deep learning. In Emerging Cutting-Edge Developments in Intelligent Traffic and Transportation Systems. IOS Press, 142-158."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3090521"},{"key":"e_1_3_2_1_18_1","volume-title":"Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection. The Visual Computer","author":"Xu Jiawei","year":"2025","unstructured":"Jiawei Xu, Qiangqiang Zhou, Jiacong Yu, Chen Liao, and Dandan Zhu. 2025. Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection. The Visual Computer (2025), 1-13."},{"key":"e_1_3_2_1_19_1","volume-title":"Enhancing Text Authenticity: A Novel Hybrid Approach for AI-Generated Text Detection. arXiv preprint arXiv:2406.06558","author":"Zhang Ye","year":"2024","unstructured":"Ye Zhang, Qian Leng, Mengran Zhu, Rui Ding, Yue Wu, Jintong Song, and Yulu Gong. 2024. Enhancing Text Authenticity: A Novel Hybrid Approach for AI-Generated Text Detection. arXiv preprint arXiv:2406.06558 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00098"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of ECCV.","author":"Du Penghui","year":"2024","unstructured":"Penghui Du, Yu Wang, Yifan Sun, Luting Wang, Yue Liao, Gang Zhang, Errui Ding, Yan Wang, Jingdong Wang, and Si Liu. 2024. LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction. In Proceedings of ECCV."},{"key":"e_1_3_2_1_22_1","volume-title":"Audio and Multiscale Visual Cues Driven Cross-modal Transformer for Idling Vehicle Detection. arXiv preprint arXiv:2504.16102","author":"Li Xiwen","year":"2025","unstructured":"Xiwen Li, Ross Whitaker, and Tolga Tasdizen. 2025. Audio and Multiscale Visual Cues Driven Cross-modal Transformer for Idling Vehicle Detection. arXiv preprint arXiv:2504.16102 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"LP-DETR: Layer-wise Progressive Relations for Object Detection. arXiv preprint arXiv:2502.05147","author":"Kang Zhengjian","year":"2025","unstructured":"Zhengjian Kang, Ye Zhang, Xiaoyu Deng, Xintao Li, and Yongzhe Zhang. 2025. LP-DETR: Layer-wise Progressive Relations for Object Detection. arXiv preprint arXiv:2502.05147 (2025)."},{"key":"e_1_3_2_1_24_1","first-page":"1","article-title":"Semantic collaborative learning for cross-modal moment localization","volume":"42","author":"Hu Yupeng","year":"2023","unstructured":"Yupeng Hu, Kun Wang, Meng Liu, Haoyu Tang, and Liqiang Nie. 2023. Semantic collaborative learning for cross-modal moment localization. ACM Transactions on Information Systems, Vol. 42, 2 (2023), 1-26.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Zhe Li Xiangfei Qiu Peng Chen Yihang Wang Hanyin Cheng Yang Shu Jilin Hu Chenjuan Guo Aoying Zhou Qingsong Wen et al. 2025. TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting. In SIGKDD.","DOI":"10.1145\/3711896.3737442"},{"key":"e_1_3_2_1_26_1","unstructured":"Jingzehua Xu Guanwen Xie Ziqi Zhang Xiangwang Hou Dongfang Ma Shuai Zhang Yong Ren and Dusit Niyato. 2024. Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task? arXiv:2412.03959 [cs.RO] https:\/\/arxiv.org\/abs\/2412.03959"},{"key":"e_1_3_2_1_27_1","volume-title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching. In ICLR.","author":"Wu Xingjian","year":"2025","unstructured":"Xingjian Wu, Xiangfei Qiu, Zhengyu Li, Yihang Wang, Jilin Hu, Chenjuan Guo, Hui Xiong, and Bin Yang. 2025. CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching. In ICLR."},{"key":"e_1_3_2_1_28_1","volume-title":"MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrast. arXiv preprint arXiv:2410.15997","author":"Hu Shiyan","year":"2024","unstructured":"Shiyan Hu, Kai Zhao, Xiangfei Qiu, Yang Shu, Jilin Hu, Bin Yang, and Chenjuan Guo. 2024. MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrast. arXiv preprint arXiv:2410.15997 (2024)."},{"key":"e_1_3_2_1_29_1","unstructured":"Hongfan Gao Wangmeng Shen Xiangfei Qiu Ronghui Xu Bin Yang and Jilin Hu. 2025. SSD-TS: Exploring the potential of linear state space models for diffusion models in time series imputation. In SIGKDD."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_1_32_1","volume-title":"Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation. arXiv preprint arXiv:2505.18556","author":"Zhuang Jun","year":"2025","unstructured":"Jun Zhuang, Haibo Jin, Ye Zhang, Zhengjian Kang, Wenbin Zhang, Gaby G Dagher, and Haohan Wang. 2025. Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation. arXiv preprint arXiv:2505.18556 (2025)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-024-00872-x"},{"key":"e_1_3_2_1_34_1","volume-title":"Self-Adaptive Robust Motion Planning for High DoF Robot Manipulator using Deep MPC. arXiv preprint arXiv:2407.12887","author":"Zhang Ye","year":"2024","unstructured":"Ye Zhang, Kangtong Mo, Fangzhou Shen, Xuanzhen Xu, Xingyu Zhang, Jiayue Yu, and Chang Yu. 2024. Self-Adaptive Robust Motion Planning for High DoF Robot Manipulator using Deep MPC. arXiv preprint arXiv:2407.12887 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline. arXiv preprint arXiv:2505.11250","author":"Liu Xvyuan","year":"2025","unstructured":"Xvyuan Liu, Xiangfei Qiu, Xingjian Wu, Zhengyu Li, Chenjuan Guo, Jilin Hu, and Bin Yang. 2025. Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline. arXiv preprint arXiv:2505.11250 (2025)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657727"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01323"},{"key":"e_1_3_2_1_38_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3662732"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657831"},{"key":"e_1_3_2_1_43_1","volume-title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval. https:\/\/arxiv.org\/abs\/2503.21309","author":"Li Zixu","year":"2025","unstructured":"Zixu Li, Zhiheng Fu, Yupeng Hu, Zhiwei Chen, Haokun Wen, and Liqiang Nie. 2025. FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval. https:\/\/arxiv.org\/abs\/2503.21309 (2025)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890642"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888153"},{"key":"e_1_3_2_1_46_1","volume-title":"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, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9870824"},{"key":"e_1_3_2_1_49_1","unstructured":"Haokun Chen Yueqi Zhang Yuan Bi Yao Zhang Tong Liu Jinhe Bi Jian Lan Jindong Gu Claudia Grosser Denis Krompass et al. 2025. Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs. arXiv preprint arXiv:2505.23270 (2025)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108593"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3416616"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681526"},{"key":"e_1_3_2_1_53_1","volume-title":"Collaborative Computing: Networking, Applications and Worksharing","author":"Zhan Peng","unstructured":"Peng Zhan, Yupeng Hu, Wei Luo, Yang Xu, Qi Zhang, and Xueqing Li. 2019. Feature-based online segmentation algorithm for streaming time series (short paper). In Collaborative Computing: Networking, Applications and Worksharing. Springer, 477-487."},{"key":"e_1_3_2_1_54_1","volume-title":"Building shortcuts between distant nodes with biaffine mapping for graph convolutional networks. ACM Transactions on Knowledge Discovery from Data","author":"Zhang Acong","year":"2024","unstructured":"Acong Zhang, Jincheng Huang, Ping Li, and Kai Zhang. 2024. Building shortcuts between distant nodes with biaffine mapping for graph convolutional networks. ACM Transactions on Knowledge Discovery from Data, Vol. 18, 6 (2024), 1-21."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102296"},{"key":"e_1_3_2_1_56_1","first-page":"1949","article-title":"Graph Neural Network Defense Combined with Contrastive Learning","volume":"17","author":"Na CHEN","year":"2023","unstructured":"CHEN Na, HUANG Jincheng, and LI Ping. 2023. Graph Neural Network Defense Combined with Contrastive Learning. Journal of Frontiers of Computer Science & Technology, Vol. 17, 8 (2023), 1949.","journal-title":"Journal of Frontiers of Computer Science & Technology"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3714428"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107393"},{"key":"e_1_3_2_1_59_1","volume-title":"Transunet: Transformers make strong encoders for medical image segmentation. arXiv:2102.04306","author":"Chen Jieneng","year":"2021","unstructured":"Jieneng Chen, Yongyi Lu, Qihang Yu, Xiangde Luo, Ehsan Adeli, Yan Wang, Le Lu, Alan L Yuille, and Yuyin Zhou. 2021. Transunet: Transformers make strong encoders for medical image segmentation. arXiv:2102.04306"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.3389\/fenrg.2024.1424928"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278131"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02834"},{"key":"e_1_3_2_1_63_1","first-page":"1318","article-title":"SPOT: Structure Patching and Overlap Tweaking for Effective Pipelining in Privacy-Preserving MLaaS with Tiny Clients. In 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS)","author":"Xu Xiangrui","year":"2024","unstructured":"Xiangrui Xu, Qiao Zhang, Rui Ning, Chunsheng Xin, and Hongyi Wu. 2024. SPOT: Structure Patching and Overlap Tweaking for Effective Pipelining in Privacy-Preserving MLaaS with Tiny Clients. In 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS). IEEE Computer Society, 1318-1329.","journal-title":"IEEE Computer Society"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888444"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.3030624"},{"key":"e_1_3_2_1_66_1","volume-title":"Comet: A communication-efficient and performant approximation for private transformer inference. arXiv preprint arXiv:2405.17485","author":"Xu Xiangrui","year":"2024","unstructured":"Xiangrui Xu, Qiao Zhang, Rui Ning, Chunsheng Xin, and Hongyi Wu. 2024. Comet: A communication-efficient and performant approximation for private transformer inference. arXiv preprint arXiv:2405.17485 (2024)."},{"key":"e_1_3_2_1_67_1","volume-title":"International Conference on Smart Electrical Grid and Renewable Energy. Springer, 269-282","author":"Yang Hao","year":"2024","unstructured":"Hao Yang, Lei Yu, Xinhao Lin, Yinliang Liu, Xian Qiao, Haidian Li, Bowen Dong, and Tianyu Chen. 2024. An edge computing-based lightweight topology identification method for low voltage power distribution networks. In International Conference on Smart Electrical Grid and Renewable Energy. Springer, 269-282."},{"key":"e_1_3_2_1_68_1","volume-title":"ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM. arXiv preprint arXiv:2506.14766","author":"Wang Yujun","year":"2025","unstructured":"Yujun Wang, Jinhe Bi, Yunpu Ma, and Soeren Pirk. 2025. ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM. arXiv preprint arXiv:2506.14766 (2025)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923608"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_1_73_1","volume-title":"Dialog-based interactive image retrieval. Advances in neural information processing systems","author":"Guo Xiaoxiao","year":"2018","unstructured":"Xiaoxiao Guo, Hui Wu, Yu Cheng, Steven Rennie, Gerald Tesauro, and Rogerio Feris. 2018. Dialog-based interactive image retrieval. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_75_1","volume-title":"Gabriela Csurka, and Diane Larlus.","author":"Delmas Ginger","year":"2022","unstructured":"Ginger Delmas, Rafael Sampaio de Rezende, Gabriela Csurka, and Diane Larlus. 2022. Artemis: Attention-based retrieval with text-explicit matching and implicit similarity. arXiv:2203.08101"},{"key":"e_1_3_2_1_76_1","volume-title":"International Conference on Learning Representations.","author":"Chen Yiyang","year":"2024","unstructured":"Yiyang Chen, Zhedong Zheng, Wei Ji, Leigang Qu, and Tat-Seng Chua. 2024. Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_77_1","volume-title":"LLM-enhanced Composed Image Retrieval: An Intent Uncertainty-aware Linguistic-Visual Dual Channel Matching Model. ACM Transactions on Information Systems","author":"Ge Hongfei","year":"2024","unstructured":"Hongfei Ge, Yuanchun Jiang, Jianshan Sun, Kun Yuan, and Yezheng Liu. 2024. LLM-enhanced Composed Image Retrieval: An Intent Uncertainty-aware Linguistic-Visual Dual Channel Matching Model. ACM Transactions on Information Systems (2024)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681493"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657823"},{"key":"e_1_3_2_1_80_1","volume-title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","author":"Ventura Lucas","year":"2024","unstructured":"Lucas Ventura, Antoine Yang, Cordelia Schmid, and G\u00fcl Varol. 2024. CoVR-2: Automatic Data Construction for Composed Video Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_81_1","volume-title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder. Transactions on Machine Learning Research","author":"Liu Zheyuan","year":"2024","unstructured":"Zheyuan Liu, Weixuan Sun, Damien Teney, and Stephen Gould. 2024. Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_2_1_82_1","volume-title":"Sentence-level Prompts Benefit Composed Image Retrieval. In International Conference on Learning Representations.","author":"Xu Xinxing","year":"2024","unstructured":"Xinxing Xu, Yong Liu, Salman Khan, Fahad Khan, Wangmeng Zuo, Rick Siow Mong Goh, Chun-Mei Feng, et al., 2024. Sentence-level Prompts Benefit Composed Image Retrieval. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27885"},{"key":"e_1_3_2_1_84_1","volume-title":"Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval","author":"Wen Haokun","year":"2023","unstructured":"Haokun Wen, Xuemeng Song, Jianhua Yin, Jianlong Wu, Weili Guan, and Liqiang Nie. 2023. Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3235495"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:00:15Z","timestamp":1765339215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755366"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":88,"alternative-id":["10.1145\/3746027.3755366","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755366","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"}}]}}