DiCE-CIR: Direct Composition Learning for Efficient Zero-Shot Composed Image Retrieval
Institute of Information & Communications Technology Planning & Evaluation (IITP)（信息通信技术规划与评估研究所（IITP））；Department of Artificial Intelligence, Korea University（韩国大学人工智能系）
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text describing the desired modification. Recent ZS-CIR studies have relied on projection-based methods that map a reference image into pseudo-word tokens in the text embedding space. However, such methods require additional projection and re-encoding steps, increasing training complexity, reducing efficiency, and introducing a discrepancy between training and inference. In this paper, we propose DiCE-CIR, a direct composition learning method that predicts composed query representations by directly composing a reference image and an edit text. To enable scalable training without manually annotated triplets, we automatically construct compositional training samples from large-scale image-caption pairs using a large language model. Based on these samples, we train a lightweight composition module with objectives that promote alignment with the target, edit-consistent semantic transformation, and retrieval discriminability. We conduct extensive experiments on ZS-CIR benchmarks and show that DiCE-CIR achieves state-of-the-art performance on CIRCO and competitive performance on CIRR while maintaining high computational efficiency.
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Institute of Technology（北京理工大学）；University of Adelaide（阿德莱德大学）
TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval
School of Software, Shandong University（山东大学软件学院）；Department of Computing, Hong Kong Polytechnic University（香港理工大学计算机系）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）
NCL-CIR: Noise-aware Contrastive Learning for Composed Image Retrieval
Hong Kong Baptist University（香港 Baptist 大学）；BNU-HKBU United International College（BNU-HKBU 国际学院）；University of Wollongong（沃林根大学）；University of Surrey（萨里大学）
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Microsoft（微软公司）；Minzu University of China（中央民族大学）；University of Adelaide（阿德莱德大学）
Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；School of Information Engineering, Minzu University of China（中央民族大学信息工程学院）；School of Cyberspace Science and Technology, Beijing Institute of Technology（北京理工大学网络空间科学与技术学院）
FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval
School of Software, Shandong University（山东大学软件学院）；School of Data Science, City University of Hong Kong（香港城市大学数据科学学院）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）
Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；School of Information Engineering, Minzu University of China（中央民族大学信息工程学院）；Beijing Institute of Technology（北京理工大学）；University of Adelaide（阿德莱德大学）
Czech Technical University in Prague（布拉格捷克理工大学）；Athena Research Center（雅典娜研究中心）；National Technical University of Athens（雅典国立技术大学）；Hellenic Robotics Center of Excellence（希腊机器人卓越中心）；IARAI
Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
Sun Yat-sen University（中山大学）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing（机器智能与先进计算重点实验室）
Composed Object Retrieval: Object-level Retrieval via Composed Expressions
Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, Ministry of Education, Jiangsu, China（新一代人工智能技术及跨学科应用国家重点实验室，东南大学，教育部，江苏，中国）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE（穆罕默德·本·扎耶德人工智能大学（MBZUAI），阿布扎赫德，阿联酋）
Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
针对零样本组合图像检索中缺乏标注三元组及大型 VL 模型部署困难的问题，提出 ISA 框架，通过 Image2Sentence、非对称架构与蒸馏对齐提升检索准确率和效率。
