% Key papers for Composed and text-based image retrieval (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages. @inproceedings{cvpr2016_natural_11724, title = {{Natural Language Object Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2016}, } @inproceedings{cvpr2017_person_12529, title = {{Person Search With Natural Language Description}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, } @inproceedings{cvpr2016_sketch_11868, title = {{Sketch Me That Shoe}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2016}, } @inproceedings{cvpr2021_fashion_17006, title = {{Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, } @inproceedings{cvpr2020_image_15673, title = {{Image Search With Text Feedback by Visiolinguistic Attention Learning}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020}, } @inproceedings{aaai2020_pose_103670, title = {{Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2020}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/6777}, } @inproceedings{cvpr2017_deep_12188, title = {{Deep Visual-Semantic Quantization for Efficient Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, } @inproceedings{cvpr2020_sketch_16253, title = {{Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020}, } @inproceedings{cvpr2017_beyond_12081, title = {{Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, } @inproceedings{aaai2021_dual_468, title = {{Dual Compositional Learning in Interactive Image Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2021}, url = {https://aaai.org/papers/01771-dual-compositional-learning-in-interactive-image-retrieval/}, } @inproceedings{cvpr2023_zero_22592, title = {{Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, url = {https://cvpr.thecvf.com/virtual/2023/poster/21442}, } @inproceedings{cvpr2019_livesketch_14472, title = {{LiveSketch: Query Perturbations for Guided Sketch-Based Visual Search}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2019}, } @inproceedings{aaai2024_context_5485, title = {{Context-I2W: Mapping Images to Context-Dependent Words for Accurate Zero-Shot Composed Image Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/28324}, } @inproceedings{cvpr2021_scene_17827, title = {{Scene Text Retrieval via Joint Text Detection and Similarity Learning}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, } @inproceedings{cvpr2023_multilateral_21624, title = {{Multilateral Semantic Relations Modeling for Image Text Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, url = {https://cvpr.thecvf.com/virtual/2023/poster/21892}, } @inproceedings{cvpr2017_spatial_12648, title = {{Spatial-Semantic Image Search by Visual Feature Synthesis}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, } @inproceedings{aaai2022_action_1699, title = {{Action-Aware Embedding Enhancement for Image-Text Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2022}, url = {https://aaai.org/papers/01323-action-aware-embedding-enhancement-for-image-text-retrieval/}, } @inproceedings{aaai2025_encoder_8872, title = {{ENCODER: Entity Mining and Modification Relation Binding for Composed Image Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/32541}, } @inproceedings{aaai2019_incorporating_100214, title = {{Incorporating Semantic Similarity with Geographic Correlation for Query-POI Relevance Learning}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2019}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/3922}, } @inproceedings{cvpr2024_you_25302, title = {{You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, url = {https://cvpr.thecvf.com/virtual/2024/poster/30352}, } @inproceedings{aaai2024_let_6518, title = {{Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/28207}, } @inproceedings{cvpr2024_visual_25245, title = {{Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, url = {https://cvpr.thecvf.com/virtual/2024/poster/31600}, } @inproceedings{cvpr2025_reason_27399, title = {{Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/33289}, } @inproceedings{aaai2024_fashionern_5970, title = {{FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/27885}, } @inproceedings{iclr2024_composed_34654, title = {{Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024}, url = {https://iclr.cc/virtual/2024/poster/18420}, } @inproceedings{neurips2024_inquire_73532, title = {{INQUIRE: A Natural World Text-to-Image Retrieval Benchmark}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/97543}, } @inproceedings{aaai2025_bev_8211, title = {{BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/32782}, } @inproceedings{cvpr2025_generative_26428, title = {{Generative Zero-Shot Composed Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/34000}, } @inproceedings{cvpr2025_missing_26962, title = {{Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/33968}, } @inproceedings{cvpr2025_towards_27915, title = {{Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/34571}, } @inproceedings{iclr2025_colpali_83480, title = {{ColPali: Efficient Document Retrieval with Vision Language Models}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025}, url = {https://iclr.cc/virtual/2025/poster/28336}, } @inproceedings{cvpr2025_ilias_26570, title = {{ILIAS: Instance-Level Image retrieval At Scale}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/34712}, } @inproceedings{iclr2024_sentence_35164, title = {{Sentence-level Prompts Benefit Composed Image Retrieval}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024}, url = {https://iclr.cc/virtual/2024/poster/17909}, } @inproceedings{aaai2026_habit_102663, title = {{HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/37608}, } @inproceedings{aaai2025_leveraging_9782, title = {{Leveraging Large Vision-Language Model as User Intent-Aware Encoder for Composed Image Retrieval}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/32768}, } @inproceedings{aaai2024_transformer_7644, title = {{Transformer-Empowered Multi-Modal Item Embedding for Enhanced Image Search in E-commerce}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/30311}, } @inproceedings{cvpr2025_collm_25723, title = {{CoLLM: A Large Language Model for Composed Image Retrieval}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/34564}, }