{"total":31,"rows":[{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119,"area":null},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2311.17055","title":"No Representation Rules Them All in Category Discovery","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2312.01998","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","created":"2023-12-04","cited_by_count":27,"area":null},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2311.00750","title":"Are These the Same Apple? Comparing Images Based on Object Intrinsics","created":"2023-11-01","cited_by_count":19,"area":null},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2507.14902","title":"U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs","created":"2025-07-20","cited_by_count":10,"area":null},{"id":"2504.00954","title":"IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2504.05316","title":"Scale Up Composed Image Retrieval Learning via Modification Text Generation","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2502.20008","title":"Joint Fusion and Encoding: Advancing Multimodal Retrieval from the Ground Up","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2510.04564","title":"Conditional Representation Learning for Customized Tasks","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2504.08368","title":"FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2505.17796","title":"DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2404.16398","title":"Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval","created":"2024-04-25","cited_by_count":3,"area":null},{"id":"2410.11657","title":"Unveiling the Mystery of Visual Attributes of Concrete and Abstract Concepts: Variability, Nearest Neighbors, and Challenging Categories","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2607.18237","title":"The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric","created":"2026-07-20","cited_by_count":3,"area":null},{"id":"2406.09188","title":"An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2503.01334","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2604.14710","title":"G-MIXER: Geodesic Mixup-based Implicit Semantic Expansion and Explicit Semantic Re-ranking for Zero-Shot Composed Image Retrieval","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2605.21261","title":"STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2608.29607","title":"SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions","created":"2026-08-30","cited_by_count":2,"area":null},{"id":"2601.16125","title":"Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2604.11539","title":"CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.07032","title":"Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.00374","title":"Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2510.01513","title":"From Videos to Indexed Knowledge Graphs -- Framework to Marry Methods for Multimodal Content Analysis and Understanding","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2603.04598","title":"PinPoint: Evaluation of Composed Image Retrieval with Explicit Negatives, Multi-Image Queries, and Paraphrase Testing","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.11520","title":"FBCIR: Balancing Cross-Modal Focuses in Composed Image Retrieval","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2609.31202","title":"Preserve-and-Compose Training for Composed Image Retrieval","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.17841","title":"FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}