{"total":107,"rows":[{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251,"area":null},{"id":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176,"area":null},{"id":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166,"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":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83,"area":null},{"id":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52,"area":null},{"id":"2306.07969","title":"GeneCIS: A Benchmark for General Conditional Image Similarity","created":"2023-06-13","cited_by_count":47,"area":null},{"id":"2303.09429","title":"Data Roaming and Quality Assessment for Composed Image Retrieval","created":"2023-03-16","cited_by_count":46,"area":null},{"id":"2211.07394","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","created":"2022-11-14","cited_by_count":45,"area":null},{"id":"2405.00571","title":"Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval","created":"2024-05-01","cited_by_count":44,"area":null},{"id":"2303.16604","title":"Bi-directional Training for Composed Image Retrieval via Text Prompt Learning","created":"2023-03-29","cited_by_count":43,"area":null},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42,"area":null},{"id":"2305.16304","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","created":"2023-05-25","cited_by_count":35,"area":null},{"id":"2207.08150","title":"FashionViL: Fashion-Focused Vision-and-Language Representation Learning","created":"2022-07-17","cited_by_count":32,"area":null},{"id":"2106.04128","title":"Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback","created":"2021-06-08","cited_by_count":29,"area":null},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29,"area":null},{"id":"2208.03354","title":"A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch","created":"2022-08-05","cited_by_count":28,"area":null},{"id":"2405.02951","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","created":"2024-05-05","cited_by_count":24,"area":null},{"id":"2112.03162","title":"Embedding Arithmetic of Multimodal Queries for Image Retrieval","created":"2021-12-06","cited_by_count":21,"area":null},{"id":"2405.19149","title":"CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval","created":"2024-05-29","cited_by_count":21,"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":"2105.15089","title":"Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model","created":"2021-05-31","cited_by_count":20,"area":null},{"id":"2312.02428","title":"FreestyleRet: Retrieving Images from Style-Diversified Queries","created":"2023-12-05","cited_by_count":20,"area":null},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2407.20243","title":"Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions","created":"2024-07-17","cited_by_count":16,"area":null},{"id":"2312.06179","title":"Dynamic Weighted Combiner for Mixed-Modal Image Retrieval","created":"2023-12-11","cited_by_count":15,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2306.02092","title":"Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations","created":"2023-06-03","cited_by_count":14,"area":null},{"id":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2510.12474","title":"SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression","created":"2025-10-14","cited_by_count":14,"area":null},{"id":"2104.02429","title":"Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning","created":"2021-04-06","cited_by_count":12,"area":null},{"id":"2308.10170","title":"FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory","created":"2023-08-20","cited_by_count":11,"area":null},{"id":"2310.08750","title":"Search-Adaptor: Embedding Customization for Information Retrieval","created":"2023-10-12","cited_by_count":11,"area":null},{"id":"2404.15790","title":"Leveraging Large Language Models for Multimodal Search","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2410.15624","title":"Test-time Adaptation for Cross-modal Retrieval with Query Shift","created":"2024-10-21","cited_by_count":10,"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":"2508.13843","title":"UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion","created":"2025-08-19","cited_by_count":10,"area":null},{"id":"2309.05551","title":"OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data","created":"2023-09-11","cited_by_count":9,"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":"2203.03809","title":"Image Search with Text Feedback by Additive Attention Compositional Learning","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2210.15028","title":"FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2406.18836","title":"Zero-shot Composed Image Retrieval Considering Query-target Relationship Leveraging Masked Image-text Pairs","created":"2024-06-27","cited_by_count":7,"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":"2509.25638","title":"Generalized Contrastive Learning for Universal Multimodal Retrieval","created":"2025-09-30","cited_by_count":7,"area":null},{"id":"2601.14706","title":"LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval","created":"2026-01-21","cited_by_count":7,"area":null},{"id":"2204.03111","title":"UIGR: Unified Interactive Garment Retrieval","created":"2022-04-06","cited_by_count":6,"area":null},{"id":"2403.02875","title":"Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples","created":"2024-03-05","cited_by_count":6,"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":"2204.11004","title":"Training and challenging models for text-guided fashion image retrieval","created":"2022-04-23","cited_by_count":5,"area":null},{"id":"2304.01961","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","created":"2023-04-04","cited_by_count":5,"area":null},{"id":"2312.15844","title":"Learning-To-Rank Approach for Identifying Everyday Objects Using a Physical-World Search Engine","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2401.08472","title":"Instilling Multi-round Thinking to Text-guided Image Generation","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2409.05405","title":"A Survey of Multimodal Composite Editing and Retrieval","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2502.08438","title":"Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex Interactions","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2503.19868","title":"GENIUS: A Generative Framework for Universal Multimodal Search","created":"2025-03-25","cited_by_count":5,"area":null},{"id":"2111.00905","title":"Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry","created":"2021-10-28","cited_by_count":4,"area":null},{"id":"2207.04211","title":"BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2412.03297","title":"Composed Image Retrieval for Training-Free Domain Conversion","created":"2024-12-04","cited_by_count":4,"area":null},{"id":"2301.05174","title":"Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study","created":"2023-01-12","cited_by_count":3,"area":null},{"id":"2301.13014","title":"Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval","created":"2022-12-27","cited_by_count":3,"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":"2408.07910","title":"DM2RM: Dual-Mode Multimodal Ranking for Target Objects and Receptacles Based on Open-Vocabulary Instructions","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2503.19145","title":"Compositional Caching for Training-free Open-vocabulary Attribute Detection","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2505.20291","title":"VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2602.09839","title":"ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2602.23029","title":"WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2103.06032","title":"Cross-modal Image Retrieval with Deep Mutual Information Maximization","created":"2021-03-10","cited_by_count":2,"area":null},{"id":"2107.00955","title":"Concept Identification of Directly and Indirectly Related Mentions Referring to Groups of Persons","created":"2021-07-02","cited_by_count":2,"area":null},{"id":"2111.14145","title":"FashionSearchNet-v2: Learning Attribute Representations with Localization for Image Retrieval with Attribute Manipulation","created":"2021-11-28","cited_by_count":2,"area":null},{"id":"2311.14837","title":"Benchmarking Robustness of Text-Image Composed Retrieval","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2501.08347","title":"SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval","created":"2025-01-12","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":"2105.03050","title":"fAshIon after fashion: A Report of AI in Fashion","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2207.01058","title":"Chat-to-Design: AI Assisted Personalized Fashion Design","created":"2022-07-03","cited_by_count":1,"area":null},{"id":"2210.09377","title":"6th Place Solution to Google Universal Image Embedding","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2210.17417","title":"Fashion-Specific Attributes Interpretation via Dual Gaussian Visual-Semantic Embedding","created":"2022-10-28","cited_by_count":1,"area":null},{"id":"2408.11553","title":"AnyDesign: Versatile Area Fashion Editing via Mask-Free Diffusion","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2409.13513","title":"Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2410.01536","title":"EUFCC-CIR: a Composed Image Retrieval Dataset for GLAM Collections","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2503.00619","title":"PinLanding: Content-First Keyword Landing Page Generation via Multi-Modal AI for Web-Scale Discovery","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2507.07135","title":"FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2605.22552","title":"FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.27708","title":"ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2201.10431","title":"Main Product Detection with Graph Networks for Fashion","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2211.06688","title":"Partial Visual-Semantic Embedding: Fashion Intelligence System with Sensitive Part-by-Part Learning","created":"2022-11-12","cited_by_count":0,"area":null},{"id":"2305.00052","title":"Click-Feedback Retrieval","created":"2023-04-28","cited_by_count":0,"area":null},{"id":"2305.02307","title":"Fashionpedia-Taste: A Dataset towards Explaining Human Fashion Taste","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2305.02360","title":"Fashionpedia-Ads: Do Your Favorite Advertisements Reveal Your Fashion Taste?","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2401.04575","title":"Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding","created":"2024-01-09","cited_by_count":0,"area":null},{"id":"2504.00812","title":"Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2506.02291","title":"Entity Image and Mixed-Modal Image Retrieval Datasets","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2509.24477","title":"Performance-Efficiency Trade-off for Fashion Image Retrieval","created":"2025-09-29","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":"2603.05446","title":"NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette Queries","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2605.24442","title":"Benchmarking Composed Image Retrieval for Applied Earth Observation","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2605.24634","title":"Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.27897","title":"A Multi-Attribute Latent Space for Visual Analysis of Watches","created":"2026-06-26","cited_by_count":0,"area":null}],"next_cursor":"100"}