{"total":52,"rows":[{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"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":"2405.07472","title":"GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting","created":"2024-05-13","cited_by_count":22,"area":null},{"id":"2404.11317","title":"Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives","created":"2024-04-17","cited_by_count":20,"area":null},{"id":"2408.11305","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","created":"2024-08-21","cited_by_count":17,"area":"mllm"},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2604.21806","title":"TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval","created":"2026-04-23","cited_by_count":15,"area":null},{"id":"2403.01431","title":"Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval","created":"2024-03-03","cited_by_count":14,"area":null},{"id":"2312.12273","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering","created":"2023-12-19","cited_by_count":11,"area":null},{"id":"2510.25238","title":"VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2505.19952","title":"Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"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":"2505.20764","title":"ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval","created":"2025-05-27","cited_by_count":7,"area":null},{"id":"2407.11480","title":"AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Models","created":"2024-07-16","cited_by_count":6,"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":"2503.19868","title":"GENIUS: A Generative Framework for Universal Multimodal Search","created":"2025-03-25","cited_by_count":5,"area":null},{"id":"2505.19707","title":"MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2507.21917","title":"ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval","created":"2025-07-29","cited_by_count":5,"area":"lr"},{"id":"2508.00955","title":"From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2503.17871","title":"good4cir: Generating Detailed Synthetic Captions for Composed Image Retrieval","created":"2025-03-22","cited_by_count":4,"area":"mllm"},{"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":"2511.06225","title":"MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition","created":"2025-11-09","cited_by_count":4,"area":"mllm"},{"id":"2507.06210","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","created":"2025-07-08","cited_by_count":3,"area":"mllm"},{"id":"2510.05586","title":"CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval","created":"2025-10-07","cited_by_count":3,"area":"mllm"},{"id":"2602.01639","title":"ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval","created":"2026-02-02","cited_by_count":3,"area":"mllm"},{"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":"2505.05229","title":"Does CLIP perceive art the same way we do?","created":"2025-05-08","cited_by_count":2,"area":null},{"id":"2510.05759","title":"OneVision: An End-to-End Generative Framework for Multi-view E-commerce Vision Search","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2603.12937","title":"SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2509.23370","title":"GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval","created":"2025-09-27","cited_by_count":1,"area":"lr"},{"id":"2509.26330","title":"SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval","created":"2025-09-30","cited_by_count":1,"area":"mllm"},{"id":"2602.08603","title":"OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval","created":"2026-02-09","cited_by_count":1,"area":"agents"},{"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":"2607.27959","title":"FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2412.07333","title":"Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion Model","created":"2024-12-10","cited_by_count":0,"area":"diffusion"},{"id":"2501.13968","title":"Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2503.22884","title":"AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs","created":"2025-03-28","cited_by_count":0,"area":"mllm"},{"id":"2507.09487","title":"HMID-Net: An Exploration of Masked Image Modeling and Knowledge Distillation in Hyperbolic Space","created":"2025-07-13","cited_by_count":0,"area":"distill"},{"id":"2508.04424","title":"Composed Object Retrieval: Object-level Retrieval via Composed Expressions","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2603.04037","title":"DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval","created":"2026-03-04","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":"2604.05393","title":"Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.05583","title":"WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.05809","title":"Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models","created":"2026-04-07","cited_by_count":0,"area":"safety"},{"id":"2604.12904","title":"A Sanity Check on Composed Image Retrieval","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.08389","title":"Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.13427","title":"VietFashion: Benchmarking Sketch-Text Composed Image Retrieval for Cultural Outfits","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.19684","title":"Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2607.20291","title":"Diverse-Intent Multi-Turn Fashion Image Retrieval","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.23102","title":"Training-Free Pseudo-Fusion for Composed Image Retrieval with Diffusion Models and Multimodal Large Language Models","created":"2026-08-24","cited_by_count":0,"area":"mllm"},{"id":"2608.26632","title":"Who Remains, What Changes: Identity Anchored Composed Gait Retrieval","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}