{"total":19,"rows":[{"id":"2510.25387","title":"Instance-Level Composed Image Retrieval","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2502.15682","title":"ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval","created":"2025-02-21","cited_by_count":9,"area":null},{"id":"2508.10637","title":"Processing and acquisition traces in visual encoders: What does CLIP know about your camera?","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2510.02898","title":"One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2512.12610","title":"Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching","created":"2025-12-14","cited_by_count":2,"area":null},{"id":"2503.07038","title":"Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2510.09171","title":"Instance-Level Generation for Representation Learning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.11930","title":"SupScene: Scene-Structured Overlap Supervision for Image Retrieval in Unconstrained SfM","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2603.28603","title":"ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2604.05039","title":"ID-Sim: An Identity-Focused Similarity Metric","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2608.01794","title":"Illuminating Visual Identity in Universal Multimodal Embeddings","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2506.16745","title":"Class Agnostic Instance-level Descriptor for Visual Instance Search","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2511.09820","title":"From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2603.17186","title":"Visual Product Search Benchmark","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2608.07057","title":"KnifeHunter: Structured Local Representation Learning for Fine-Grained Knife Image Retrieval in Law Enforcement","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.29917","title":"FoundYou: A Unified Model for Personalized Segmentation and Retrieval","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.33359","title":"When Does Geometric View Synthesis Help Wine Label Retrieval? A Public One-Shot Benchmark Across Self-Supervised and Vision-Language Backbones","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38278","title":"Masked Swingers: Harnessing Data Augmentation to Advance Autoencoders for Self-Supervised Learning","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.17986","title":"Web Scale on a Budget: Tail-Aware Retrieval Evaluation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}