{"total":23,"rows":[{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2309.01858","title":"Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations","created":"2023-09-04","cited_by_count":28,"area":null},{"id":"2303.16382","title":"ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation","created":"2023-03-29","cited_by_count":18,"area":null},{"id":"2406.09294","title":"You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2510.25387","title":"Instance-Level Composed Image Retrieval","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2103.11781","title":"Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales","created":"2021-03-22","cited_by_count":11,"area":null},{"id":"2602.24181","title":"A Mixed Diet Makes DINO An Omnivorous Vision Encoder","created":"2026-02-27","cited_by_count":4,"area":null},{"id":"2312.10282","title":"RetailKLIP : Finetuning OpenCLIP backbone using metric learning on a single GPU for Zero-shot retail product image classification","created":"2023-12-16","cited_by_count":3,"area":null},{"id":"2309.17164","title":"Retail-786k: a Large-Scale Dataset for Visual Entity Matching","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2402.07819","title":"A Benchmark Grocery Dataset of Realworld Point Clouds From Single View","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2509.04351","title":"Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking","created":"2025-09-04","cited_by_count":2,"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":"2409.13513","title":"Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval","created":"2024-09-20","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":"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":"2608.01794","title":"Illuminating Visual Identity in Universal Multimodal Embeddings","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2310.14063","title":"Concept-based Anomaly Detection in Retail Stores for Automatic Correction using Mobile Robots","created":"2023-10-21","cited_by_count":0,"area":null},{"id":"2312.07482","title":"Classification of retail products: From probabilistic ranking to neural networks","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2410.21237","title":"Hierarchical Knowledge Graph Construction from Images for Scalable E-Commerce","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2503.07853","title":"Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2511.10276","title":"RoboBenchMart: Benchmarking Robots in Retail Environment","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2512.04888","title":"ZeBROD: Zero-Retraining Based Recognition and Object Detection Framework","created":"2025-12-04","cited_by_count":0,"area":null}],"next_cursor":null}