{"total":16,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2311.05804","title":"Model-as-a-Service (MaaS): A Survey","created":"2023-11-10","cited_by_count":25,"area":null},{"id":"2404.16260","title":"OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search","created":"2024-04-25","cited_by_count":13,"area":null},{"id":"2205.02411","title":"Relational Representation Learning in Visually-Rich Documents","created":"2022-05-05","cited_by_count":11,"area":null},{"id":"2407.07518","title":"Multi-modal Crowd Counting via a Broker Modality","created":"2024-07-10","cited_by_count":11,"area":null},{"id":"2302.11052","title":"Que2Engage: Embedding-based Retrieval for Relevant and Engaging Products at Facebook Marketplace","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2304.02853","title":"Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce","created":"2023-04-06","cited_by_count":8,"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":"2410.17337","title":"Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data","created":"2024-10-22","cited_by_count":6,"area":null},{"id":"2302.05093","title":"Unified Vision-Language Representation Modeling for E-Commerce Same-Style Products Retrieval","created":"2023-02-10","cited_by_count":5,"area":null},{"id":"2306.02928","title":"LRVS-Fashion: Extending Visual Search with Referring Instructions","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2408.02978","title":"ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval","created":"2024-08-06","cited_by_count":1,"area":null},{"id":"2208.00955","title":"Large-Scale Product Retrieval with Weakly Supervised Representation Learning","created":"2022-08-01","cited_by_count":0,"area":null},{"id":"2501.14826","title":"Multi-Modality Transformer for E-Commerce: Inferring User Purchase Intention to Bridge the Query-Product Gap","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2511.05325","title":"Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2605.18434","title":"TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval","created":"2026-05-18","cited_by_count":0,"area":null}],"next_cursor":null}