{"total":32,"rows":[{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640,"area":null},{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2103.13061","title":"Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning","created":"2021-03-24","cited_by_count":28,"area":null},{"id":"2110.01445","title":"Robust and Decomposable Average Precision for Image Retrieval","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2110.01209","title":"Learning Structural Representations for Recipe Generation and Food Retrieval","created":"2021-10-04","cited_by_count":17,"area":null},{"id":"2203.16071","title":"Learning Program Representations for Food Images and Cooking Recipes","created":"2022-03-30","cited_by_count":16,"area":null},{"id":"2205.12396","title":"Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2106.03158","title":"Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions","created":"2021-06-06","cited_by_count":10,"area":null},{"id":"2309.08250","title":"Optimization of Rank Losses for Image Retrieval","created":"2023-09-15","cited_by_count":10,"area":null},{"id":"2304.12570","title":"Learnable Pillar-based Re-ranking for Image-Text Retrieval","created":"2023-04-25","cited_by_count":9,"area":null},{"id":"2110.11592","title":"Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2102.02547","title":"CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval","created":"2021-02-04","cited_by_count":7,"area":null},{"id":"2107.00372","title":"Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2108.00724","title":"Learning TFIDF Enhanced Joint Embedding for Recipe-Image Cross-Modal Retrieval Service","created":"2021-08-02","cited_by_count":6,"area":null},{"id":"2204.09730","title":"Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2207.14428","title":"Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval","created":"2022-07-29","cited_by_count":5,"area":null},{"id":"2304.02016","title":"The Multimodal And Modular Ai Chef: Complex Recipe Generation From Imagery","created":"2023-03-20","cited_by_count":5,"area":null},{"id":"2108.03788","title":"Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images","created":"2021-08-09","cited_by_count":4,"area":null},{"id":"2210.10628","title":"RecipeMind: Guiding Ingredient Choices from Food Pairing to Recipe Completion using Cascaded Set Transformer","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2205.03891","title":"Cross-lingual Adaptation for Recipe Retrieval with Mixup","created":"2022-05-08","cited_by_count":3,"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":"2303.00720","title":"Cross-Modal Entity Matching for Visually Rich Documents","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2205.04948","title":"Transformer-based Cross-Modal Recipe Embeddings with Large Batch Training","created":"2022-05-10","cited_by_count":1,"area":null},{"id":"2205.10592","title":"Facing the Void: Overcoming Missing Data in Multi-View Imagery","created":"2022-05-21","cited_by_count":1,"area":null},{"id":"2210.06618","title":"QMRNet: Quality Metric Regression for EO Image Quality Assessment and Super-Resolution","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2510.20393","title":"Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2108.00705","title":"Efficient Deep Feature Calibration for Cross-Modal Joint Embedding Learning","created":"2021-08-02","cited_by_count":0,"area":null},{"id":"2112.09839","title":"Calorie Aware Automatic Meal Kit Generation from an Image","created":"2021-12-18","cited_by_count":0,"area":null},{"id":"2302.01005","title":"Predefined domain specific embeddings of food concepts and recipes: A case study on heterogeneous recipe datasets","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2511.15201","title":"Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2604.15628","title":"SIMMER: Cross-Modal Food Image--Recipe Retrieval via MLLM-Based Embedding","created":"2026-04-17","cited_by_count":0,"area":null}],"next_cursor":null}