{"total":23,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75,"area":null},{"id":"2307.03373","title":"All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment","created":"2023-07-07","cited_by_count":27,"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":"2312.08592","title":"Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis","created":"2023-12-14","cited_by_count":10,"area":null},{"id":"2406.10261","title":"FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination","created":"2024-06-11","cited_by_count":10,"area":null},{"id":"2302.07960","title":"Learning to Substitute Ingredients in Recipes","created":"2023-02-15","cited_by_count":8,"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":"2205.03891","title":"Cross-lingual Adaptation for Recipe Retrieval with Mixup","created":"2022-05-08","cited_by_count":3,"area":null},{"id":"2504.01321","title":"COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2601.04491","title":"A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Management","created":"2026-01-08","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":"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":"2512.18245","title":"Spectral Discrepancy and Cross-modal Semantic Consistency Learning for Object Detection in Hyperspectral Image","created":"2025-12-20","cited_by_count":1,"area":null},{"id":"2205.02141","title":"RecipeSnap -- a lightweight image-to-recipe model","created":"2022-05-04","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":"2511.16037","title":"LLMs-based Augmentation for Domain Adaptation in Long-tailed Food Datasets","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2603.09688","title":"Fusing Semantic, Lexical, and Domain Perspectives for Recipe Similarity Estimation","created":"2026-03-10","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},{"id":"2607.06148","title":"RFHNet: Relational and Frequency-Aware Hashing Network for Large-Scale Fine-Grained Food Image Retrieval","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":null}