{"total":35,"rows":[{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75,"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":"2108.01361","title":"Cycle-Consistent Inverse GAN for Text-to-Image Synthesis","created":"2021-08-03","cited_by_count":27,"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":"2108.04533","title":"ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer","created":"2021-08-10","cited_by_count":11,"area":null},{"id":"2409.12010","title":"ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation","created":"2024-09-18","cited_by_count":11,"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":"2103.08397","title":"Metric Learning for Anti-Compression Facial Forgery Detection","created":"2021-03-15","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":"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":"2108.06458","title":"Cross-Modal Graph with Meta Concepts for Video Captioning","created":"2021-08-14","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":"2402.09242","title":"Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection","created":"2024-02-14","cited_by_count":3,"area":null},{"id":"2103.06032","title":"Cross-modal Image Retrieval with Deep Mutual Information Maximization","created":"2021-03-10","cited_by_count":2,"area":null},{"id":"2203.15778","title":"Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method","created":"2022-03-29","cited_by_count":2,"area":null},{"id":"2103.04731","title":"Self-Augmented Multi-Modal Feature Embedding","created":"2021-03-08","cited_by_count":1,"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":"2211.16208","title":"SLAN: Self-Locator Aided Network for Cross-Modal Understanding","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2408.13358","title":"Shape-Preserving Generation of Food Images for Automatic Dietary Assessment","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2509.06006","title":"Khana: A Comprehensive Indian Cuisine Dataset","created":"2025-09-07","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":"2205.02141","title":"RecipeSnap -- a lightweight image-to-recipe model","created":"2022-05-04","cited_by_count":0,"area":null},{"id":"2212.10939","title":"Joint Embedding of 2D and 3D Networks for Medical Image Anomaly Detection","created":"2022-12-21","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":"2405.19606","title":"Relation Modeling and Distillation for Learning with Noisy Labels","created":"2024-05-30","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}