{"total":75,"rows":[{"id":"2108.06781","title":"Online Continual Learning For Visual Food Classification","created":"2021-08-15","cited_by_count":39,"area":null},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2312.14991","title":"FoodLMM: A Versatile Food Assistant using Large Multi-modal Model","created":"2023-12-22","cited_by_count":32,"area":"mllm"},{"id":"2502.11748","title":"ILIAS: Instance-Level Image retrieval At Scale","created":"2025-02-17","cited_by_count":30,"area":"mllm"},{"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":"2402.15761","title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","created":"2024-02-24","cited_by_count":22,"area":"ssm"},{"id":"2307.00183","title":"Long-Tailed Continual Learning For Visual Food Recognition","created":"2023-07-01","cited_by_count":20,"area":null},{"id":"2210.14748","title":"Long-tailed Food Classification","created":"2022-10-26","cited_by_count":19,"area":null},{"id":"2308.05938","title":"FoodSAM: Any Food Segmentation","created":"2023-08-11","cited_by_count":19,"area":null},{"id":"2202.05491","title":"Exemplar-free Online Continual Learning","created":"2022-02-11","cited_by_count":18,"area":null},{"id":"2309.08912","title":"Delving into Multimodal Prompting for Fine-grained Visual Classification","created":"2023-09-16","cited_by_count":14,"area":null},{"id":"2604.12012","title":"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment","created":"2026-04-13","cited_by_count":13,"area":"mllm"},{"id":"2406.05814","title":"TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models","created":"2024-06-09","cited_by_count":12,"area":"mllm"},{"id":"2406.10318","title":"Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding","created":"2024-06-14","cited_by_count":11,"area":"mllm"},{"id":"2307.00182","title":"Single-Stage Heavy-Tailed Food Classification","created":"2023-07-01","cited_by_count":10,"area":null},{"id":"2310.11702","title":"DPF-Nutrition: Food Nutrition Estimation via Depth Prediction and Fusion","created":"2023-10-18","cited_by_count":10,"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":"2412.14233","title":"Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2108.02947","title":"A review on vision-based analysis for automatic dietary assessment","created":"2021-08-06","cited_by_count":9,"area":null},{"id":"2111.05956","title":"Feature Generation for Long-tail Classification","created":"2021-11-10","cited_by_count":9,"area":null},{"id":"2203.05306","title":"GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grains","created":"2022-03-10","cited_by_count":9,"area":null},{"id":"2403.07403","title":"From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios","created":"2024-03-12","cited_by_count":9,"area":null},{"id":"2407.09285","title":"MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction: Methods and Results","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2411.10492","title":"MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Clouds","created":"2024-11-14","cited_by_count":9,"area":null},{"id":"2406.08332","title":"UDON: Universal Dynamic Online distillatioN for generic image representations","created":"2024-06-12","cited_by_count":8,"area":"distill"},{"id":"2504.06925","title":"Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition","created":"2025-04-09","cited_by_count":7,"area":"mllm"},{"id":"2310.04689","title":"SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection","created":"2023-10-07","cited_by_count":6,"area":"diffusion"},{"id":"2304.05619","title":"NutritionVerse-3D: A 3D Food Model Dataset for Nutritional Intake Estimation","created":"2023-04-12","cited_by_count":5,"area":null},{"id":"2311.11901","title":"Identifying the Defective: Detecting Damaged Grains for Cereal Appearance Inspection","created":"2023-11-20","cited_by_count":5,"area":null},{"id":"2403.07356","title":"Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2404.01409","title":"OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2211.07440","title":"Leveraging Automatic Personalised Nutrition: Food Image Recognition Benchmark and Dataset based on Nutrition Taxonomy","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2309.00199","title":"Diffusion Model with Clustering-based Conditioning for Food Image Generation","created":"2023-09-01","cited_by_count":4,"area":"diffusion"},{"id":"2309.01075","title":"Muti-Stage Hierarchical Food Classification","created":"2023-09-03","cited_by_count":4,"area":null},{"id":"2408.14135","title":"Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models","created":"2024-08-26","cited_by_count":4,"area":"diffusion"},{"id":"2309.06308","title":"AI4Food-NutritionFW: A Novel Framework for the Automatic Synthesis and Analysis of Eating Behaviours","created":"2023-09-12","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":"2411.08715","title":"Retrieval Augmented Recipe Generation","created":"2024-11-13","cited_by_count":3,"area":"mllm"},{"id":"2306.01747","title":"UMDFood: Vision-language models boost food composition compilation","created":"2023-05-18","cited_by_count":2,"area":"mllm"},{"id":"2308.03272","title":"Feature-Suppressed Contrast for Self-Supervised Food Pre-training","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2309.07704","title":"NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches","created":"2023-09-14","cited_by_count":2,"area":null},{"id":"2405.05853","title":"Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2501.04150","title":"Benchmarking Large and Small MLLMs","created":"2025-01-04","cited_by_count":2,"area":"mllm"},{"id":"2507.04412","title":"SFOOD: A Multimodal Benchmark for Comprehensive Food Attribute Analysis Beyond RGB with Spectral Insights","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2508.12137","title":"Infusing fine-grained visual knowledge to Vision-Language Models","created":"2025-08-16","cited_by_count":2,"area":"mllm"},{"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":"2604.12356","title":"OmniFood8K: Single-Image Nutrition Estimation via Hierarchical Frequency-Aligned Fusion","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2206.01153","title":"Multi-View Active Fine-Grained Recognition","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2305.07257","title":"A Central Asian Food Dataset for Personalized Dietary Interventions, Extended Abstract","created":"2023-05-12","cited_by_count":1,"area":null},{"id":"2308.11452","title":"Food Image Classification and Segmentation with Attention-based Multiple Instance Learning","created":"2023-08-22","cited_by_count":1,"area":null},{"id":"2407.03463","title":"Precision at Scale: Domain-Specific Datasets On-Demand","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2408.03922","title":"FMiFood: Multi-modal Contrastive Learning for Food Image Classification","created":"2024-08-07","cited_by_count":1,"area":null},{"id":"2412.20370","title":"Differential Evolution Integrated Hybrid Deep Learning Model for Object Detection in Pre-made Dishes","created":"2024-12-29","cited_by_count":1,"area":null},{"id":"2501.15998","title":"Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2503.05228","title":"RecipeGen: A Benchmark for Real-World Recipe Image Generation","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2503.18997","title":"Improving Food Image Recognition with Noisy Vision Transformer","created":"2025-03-24","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":"2512.21860","title":"Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models","created":"2025-12-26","cited_by_count":1,"area":"mllm"},{"id":"2210.14147","title":"Food Ingredients Recognition through Multi-label Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2503.06647","title":"Personalized Class Incremental Context-Aware Food Classification for Food Intake Monitoring Systems","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2503.18548","title":"Benchmarking Post-Hoc Unknown-Category Detection in Food Recognition","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2507.22057","title":"MetaLab: Few-Shot Game Changer for Image Recognition","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2508.03996","title":"Investigating the Impact of Large-Scale Pre-training on Nutritional Content Estimation from 2D Images","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.03873","title":"SalientFusion: Context-Aware Compositional Zero-Shot Food Recognition","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.19028","title":"Weakly Supervised Food Image Segmentation using Vision Transformers and Segment Anything Model","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.21199","title":"3rd Place Solution to Large-scale Fine-grained Food Recognition","created":"2025-10-24","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":"2601.07970","title":"Sesame Plant Segmentation Dataset: A YOLO Formatted Annotated Dataset","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2603.23034","title":"Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment","created":"2026-03-24","cited_by_count":0,"area":"driving"},{"id":"2606.04986","title":"Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2607.06185","title":"Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition","created":"2026-07-07","cited_by_count":0,"area":"mllm"},{"id":"2607.12911","title":"Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition","created":"2026-07-14","cited_by_count":0,"area":"mllm"},{"id":"2607.25794","title":"Fine-Grained Food Image Understanding via Target-Aware Data Alignment","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.03428","title":"OliveGemma: A 3 Billion Visual Language Model for Recognising the Mediterranean & European Diet","created":"2026-08-04","cited_by_count":0,"area":"mllm"}],"next_cursor":null}