CulturalMenuBench is a new benchmark comprising 4,870 culinary items in 10 languages across 18 regions, designed to test multimodal language models on tasks that combine dish recognition, step-by-step cooking images, ingredients, procedural text, and regional labels. The benchmark reveals a large knowledge‑application gap: models that score over 94% on standard multiple‑choice questions fall to at most 56% when attributing dishes to Chinese regional cuisines, indicating that cultural knowledge is present but not activated by visual input. Diagnostic analyses show that accuracy is driven by visual distinctiveness rather than cultural structure, and that removing sequential cooking images selectively harms process‑grounded tasks, confirming the need for procedural evidence.
By Bo Zeng, Linfeng Gao, Peiqin Lin, Yu Zhao, Mingyan Zeng, Yu Tong, Xintong Wang, Linlong Xu, Longyue Wang, Weihua Luo, Qinggang Zhang, Jinsong Su
Fine-grained food image retrieval is a key task in computational gastronomy, with applications in food traceability, dietary monitoring, and smart catering systems. Although hashing-based retrieval is attractive for large-scale search due to its storage efficiency and fast Hamming-distance computation, existing methods often perform poorly in fine-grained food scenarios, where subtle local semantics and frequency-sensitive visual cues are essential.
arXiv:2608. 03428v1 Announce Type: cross Abstract: Image based dietary assessment offers a scalable alternative to self reported food diaries, yet fine-grained food recognition remains challenging due to high intra-class variability and visually similar dishes.
By Dimitrios I. Zaridis, Traianos Tsiokris, Vasileios C. Pezoulas, Daphni Plati, Eugenia Mylona, Eleni Georga, Nikos Tsiknakis, Antonis Sakellarios, Dimitrios I. Fotiadis
arXiv:2609.22099v1 Announce Type: new
Abstract: Cooking is a complex process that transforms raw ingredients into delicious and nutritious dishes, yet the recipes that encode this process remain larg...
By Mansi Goel, Sumit Bhagat, Saloni Srivastava, Malav Patel, Shlok Vinodkumar Mehroliya, Ganesh Bagler
arXiv:2608. 06917v1 Announce Type: new Abstract: Recent Large Multimodal Models (LMMs) have achieved impressive performance in recipe generation from food images.
By Guoshan Liu, Bin Zhu, Pengkun Jiao, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang
NutriVision is an end‑to‑end framework that estimates calories, mass, fat, carbohydrates, and protein from a single RGB image and optional ingredient list. It generates depth information with DepthAnything‑V3, encodes ingredient descriptions via CLIP, and fuses visual geometry and ingredient semantics through an Ingredient‑Conditioned Frequency‑Aligned Fusion Module, an Ingredient‑Aware Mask‑based Prediction Head, and modality‑specific Internal Semantic Modeling blocks. On the Nutrition5k dataset, NutriVision achieves a mean PMAE of 13.60 ± 0.10 %, outperforming prior methods by significant margins.
By Avinash Anand, Aman Kumar, Chaitanya Lakhchaura, Ashutosh Kumar, Akshita Abrol, Timothy Liu, Zhengkui Wang
arXiv:2609.37230v1 Announce Type: cross
Abstract: Visual distinctions are often finer than those reflected in linguistic conceptualization. Vision-language models exhibit a similar asymmetry: a disti...
By Woosang Jeon, Jiwon Yang, Soo Chung, Taehyeong Kim
ConstraintMatch is a training‑free inference technique that improves image‑text matching by enforcing entity‑level regional consistency. It compares independent crop selections for each category and attribute against a shared crop choice within each entity, using the resulting gap as a matching cost. The method calibrates spatial references, clips per‑entity residuals, and subtracts a scaled mean cost from global similarity, achieving significant gains over global matching and SGI across multiple benchmarks.
By Yuhong Zhou, Yubo Gao, Xiangbo Shu
arXiv:2607. 18237v1 Announce Type: cross Abstract: Human visual similarity judgments are context-dependent.
By Sheng-Yu Wang, Yotam Nitzan, Aaron Hertzmann, Jun-Yan Zhu, Eli Shechtman, Alexei A. Efros, Richard Zhang
CRISP (Compositional Relational Invariance from Spatial Primitives) is an image‑classification framework that decomposes visual recognition into primitive elements and their relational composition. It represents these compositions with soft unary, binary, and ternary predicates over primitive locations and appearance, enabling differentiable spatial and visual alignment learned end‑to‑end. Evaluated on five DomainBed datasets covering style, provenance, and camera‑trap shifts, CRISP achieves new state‑of‑the‑art performance on both benchmarks.
By Dat Nguyen, Duc-Duy Nguyen
arXiv:2606. 08948v1 Announce Type: cross Abstract: Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large multimodal datasets linking diverse foods to complete nutrient profiles.
By Runze Yan, Minxiao Wang, Jiaying Lu, Darren Liu, Xiao Hu, Hanqi Luo
arXiv:2608.29249v1 Announce Type: new
Abstract: The online culinary ecosystem is increasingly populated by recipe content generated, modified, or summarized by Large Language Models (LLMs). While oft...
By Saransh Kumar Gupta, Armaan Shah, Lipika Dey, Partha Pratim Das, Ramesh Jain