CVPR 2025 Open Access Repository

2nd MetaFood Workshop

VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction: Ahmad AlMughrabi,

Umair Haroon,

Ricardo Marques,

Petia Radeva; [pdf] [arXiv]
[bibtex]
@InProceedings{AlMughrabi_2025_CVPR, author = {AlMughrabi, Ahmad and Haroon, Umair and Marques, Ricardo and Radeva, Petia}, title = {VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {450-457} }
SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos: Joshua Li,

Fernando Jose Pena Cantu,

Emily Yu,

Alexander Wong,

Yuchen Cui,

Yuhao Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_CVPR, author = {Li, Joshua and Cantu, Fernando Jose Pena and Yu, Emily and Wong, Alexander and Cui, Yuchen and Chen, Yuhao}, title = {SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {467-473} }
Decomposing Food Images for Better Nutrition Analysis: A Nutritionist-Inspired Two-Step Multimodal LLM Approach: Pitikorn Khlaisamniang,

Kun Kerdthaisong,

Supasate Vorathammathorn,

Nutchanon Yongsatianchot,

Hirunkul Phimsiri,

Amrest Chinkamol,

Teermade Thitseesaeng,

Kanyakorn Veerakanjana,

Kaisorn Kachai,

Piyalitt Ittichaiwong,

Tossaporn Saengja; [pdf] [supp]
[bibtex]
@InProceedings{Khlaisamniang_2025_CVPR, author = {Khlaisamniang, Pitikorn and Kerdthaisong, Kun and Vorathammathorn, Supasate and Yongsatianchot, Nutchanon and Phimsiri, Hirunkul and Chinkamol, Amrest and Thitseesaeng, Teermade and Veerakanjana, Kanyakorn and Kachai, Kaisorn and Ittichaiwong, Piyalitt and Saengja, Tossaporn}, title = {Decomposing Food Images for Better Nutrition Analysis: A Nutritionist-Inspired Two-Step Multimodal LLM Approach}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {482-491} }
Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction: Riddhi Jain,

Manasi Patwardhan,

Aayush Mishra,

Parijat Deshpande,

Beena Rai; [pdf]
[bibtex]
@InProceedings{Jain_2025_CVPR, author = {Jain, Riddhi and Patwardhan, Manasi and Mishra, Aayush and Deshpande, Parijat and Rai, Beena}, title = {Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {411-419} }
Stochastic-based Patch Filtering for Few-Shot Learning: Javier Ródenas Cumplido,

Eduardo Aguilar,

Petia Radeva; [pdf]
[bibtex]
@InProceedings{Cumplido_2025_CVPR, author = {Cumplido, Javier R\'odenas and Aguilar, Eduardo and Radeva, Petia}, title = {Stochastic-based Patch Filtering for Few-Shot Learning}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {440-449} }
Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification: GaYeon Koh,

Hyun-Jic Oh,

Jeonghyun Noh,

Won-Ki Jeong; [pdf] [arXiv]
[bibtex]
@InProceedings{Koh_2025_CVPR, author = {Koh, GaYeon and Oh, Hyun-Jic and Noh, Jeonghyun and Jeong, Won-Ki}, title = {Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {391-400} }
Agro-Net: A Convolution-Attention Fusion based hyperspectral model for agro-food quality assessment: Ocean Monjur,

Md. Toukir Ahmed,

Md Wadud Ahmed,

Mohammed Kamruzzaman; [pdf]
[bibtex]
@InProceedings{Monjur_2025_CVPR, author = {Monjur, Ocean and Ahmed, Md. Toukir and Ahmed, Md Wadud and Kamruzzaman, Mohammed}, title = {Agro-Net: A Convolution-Attention Fusion based hyperspectral model for agro-food quality assessment}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {474-481} }
Food Degradation Analysis Using Multimodal Fuzzy Clustering: Julio Valdes,

Stephie Liu,

Shawn Yang,

Yuhao Chen,

Alexander Wong,

Pengcheng Xi; [pdf] [supp]
[bibtex]
@InProceedings{Valdes_2025_CVPR, author = {Valdes, Julio and Liu, Stephie and Yang, Shawn and Chen, Yuhao and Wong, Alexander and Xi, Pengcheng}, title = {Food Degradation Analysis Using Multimodal Fuzzy Clustering}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {420-429} }
Extra-Lightweight AI-Based Privacy Preserving Framework for Egocentric Wearable Cameras: Long Li,

Fengqing Zhu,

Heather Eicher-Miller,

J. Graham Thomas,

Yuning Huang,

Edward Sazonov; [pdf]
[bibtex]
@InProceedings{Li_2025_CVPR, author = {Li, Long and Zhu, Fengqing and Eicher-Miller, Heather and Thomas, J. Graham and Huang, Yuning and Sazonov, Edward}, title = {Extra-Lightweight AI-Based Privacy Preserving Framework for Egocentric Wearable Cameras}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {401-410} }
FoodVideoQA: A Novel Baseline Framework for Dietary Monitoring: Krish Shah,

Siddharth Viswanath,

Pengcheng Xi,

Alexander Wong,

Yuhao Chen; [pdf]
[bibtex]
@InProceedings{Shah_2025_CVPR, author = {Shah, Krish and Viswanath, Siddharth and Xi, Pengcheng and Wong, Alexander and Chen, Yuhao}, title = {FoodVideoQA: A Novel Baseline Framework for Dietary Monitoring}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {458-466} }
Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition: Sergio Romero-Tapiador,

Ruben Tolosana,

Blanca Lacruz-Pleguezuelos,

Laura Judith Marcos-Zambrano,

Guadalupe X. Bazán,

Isabel Espinosa-Salinas,

Julian Fierrez,

Javier Ortega-Garcia,

Enrique Carrillo de Santa Pau,

Aythami Morales; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Romero-Tapiador_2025_CVPR, author = {Romero-Tapiador, Sergio and Tolosana, Ruben and Lacruz-Pleguezuelos, Blanca and Marcos-Zambrano, Laura Judith and Baz\'an, Guadalupe X. and Espinosa-Salinas, Isabel and Fierrez, Julian and Ortega-Garcia, Javier and de Santa Pau, Enrique Carrillo and Morales, Aythami}, title = {Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {430-439} }