Venue: Dublin, Ireland —— Date: 28 October, 2025
Host: The MMFood’25 workshop will be hosted on-site at the 33rd ACM International Conference on Multimedia (ACMMM25).
Acknowledgement: This workshop has been supported by the Mphasis AI & Applied Tech Lab at Ashoka - a collaboration between Ashoka University and Mphasis Limited (India).
Contact: mmfood.contact@gmail.com
Virtual Participation
In case you aren't able to attend the MMFood'25 workshop in person and/or are presenting your work online, we welcome you to join the MMFood'25 workshop online. The virtual participation details are as follows:
📅 Time: Oct 28, 2025, 9:00 AM GMT/UTC
🔗 Join Zoom Meeting: https://zoom.us/j/93429559023?pwd=VMdiNbVnrXukRuB3GJbilqxIWVxjQm.1
💬 Meeting ID: 934 2955 9023
🔒 Passcode: smgqsdr
Please note that you may need to enter the passcode only if you do not join the zoom meeting online by logging in.
Important Note: Ireland has switched off the Daylight Savings Time on the 26th Oct. 2025. Accordingly, Ireland is now using GMT/UTC + 0 (not GMT/UTC + 1 as during the summers). The meeting time mentioned above reflects this update. Please plan accordingly.
Program Schedule
-
09:00 - 09:10
Chair’s Address - Day's Program
-
09:15 - 10:30
Keynote Talk by Prof. Ganesh Bagler
Computational Gastronomy - The Emerging Science of Food, Flavors, Nutrition, and Personalized Health
-
10:30 - 11:00
Morning Tea
-
11:00 - 12:30
Full Paper Presentations
12 minutes each – including Q&A
What we talk about when we talk about food experiences
Yihan Kang, Shu Zhong, Sriram Subramanian and Marianna Obrist
Blockchain-Based Paddy Crop Marketplace: Enhancing Farmer-Buyer Trust Through Smart Contracts
A Kandasamy, Chandrasekaran K, Usha Divakarla and Mohan Krishna
FLICSNet: A Novel Framework for Cooking Action Segmentation from Video
Sandeep Khanna, Chiranjoy Chattopadhyay and Suman Kundu
Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation
Lubnaa Abdur Rahman, Ioannis Papathanail and Stavroula Mougiakakou
Extending FKG.in: Towards A Food Claim Traceability Network
Saransh Kumar Gupta, Rizwan Gulzar Mir, Lipika Dey, Partha Pratim Das, Anirban Sen and Ramesh Jain
Contextualized Food Planning for Fluoride Toxicity Mitigation Using Multimodal Data
Tiyasa Das, Monojit Samajder and Chandreyee Das
TATVA: Turmeric Adulteration Detection using Thermal Video Analysis
Rupinder Kaur, Shahbaz Ahmad Khanday, Simrandeep Singh, Uday Thakur, Ashish Verma and Mukesh Saini
-
12:30 - 13:30
Lunch
-
13:30 - 14:15
Invited Talk by Dr. Adarsh Nadig
There is Nothing Artificial About Taste Intelligence
-
14:15 - 14:45
Short Paper Presentations
5 Minutes Lightning Pitch
Diffusion-Guided 3D-Aware Calorie Estimation from a Single Food Image
Mayu Ogishi, Hikaru Tanabe and Keiji Yanai
Food Nutrient Estimation Based on a Dual-directional Self-attention Aggregation Enhanced Inception Model
Aixue Shen, Xian-Hua Han, Xu Qiao, Ke Liu, Jiande Sun and Jian Wang
What’s Not on the Plate? Rethinking Food Computing through Indigenous Indian Datasets
Pamir Gogoi, Neha Joshi, Ayushi Pandey, Deepthi Sudharsan, Saransh Kumar Gupta, Lipika Dey, Partha Pratim Das, Kalika Bali and Vivek Seshadri
Decoupled Clip and Dynamic Sampling Policy Optimization for Food Reasoning Segmentation
Hikaru Tanabe and Keiji Yanai
Towards an Action-Centric Ontology for Cooking Procedures Using Temporal Graphs
Aarush Kumbhakern, Saransh Kumar Gupta, Lipika Dey and Partha Pratim Das
-
15:00 - 15:30
Afternoon Tea
-
15:30 - 16:30
Panel Discussion
Multimodal Food Computing - Bridging Cultural Heritage, Artificial Intelligence, and Sustainable Food Futures
-
16:30 - 16:45
Closing Remarks
-
16:45 - 18:30
Poster Session
Legend
News
The program details and schedule for the MMFood'25 workshop have been announced. Click here to know more.
The accepted papers for the MMFood'25 workshop have been announced. Congratulations to all the authors! Click here to know more.
In addition to the full papers (4–8 pages), we also invite short papers (up to 4 pages) that present early-stage work, novel ideas, or innovative applications. More information can be found here.
The deadline for new paper submissions deadline has been extended to 18th July EoD AoE (strict).
The call for papers is open now for MMFood'25! Click here to know more.
The MMFood'25 program details will be available soon on the website.
Overview
This Multi-modal Food Computing (MMFood’25) workshop will explore the intersection of AI, computer vision, natural language processing, and sensory modeling in understanding food. It aims to advance multimodal methods for food recognition, recommendation, and analysis, addressing challenges in health, nutrition, and sustainability. By bringing together researchers from AI, food science, health informatics, computational social science, and human-computer interaction (HCI), this workshop will foster interdisciplinary collaboration to drive innovation in multimodal food computing.
Several past workshops have addressed specific aspects of food computing but lacked a comprehensive focus on multimodality in food. Our goal is to establish a broader, more inclusive initiative, starting with a full-day workshop and evolving it into a major activity under SIGMM: ACM Special Interest Group on Multimedia.
Multimodal Food Computing
Food computing is inherently multimodal, integrating vision, smell, taste, touch, and language with computational methods to acquire and analyze diverse food-related data. Our perception of food is shaped by multiple sensory inputs and cognitive associations, making food a uniquely multimodal experience. Advances in artificial intelligence, computer vision, natural language processing, and sensory modeling have enabled new ways to recognize, retrieve, recommend, predict, and monitor food, addressing key challenges in health, nutrition, sustainability, and food culture.
In light of AI’s growing role in food-related industries — from healthcare and nutrition to sustainability and agroecology — multimodal food computing presents a natural and promising progression into exciting opportunities for both fundamental as well as applied research. Food perception and decision-making involve a fusion of sensory inputs — vision, smell, taste, touch — combined with language, memory, and social influences. Beyond personal choices, geographic, cultural, and socio-economic factors shape food systems and dietary habits, further amplified by digital communities, social media trends, and AI-driven personalization.
This opens up vast opportunities for food computing researchers to harness the power of multimodal intelligence! The ambition of this workshop is to bring together researchers and practitioners working on a wide range of problems related to food computing using various types of food data. It will provide a platform to brainstorm on critical global food-related problems and exchange ideas on how multimodal information can be leveraged to solve them.
Workshop Scope
This workshop will explore multimodal innovations centering food at the intersection of (including but not limited to):
- Computer Vision (e.g., food recognition, portion estimation, visual appeal analysis)
- Natural Language Processing (NLP) & Large Language Models (LLMs) (e.g., food descriptions, opinions, recipe generation, dietary guidelines)
- Machine Learning & AI Planning (e.g., personalized food recommendations, assessing dietary adherence, problems related to food supply-chain and associated logistics)
- Sensory Science & Multisensory AI (e.g., perception modeling of taste, smell, texture and other dimensions of food)
- Behavioral & Social Computing (e.g., analysis of food trends, digital food communities, understanding cultural influences, detecting early warning signals of food safety and security for risk analysis)
It will also address technical and ethical challenges, such as:
- Data standardization across diverse modalities (images, text, nutrition, biometrics)
- Interpretability of AI-driven food recommendations and their impact
- Ensuring inclusivity in AI-powered food solutions across populations, dietary needs, and eating cultures