Yang Longqi, Hsieh Cheng-Kang, Yang Hongjian, Pollak John P, Dell Nicola, Belongie Serge, Cole Curtis, Estrin Deborah
2 West Loop Road, NY, NY 10044, Department of Computer Science, Cornell Tech, Cornell University.
4732 Boelter Hall, Los Angeles, CA 90095, Department of Computer Science, UCLA.
ACM Trans Inf Syst. 2017 Aug;36(1). doi: 10.1145/3072614.
Nutrient-based meal recommendations have the potential to help individuals prevent or manage conditions such as diabetes and obesity. However, learning people's food preferences and making recommendations that simultaneously appeal to their palate and satisfy nutritional expectations are challenging. Existing approaches either only learn high-level preferences or require a prolonged learning period. We propose , a personalized nutrient-based meal recommender system designed to meet individuals' nutritional expectations, dietary restrictions, and fine-grained food preferences. Yum-me enables a simple and accurate food preference profiling procedure via a visual quiz-based user interface and projects the learned profile into the domain of nutritionally appropriate food options to find ones that will appeal to the user. We present the design and implementation of Yum-me and further describe and evaluate two innovative contributions. The first contriution is an open source state-of-the-art food image analysis model, named . We demonstrate FoodDist's superior performance through careful benchmarking and discuss its applicability across a wide array of dietary applications. The second contribution is a novel online learning framework that learns food preference from itemwise and pairwise image comparisons. We evaluate the framework in a field study of 227 anonymous users and demonstrate that it outperforms other baselines by a significant margin. We further conducted an end-to-end validation of the feasibility and effectiveness of Yum-me through a 60-person user study, in which Yum-me improves the recommendation acceptance rate by 42.63%.
基于营养的膳食建议有潜力帮助个人预防或管理糖尿病和肥胖等疾病。然而，了解人们的食物偏好并做出既能吸引他们的味蕾又能满足营养期望的建议具有挑战性。现有方法要么只学习高层次的偏好，要么需要较长的学习时间。我们提出了Yum-me，这是一个基于营养的个性化膳食推荐系统，旨在满足个人的营养期望、饮食限制和细粒度的食物偏好。Yum-me通过基于视觉问答的用户界面实现了一个简单而准确的食物偏好分析过程，并将学习到的分析结果投射到营养适宜的食物选项领域，以找到能吸引用户的食物。我们展示了Yum-me的设计与实现，并进一步描述和评估了两项创新成果。第一项成果是一个名为FoodDist的开源先进食物图像分析模型。我们通过仔细的基准测试证明了FoodDist的卓越性能，并讨论了它在广泛的饮食应用中的适用性。第二项成果是一个新颖的在线学习框架，它从按项目和成对的图像比较中学习食物偏好。我们在对227名匿名用户的实地研究中评估了该框架，并证明它比其他基线有显著优势。我们还通过一项60人的用户研究对Yum-me的可行性和有效性进行了端到端验证，其中Yum-me将推荐接受率提高了42.63%。
