In this paper, we introduce Recipe1M+, a new large-scale, structured corpus of over one million cooking recipes and 13 million food images. As the largest publicly available collection of recipe ...data, Recipe1M+ affords the ability to train high-capacity models on aligned, multimodal data. Using these data, we train a neural network to learn a joint embedding of recipes and images that yields impressive results on an image-recipe retrieval task. Moreover, we demonstrate that regularization via the addition of a high-level classification objective both improves retrieval performance to rival that of humans and enables semantic vector arithmetic. We postulate that these embeddings will provide a basis for further exploration of the Recipe1M+ dataset and food and cooking in general. Code, data and models are publicly available.<xref rid="fn1" ref-type="fn"> 1 1.
http://im2recipe.csail.mit.edu .
The need of increasing trustworthiness and transparency in artificial intelligence (AI)-based systems that adhere ethical principles of respect for human autonomy, prevention of harm, fairness, and ...explainability; has boosting the development of systems that incorporate such issues as a key component. Recommender systems (RSs) are included in such AI-based systems, because they use intelligent algorithms for providing the most suitable items to active users according to other users’ preferences. The RSs success is based on how much customers trust on the system, therefore recommendation explainability has become a crucial dimension for RSs adoption in real-world scenarios. Among the different successful applications of RS, it is remarkable the recent and exponential importance of recommendations for health and wellness areas. Hence, this paper aims at exploring, adapting and applying explanations for nutrition/recipes recommendations, that not only explain why the recommendation is enjoyable but also, it is aware of how healthy is the recommendation. Among the different methodologies to explain recommendations, this paper is focused on post-hoc explainability approaches and its adaptation, application and evaluation for nutrition/recipes recommendation. Eventually, it is included a comprehensive experimental study for characterizing the strengths and weaknesses of such explainability approaches in the recipe recommendation context.
•Adaptation of post-hoc recommendation explanation approaches to the recipe domain.•Integration of nutritional knowledge into the explainable recipe recommendation approaches.•The evaluation of the proposed approaches with and without nutritional knowledge.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
In the Kitchen, 1550-1800 Nunn, Hillary; Bassnett, Madeline
2022, 20221110, 2022-11-10, Volume:
4
eBook
In the Kitchen insists that the preparation of food, whether imaginative, physical, or spatial, is central to a deeper understanding of early modern food cultures and practices. Devoted to the arts ...of cooking and medicine, early modern kitchens concentrated on producing, processing, and preserving materials necessary for nourishment and survival; yet they also fed social and economic networks and nurtured a sense of physical, spiritual, and political connection to surrounding lands and their cultures. The essays in this volume illuminate this expansive view of cooking and aspire to show how the kitchen's inner workings prove tightly, though often invisibly, interwoven with local, national, and, increasingly, global surroundings. Engaging with literary and historical methodologies, including close reading, recipe analysis, and perspectives on gender, class, race, and colonialism, we begin to develop a shared theoretical and practical language for the art of cooking that combines the physical with the intellectual, the local with the global, and the domestic with the political.
This extended abstract presents the 7th International Workshop on Data Engineering Meets Intelligent Food & Cooking Recipes 2024, which will be held in conjunction with the 40th IEEE International ...Conference on Data Engineering 2024 (ICDE). The primary aim of this workshop is to provide a comprehensive overview of the latest advancements and existing challenges at the intersection of Data Engineering and Intelligent Food & Cooking Recipes.
Overview of the 3rd DECOR Workshop Andres, Frederic; Ghinea, Gheorghita; Grosky, William ...
2020 IEEE 36th International Conference on Data Engineering Workshops (ICDEW),
2020-April
Conference Proceeding
Open access
This extended abstract introduces the 3rd International Workshop on Data Engineering Meets Intelligent Food Cooking Recipes 2020 in conjunction with the 36th IEEE International Conference on Data ...Engineering 2020 (ICDE). The objectives of this workshop were to review the current development and challenges at the crossroad of data engineering and Intelligent Food amp Cooking Recipes.
In previous recipe sites, these have shown search results in list format. However, in the indeterminate desire, the user's difficult to create an apposite query and narrow their search results. And ...the user have various context. Because of that, the users often do not satisfy the top results. In this paper, we describe an application system using a virtual three-dimensional space for searching many recipes and finding a recipe that meets user's demand. The sphere objects that represent the recipes of search results place in three-dimensional space. And users can choose the recipe by overlooking and giving recipes a once-over. This system enables users to overlook the recipe results and produces the new experience for searching recipes.
RecipeScape Chang, Minsuk; Guillain, Leonore V.; Jung, Hyeungshik ...
Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems,
04/2018
Conference Proceeding
For cooking professionals and culinary students, understanding cooking instructions is an essential yet demanding task. Common tasks include categorizing different approaches to cooking a dish and ...identifying usage patterns of particular ingredients or cooking methods, all of which require extensive browsing and comparison of multiple recipes. However, no existing system provides support for such in-depth and at-scale analysis. We present RecipeScape, an interactive system for browsing and analyzing the hundreds of recipes of a single dish available online. We also introduce a computational pipeline that extracts cooking processes from recipe text and calculates a procedural similarity between them. To evaluate how RecipeScape supports culinary analysis at scale, we conducted a user study with cooking professionals and culinary students with 500 recipes for two different dishes. Results show that RecipeScape clusters recipes into distinct approaches, and captures notable usage patterns of ingredients and cooking actions.
The paper takes stock of the main successes and failures notched up by the SSNTD discipline over the past half-century or so since its inception. Its strengths stem chiefly from factors such as its ...simplicity, the small geometry of its detectors, the fact that many natural crystals have kept a record of the spontaneous fission of uranium and trans-uranic elements, as well as heavy cosmic rays, over some billions of years. The fact, additionally, that high temperatures can diminish the lengths of latent tracks in a systematic way leads to useful information that can be gleaned regarding the thermal history of rocks, etc. The weaknesses of SSNTD techniques, on the other hand, arise mainly from drawbacks such as a lack of capability for real-time data assessment, poor charge and energy spectrometry of incident particles, and lack of any penetrating understanding of the underlying mechanisms—which results in a lot of data being collected for its own sake, furnishing little insight to the research workers.
The paper ends by examining areas where as-yet unexploited potential exists, in the reviewer's opinion, for further discoveries, continuing developments, and challenging opportunities for successful new or improved applications and breakthroughs. These include geological and environmental fields, earthquake prediction, medical and life-science studies, automation, and exotic phenomena, amongst others.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK