Im2Calories: Towards an Automated Mobile Vision Food Diary

By Austin Myers, Nick Johnston, Vivek Rathod, Anoop Korattikara Balan, Alexander N. Gorban, Nathan Silberman, Sergio Guadarrama, George Papandreou, Jonathan Huang, Kevin P. Murphy. IEEE International Conference on Computer Vision, 2015

481 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Public Health, Environmental and Occupational Health

View Paper: https://www.semanticscholar.org/paper/115f30924be576b00ad5184c9ba963430887ba4f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Public Health, Environmental and Occupational Health

Citations in the corpus

A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure (2018, background): “started to research the application of deep learning for food image recognition [31].”
Deep-based Ingredient Recognition for Cooking Recipe Retrieval (2016, methodology): “However, restaurant information are difficult to acquire as stated in [24] and such context-aware recognition is only limited to restaurant food.”
Learning Cross-Modal Embeddings for Cooking Recipes and Food Images (2017, background): “Existing work, however, has focused largely on the use of medium-scale datasets for performing categorization [1, 8, 16, 13].”
Recipe1M: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images (2018, background): “Even with the impetus for food image categorization, subsequent work by [9], [10] and [11] could only improve this result to 77.4%, 79% and 80.9%, respectively, which indicates that the size of the dataset may be the limiting factor.”
Fine-Grained Image Classification by Exploring Bipartite-Graph Labels (2015, background): “Fine-grained image classification concerns the task of distinguishing sub-ordinate categories of some base classes such as dogs [26, 43], birds [5, 8], flowers [1, 40], plants [32, 45], cars [30, 36, 48], food [3, 6, 38, 59], clothes [14], fonts [10] and furniture [4].”
A Survey on Food Computing (2018, methodology): “2012) and deep features (Kagaya and Aizawa 2015; Meyers et al. 2015) are adopted.”
Segmentation from Natural Language Expressions (2016, methodology): “ person with a red shirt", or referring to parts of your meal to estimate their nutrition, \two large pieces of bacon", to decide better if one should eat it rather than the full meal as in [10]. As described in more details in Section 2, prior methods suitable for this task were limited t”
Fully Convolutional Attention Networks for Fine-Grained Recognition (2016, background): “49] - 92.5 Krause et al. [22] 92.6 92.8 Our Model 91.5 93.1 Table 4. Comparison to related work on Stanford Cars dataset. Method Accuracy(%) Acc w. Box(%) L. Bossard et al. [5] 50.8 - A. Myers et al. [50] 79.0 - Our Model 86.3 - Table 5. Experimental results on Food-101 dataset. On Stanford Dogs, St”
Inverse Cooking: Recipe Generation From Food Images (2018, background): “Subsequent works tackle more challenging tasks such as estimating the number of calories given a food image [32], estimating food quantities [5], predicting the list of present ingredients [3, 4] and finding the recipe for a given image [54, 3, 4, 45, 2].”