Recipe recognition with large multimodal food dataset
Published 1 June 2015Open access
Xin Wang, Devinder Kumar, Nicolas Thome, Matthieu Cord, Fŕed́eric Precioso
Citations174
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper compares and evaluates leading vision-based and text-based technologies on a new very large multimodal dataset (UPMC Food-101) containing about 100,000 recipes for a total of 101 food categories, and presents deep experiments of recipe recognition on this dataset using visual, textual information and fusion.
Abstract
International audience
Keywords
Computer Science
arXiv (Cornell University)Very Deep Convolutional Networks for Large-Scale Image Recognition
75,540 Citations2014Karen Simonyan, Andrew Zisserman
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
LIBLINEAR: A Library for Large Linear Classification
6,625 Citations2008Rong-En Fan, Kai‐Wei Chang +3 more
arXiv (Cornell University)Distributed Representations of Sentences and Documents
5,128 Citations2014Quoc V. Le, Tomáš Mikolov
Paragraph Vector is an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and its construction gives the algorithm the potential to overcome the weaknesses of bag-of-words models.
Lecture notes in computer scienceFood-101 – Mining Discriminative Components with Random Forests
1,963 Citations2014Lukas Bossard, Matthieu Guillaumin +1 more
A novel method to mine discriminative parts using Random Forests (rf), which allows us to mine for parts simultaneously for all classes and to share knowledge among them, and compares nicely to other s-o-a component-based classification methods.
A database for fine grained activity detection of cooking activities
515 Citations2012Marcus Rohrbach, Saad Amin +2 more
A novel database of 65 cooking activities, continuously recorded in a realistic setting, is proposed, suggesting that fine-grained activities are more difficult to detect and the body model can help in those cases.
Lecture notes in computer scienceAutomatic Expansion of a Food Image Dataset Leveraging Existing Categories with Domain Adaptation
278 Citations2015Yoshiyuki Kawano, Keiji Yanai
This paper proposes to leverage existing knowledge on food of other cultures by a generic “foodness” classifier and domain adaptation to enable not only to built other-cultured food datasets based on an original food image dataset automatically, but also to save as much crowd-sourcing costs as possible.
PFID: Pittsburgh fast-food image dataset
252 Citations2009Mei Chen, Kapil Dev Dhingra +4 more
The first visual dataset of fast foods is introduced with a total of 4,545 still images, 606 stereo pairs, 303 360° videos for structure from motion, and 27 privacy-preserving videos of eating events of volunteers to stimulate research on fast food recognition for dietary assessment.
Computer Vision and Image UnderstandingPooling in image representation: The visual codeword point of view
216 Citations2012Sandra Avila, Nicolas Thome +3 more
B BossaNova is proposed, a novel representation for content-based concept detection in images and videos, which enriches the Bag-of-Words model, and is compact and simple to compute.
Food image recognition with deep convolutional features
207 Citations2014Yoshiyuki Kawano, Keiji Yanai
The feature obtained from the Deep Convolutional Neural Network boosts food recognition accuracy greatly by integrating it with conventional hand-crafted image features, Fisher Vectors with HoG and Color patches.
IEEE Transactions on Pattern Analysis and Machine IntelligenceHarvesting Image Databases from the Web
182 Citations2010Florian Schroff, Antonio Criminisi +1 more
The objective of this work is to automatically generate a large number of images for a specified object class by combining text/metadata and visual features in order to achieve a completely automatic ranking of the images.
IEEE Transactions on MultimediaFood Balance Estimation by Using Personal Dietary Tendencies in a Multimedia Food Log
113 Citations2013Kiyoharu Aizawa, Yuto Maruyama +2 more
A Bayesian framework that makes use of personal dietary tendencies to improve both food-image detection and food-balance estimation is proposed, which is the first to make use of statistical personal bias to improve the performance of the analysis.
IEEE Transactions on Image ProcessingActive Learning Methods for Interactive Image Retrieval
98 Citations2008Philippe H. Gosselin, Matthieu Cord
Algorithms within a statistical framework to extend active learning for online content-based image retrieval (CBIR) and a batch processing of images is proposed, leading to a fast and efficient active learning scheme to retrieve sets of online images (query concept).
Lecture notes in computer scienceA Benchmark Dataset to Study the Representation of Food Images
81 Citations2015Giovanni Maria Farinella, Dario Allegra +1 more
The UNICT-FD889 dataset is introduced, the first food image dataset composed by over \(800\) distinct plates of food which can be used as benchmark to design and compare representation models of food images, and results confirm that both textures and colors are fundamental properties in food representation.
An Overview of the Technology Assisted Dietary Assessment Project at Purdue University
52 Citations2010Nitin Khanna, Carol J. Boushey +4 more
The Technology Assisted Dietary Assessment project at Purdue University is described, which includes the use of image analysis tools for identification and quantification of food that is consumed at a meal.
Lecture notes in computer scienceFoodCam: A Real-Time Mobile Food Recognition System Employing Fisher Vector
45 Citations2014Yoshiyuki Kawano, Keiji Yanai
A mobile food recognition system with Fisher Vector and liner one-vs-rest SVMs which enables us to record the authors' food habits easily and achieves the 79.2% classification rate for the top 5 category candidates when the ground-truth bounding boxes are given.
Journal of Diabetes Science and TechnologyComparative Study of the Routine Daily Usability of FoodLog
43 Citations2014Kiyoharu Aizawa, Kazuki Maeda +5 more
The subjective assessment showed that the new FoodLog tool, which fully exploits the use of images, is a promising method for food recording.
IEEE Transactions on MultimediaImage Retrieval Over Networks: Active Learning Using Ant Algorithm
24 Citations2008David Picard, Matthieu Cord +1 more
A framework for distributed content based image retrieval with online learning based on ant-like mobile agents, showing that learning both the similarity function and the localization of the relevant images leads to a significant improvement.
Pattern RecognitionSALSAS: Sub-linear active learning strategy with approximate k-NN search
19 Citations2010David Gorisse, Matthieu Cord +1 more
This article proposes a strategy to overcome scalability limitations of active learning strategies by exploiting ultra fast k-nearest-neighbor (k-NN) methods, as locality sensitive hashing (LSH), and combining them with an active learning strategy dedicated to very large databases.
ITE Transactions on Media Technology and Applications[Invited Paper] Multimedia FoodLog: Diverse Applications from Self-Monitoring to Social Contributions
9 Citations2013Kiyoharu Aizawa
The state of food record keeping is described, which usually involves paper-based forms issued by healthcare services, and FoodLog, an application that allows users to keep photo-based visual records of their meals, thereby creating and maintaining a food log is presented.