Filters








89,864 Hits in 8.1 sec

Active labeling application applied to food-related object recognition

Marc Bolaños, Maite Garolera, Petia Radeva
2013 Proceedings of the 5th international workshop on Multimedia for cooking & eating activities - CEA '13  
However, to extract the information of interest related to the eating patterns of people, we need automatic methods to process large amount of life-logging data (e.g. recognition of food-related objects  ...  Our method is successfully tested to label 89.700 food-related objects and achieves significant reduction in expert time labelling.  ...  To our knowledge, this work for first time addresses the problem of Active Labeling applied to the field of food-related object recognition.  ... 
doi:10.1145/2506023.2506032 dblp:conf/mm/BolanosGR13 fatcat:ddzmc6xeonej7blhqbt2ftvgli

Food Ingredients Recognition through Multi-label Learning [article]

Marc Bolaños and Aina Ferrà and Petia Radeva
2017 arXiv   pre-print
We tackle the problem of food ingredients recognition as a multi-label learning problem.  ...  We propose a method for adapting a highly performing state of the art CNN in order to act as a multi-label predictor for learning recipes in terms of their list of ingredients.  ...  problem of food ingredients recognition.  ... 
arXiv:1707.08816v1 fatcat:wtrv2obnsrd27dctfukjsddm4m

Kusk Object Dataset: Recording access to objects in food preparation

Atsushi Hashimoto, Shinsuke Mori, Masaaki Iiyama, Michihiko Minoh
2016 2016 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)  
The records of access to object are known as a key evidence for understanding chef's activity in food preparation. In the dataset, we provide object images as well as the records of access to object.  ...  This study aims to construct a KUSK Dataset's extension that provides records of chef's touching and releasing action to objects, which we call "access to objects," in his/her food preparation.  ...  Thus, a method that matches a recipe text and tasks in food preparation activity can be applied to other manufacturing processes as well.  ... 
doi:10.1109/icmew.2016.7574771 dblp:conf/icmcs/HashimotoMIM16 fatcat:b6qx27k2jzhgtixedfxfzwghxq

A Food Recommender Based on Frequent Sets of Food Mining Using Image Recognition [chapter]

Thunchanok Tangpong, Somkiet Leanghirun, Aran Hansuebsai, Kosuke Takano
2021 Artificial Intelligence  
The frequent set of foods extracted from food images was applied to Apriori data mining algorithm for the food recommendation process.  ...  This allowed the integrated DNN to select a suitable recognition result obtained from the different DNNs that were independently constructed.  ...  Authors would like to thank KAIT for providing scholarship and deeply appreciate Professor Kosuke Takano for his advice and facility in his Laboratory at KAIT.  ... 
doi:10.5772/intechopen.97186 fatcat:lnpiwlzbqncrpnssma655rttfi

Human Factor in Food Label Design to Support Consumer Healthcare and Safety: A Systematic Literature Review

Angelo Corallo, Maria Elena Latino, Marta Menegoli, Biagia De Devitiis, Rosaria Viscecchia
2019 Sustainability  
So, a content analysis on lead papers' sample related to the Food Industry was carried out to identify evidence about the human factor in food label design.  ...  The aim of this study is to analyze the fields of application of the Human Factor in label design to evaluate the current methods of utilization in the food industry.  ...  • The concept of "human factor" finds application in food label design as a strategy to increase the recognition speed of contents in a label, improve the label readiness, foster the product decision-making  ... 
doi:10.3390/su11154019 fatcat:ov7ipumc7ra3xpuswo65cbeeui

Object Detection using Convolutional Neural Network in the Application of Supplementary Nutrition Value of Fruits

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Object image detection is unique most auspicious claims of visual object recognition, since it will help to estimate nutrition calories and improve commons ingestion habits.  ...  The project aim is to develop an application for estimating food calories and improve people's consumption conducts for fitness.  ...  The method of food recognition is applied mistreatment Convolutional neural network mistreatment Tensor Flow.  ... 
doi:10.35940/ijitee.k1432.0981119 fatcat:gb3v7s7tpzdozlnqyn4q2yvxi4

A Survey on Food Computing [article]

Weiqing Min and Shuqiang Jiang and Linhu Liu and Yong Rui and Ramesh Jain
2019 arXiv   pre-print
In food computing, computational approaches are applied to address food related issues in medicine, biology, gastronomy and agronomy.  ...  Large-scale food data offers rich knowledge about food and can help tackle many central issues of human society. Therefore, it is time to group several disparate issues related to food computing.  ...  or food-related objects present in each bounding box.  ... 
arXiv:1808.07202v5 fatcat:qjitfexaffd3fohfb7iy3lwfyi

Learning Dynamic Spatio-Temporal Relations for Human Activity Recognition

Zhenyu Liu, Yaqiang Yao, Yan Liu, Yuening Zhu, Zhenchao Tao, Lei Wang, Yuhong Feng
2020 IEEE Access  
Moreover, a fully automatic partition method is proposed to divide a long-term human activity video into several human actions based on variational objects and qualitative spatial relations.  ...  Next, a discrete hidden Markov model is applied to model the evolution of action sequences.  ...  Each human activity video is labeled with a single high-level activity: Making Cereal, Taking Medicine, Stacking Objects, Unstacking Objects, Microwaving Food, Picking Objects, Cleaning Objects, Taking  ... 
doi:10.1109/access.2020.3009136 fatcat:skmwviewnjg2rigyztji55z6ga

Towards Eating Habits Discovery in Egocentric Photo-streams

Alina Matei, Andreea Glavan, Petia Radeva, Estefania Talavera
2021 IEEE Access  
However, it is not easy to be aware of how our food-related routine affects our healthy living.  ...  Furthermore, we show an application for the identification of food-related scenes when the camera wearer eats in isolation.  ...  (a) Frequency of non-food or food-related activities. (b) Frequency of food-related activities, i.e. time spent in a food-related scene.  ... 
doi:10.1109/access.2021.3053175 fatcat:lcmklsslqbaodmo2xdfv6xziwy

"Important stuff, everywhere!" Activity recognition with salient proto-objects as context

Lukas Rybok, Boris Schauerte, Ziad Al-Halah, Rainer Stiefelhagen
2014 IEEE Winter Conference on Applications of Computer Vision  
Object information is an important cue to discriminate between activities that draw part of their meaning from context.  ...  However, such object detectors require a significant amount of training data and complicate the transfer of the action recognition framework to novel domains with different objects and object-action relationships  ...  *Note that [17] is using ground truth object labels and thus is not directly comparable to our approach. the data set was designed to model the application of activity recognition in a household robot  ... 
doi:10.1109/wacv.2014.6836041 dblp:conf/wacv/RybokSAS14 fatcat:kv3kdsplcrc7tbn525pcurzcb4

Classifying cooking object's state using a tuned VGG convolutional neural network [article]

Rahul Paul
2018 arXiv   pre-print
This framework can be easily adapted in any other object state classification activity.  ...  To achieve different states, different manipulations would be required, as well as different grasping. To analyze the objects at different states, a dataset of cooking objects was created.  ...  They also improved the classification accuracy further on Food -101 dataset to 79% and came up with a mobile phone based application.  ... 
arXiv:1805.09391v2 fatcat:ztd2g6s43zgrtcgara7t34ht5y

Human Activity Recognition based on Dynamic Spatio-Temporal Relations [article]

Zhenyu Liu, Yaqiang Yao, Yan Liu, Yuening Zhu, Zhenchao Tao, Lei Wang, Yuhong Feng
2020 arXiv   pre-print
Moreover, a fully automatic partition method is proposed to divide a long-term human activity video into several human actions based on variational objects and qualitative spatial relations.  ...  Next, a discrete hidden Markov model is applied to model the evolution of action sequences.  ...  Each human activity video is labeled with a single high-level activity: Making Cereal , Taking Medicine, Stacking Objects, Unstacking Objects, Microwaving Food , Picking Objects, Cleaning Objects, Taking  ... 
arXiv:2006.16132v1 fatcat:snvksj7g5ra35d5bgj3vx2vm3q

Hierarchical approach to classify food scenes in egocentric photo-streams [article]

Estefania Talavera, Maria Leyva-Vallina, Md. Mostafa Kamal Sarker, Domenec Puig, Nicolai Petkov, Petia Radeva
2019 arXiv   pre-print
Specifically, we propose a new automatic approach for the classification of food-related environments, that is able to classify up to 15 such scenes.  ...  In this way, people can monitor the context around their food intake in order to get an objective insight into their daily eating routine.  ...  The collected data as part of the study and given labels is publicly available from the research group's website: http://www.ub.edu/cvub/dataset/  ... 
arXiv:1905.04097v1 fatcat:rh6et6hf5jfeznrbvo4ybv23zy

Hierarchical approach to classify food scenes in egocentric photo-streams

Estefania Talavera Martinez, Maria Leyva-Vallina, Mostafa Kamal Sarker, Domenec Puig, Nicolai Petkov, Petia Radeva
2019 IEEE journal of biomedical and health informatics  
Specifically, we propose a new automatic approach for the classification of food-related environments, that is able to classify up to 15 such scenes.  ...  In this way, people can monitor the context around their food intake in order to get an objective insight into their daily eating routine.  ...  The collected data as part of the study and given labels is publicly available from the research group's website: http://www.ub.edu/cvub/dataset/  ... 
doi:10.1109/jbhi.2019.2922390 pmid:31199277 fatcat:hq3tjlqyknfnllrgcg7dqmctym

Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition [article]

Ning Wang, Guangming Zhu, Liang Zhang, Peiyi Shen, Hongsheng Li, Cong Hua
2021 arXiv   pre-print
The full use of appearance features, the spatial location and the semantic information are also the key to improve the video-based Human-Object Interaction recognition performance.  ...  These nodes are connected by two types of relations: (i) spatial relations modeling the interactions between human and the interacted objects within each frame.  ...  CAD-120 contains long activity video sequences, which comprise segments of sub-activities. HOI recognition is performed to predict sub-activities and object affordance labels of segments.  ... 
arXiv:2108.08633v1 fatcat:ha4t45ofurgcjey3izbp5fa3vm
« Previous Showing results 1 — 15 out of 89,864 results