Filters








3,876 Hits in 5.0 sec

Fine-Grained Image Classification by Exploring Bipartite-Graph Labels

Feng Zhou, Yuanqing Lin
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Experimental results on this new food and three other datasets demonstrate BGL advances previous works in fine-grained object recognition.  ...  Given a food image, can a fine-grained object recognition engine tell "which restaurant which dish" the food belongs to?  ...  fine-grained classes vs. two ingredients (right).  ... 
doi:10.1109/cvpr.2016.127 dblp:conf/cvpr/ZhouL16 fatcat:ininzm4swbcddikl7qrx5oddnm

ISIA Food-500: A Dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network [article]

Weiqing Min, Linhu Liu, Zhiling Wang, Zhengdong Luo, Xiaoming Wei, Xiaolin Wei, Shuqiang Jiang
2020 arXiv   pre-print
Food recognition has received more and more attention in the multimedia community for its various real-world applications, such as diet management and self-service restaurants.  ...  A large-scale ontology of food images is urgently needed for developing advanced large-scale food recognition algorithms, as well as for providing the benchmark dataset for such algorithms.  ...  In addition, our work is also very relevant to fine-grained image recognition [49] , which aims to classify subordinate categories. Food recognition belongs to fine-grained image recognition.  ... 
arXiv:2008.05655v1 fatcat:4eza5mquozbr5oogvy3zsbk57i

Fine-grained Image Classification by Exploring Bipartite-Graph Labels [article]

Feng Zhou, Yuanqing Lin
2015 arXiv   pre-print
Experimental results on this new food and three other datasets demonstrates BGL advances previous works in fine-grained object recognition.  ...  Given a food image, can a fine-grained object recognition engine tell "which restaurant which dish" the food belongs to?  ...  This indicates the effectiveness of exploring the label dependency in ultra-fine grained food recognition.  ... 
arXiv:1512.02665v2 fatcat:gabw6jjy7zen3o5mdpc64gdcjm

Food recognition and recipe analysis: integrating visual content, context and external knowledge [article]

Luis Herranz, Weiqing Min, Shuqiang Jiang
2018 arXiv   pre-print
as the exploration and retrieval of food-related information.  ...  We review how visual content, context and external knowledge can be integrated effectively into food-oriented applications, with special focus on recipe analysis and retrieval, food recommendation, and  ...  Zhou and Lin [12] formulate the problem as fine-grained recognition where fine-grained labels are complemented by coarse labels (ingredients and coarser dish classes, respectively).  ... 
arXiv:1801.07239v1 fatcat:kbcpto5iznhkddvdklwxxbtehm

Deep-based Ingredient Recognition for Cooking Recipe Retrieval

Jingjing Chen, Chong-wah Ngo
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
This paper proposes deep architectures for simultaneous learning of ingredient recognition and food categorization, by exploiting the mutual but also fuzzy relationship between them.  ...  Nevertheless, ingredient recognition is a task far harder than food categorization, and this seriously challenges the feasibility of relying on them for retrieval.  ...  For the deep architectures, max pooling is adopted to merge the results of fine-grained ingredients.  ... 
doi:10.1145/2964284.2964315 dblp:conf/mm/ChenN16 fatcat:2byjb6ohdrakhivn5jaa36mjcq

Embedding Label Structures for Fine-Grained Feature Representation

Xiaofan Zhang, Feng Zhou, Yuanqing Lin, Shaoting Zhang
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
year of cars) or attributes (e.g., ingredients of food).  ...  Deep face recognition. BMVC, 2015. 2, [11] J. Deng, J. Krause, and L. Fei-Fei. Fine-grained crowdsourc- 3, 6, 7 ing for fine-grained recognition. In CVPR, pages 580–587.  ... 
doi:10.1109/cvpr.2016.126 dblp:conf/cvpr/ZhangZLZ16 fatcat:aa5v7iwcwbaphhxkjrp2qypoje

Food Recommendation: Framework, Existing Solutions and Challenges [article]

Weiqing Min, Shuqiang Jiang, Ramesh Jain
2019 arXiv   pre-print
This article proposes a unified framework for food recommendation, and identifies main issues affecting food recommendation including building the personal model, analyzing unique food characteristics,  ...  We then review existing solutions for these issues, and finally elaborate research challenges and future directions in this field.  ...  In addition, visual food analysis involves fine-grained visual feature representation learning. However, we can not simply use existing fine-grained feature learning methods for food analysis.  ... 
arXiv:1905.06269v2 fatcat:epzmc5efqneqboyesqoqs7tmni

Table of contents

2021 IEEE transactions on circuits and systems for video technology (Print)  
Yang 2465 Food and Ingredient Joint Learning for Fine-Grained Recognition ...... C. Liu, Y. Liang, Y. Xue, X. Qian, and J.  ...  Cheng 2288 Orthogonality Loss: Learning Discriminative Representations for Face Recognition ....................................... .....................................................................  ... 
doi:10.1109/tcsvt.2021.3080805 fatcat:bmy7voimtzdjbn5qpk4o2xoseu

Learning Cross-Modal Embeddings for Cooking Recipes and Food Images

Amaia Salvador, Nicholas Hynes, Yusuf Aytar, Javier Marin, Ferda Ofli, Ingmar Weber, Antonio Torralba
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We postulate that these embeddings will provide a basis for further exploration of the Recipe1M dataset and food and cooking in general.  ...  In this paper, we introduce Recipe1M, a new large-scale, structured corpus of over 1m cooking recipes and 800k food images.  ...  and the European Regional Development Fund (ERDF).  ... 
doi:10.1109/cvpr.2017.327 dblp:conf/cvpr/SalvadorHAMOW017 fatcat:dganhxaqebdrhfnvngdziivxe4

Embedding Label Structures for Fine-Grained Feature Representation [article]

Xiaofan Zhang and Feng Zhou and Yuanqing Lin and Shaoting Zhang
2016 arXiv   pre-print
Extensive and thorough experiments have been conducted on three fine-grained datasets, i.e., the Stanford car, the car-333, and the food datasets, which contain either hierarchical labels or shared attributes  ...  More importantly, it significantly outperforms previous fine-grained feature representations for image retrieval at different levels of relevance.  ...  For instance, Fig. 4 illustrates that fine-grained food dishes can share some ingredients, indicating relevance at different levels.  ... 
arXiv:1512.02895v2 fatcat:5dnwmw7o7rfphoo5rwml3wa7fa

Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition [article]

Xinda Liu, Lili Wang, Xiaoguang Han
2021 arXiv   pre-print
In this paper, we analyze the difficulties of fine-grained image recognition from a new perspective and propose a transformer architecture with the peak suppression module and knowledge guidance module  ...  Fine-grained image recognition is challenging because discriminative clues are usually fragmented, whether from a single image or multiple images.  ...  DSTL [61] uses the transfer learning strategy for the fine-grained image recognition task consisting of more than one dataset.  ... 
arXiv:2107.06538v2 fatcat:p4bjvwr45vh3fm2cfjm5byjxdm

Recognition and localization of food in cooking videos

Nachwa Aboubakr, Remi Ronfard, James Crowley
2018 Proceedings of the Joint Workshop on Multimedia for Cooking and Eating Activities and Multimedia Assisted Dietary Management - CEA/MADiMa '18  
We compare results with two techniques for detecting food types and food states, and then show that recognizing type and state with separate classifiers improves recognition results.  ...  We describe production of a new data set that provides annotated images for food types and food states.  ...  Learning food concepts Describing food transformations requires combining recognition of food type and food state. We refer to these as "composite classes".  ... 
doi:10.1145/3230519.3230590 dblp:conf/ijcai/BakrRC18 fatcat:5ryllmwjf5hldenkzojuttldgm

A Survey on Food Computing [article]

Weiqing Min and Shuqiang Jiang and Linhu Liu and Yong Rui and Ramesh Jain
2019 arXiv   pre-print
Food computing acquires and analyzes heterogenous food data from disparate sources for perception, recognition, retrieval, recommendation, and monitoring of food.  ...  Food is very essential for human life and it is fundamental to the human experience.  ...  food recognition task with pre-training and fine-tuning.] leveraged hierarchical semantics for food recognition based on joint deep feature learning from GoogLeNet and semantic label inference.  ... 
arXiv:1808.07202v5 fatcat:qjitfexaffd3fohfb7iy3lwfyi

Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images [article]

Javier Marin, Aritro Biswas, Ferda Ofli, Nicholas Hynes, Amaia Salvador, Yusuf Aytar, Ingmar Weber, Antonio Torralba
2019 arXiv   pre-print
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.  ...  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.  ...  However, the results are often not so fine-grained.  ... 
arXiv:1810.06553v2 fatcat:a7hlj3vkmbgapl2dtrzncm6rwy

Recognizing Fine-Grained and Composite Activities Using Hand-Centric Features and Script Data

Marcus Rohrbach, Anna Rohrbach, Michaela Regneri, Sikandar Amin, Mykhaylo Andriluka, Manfred Pinkal, Bernt Schiele
2015 International Journal of Computer Vision  
We show the benefits of our hand-centric approach for fine-grained activity classification and detection.  ...  The first challenge is to detect fine-grained activities, which are defined by low inter-class variability and are typically characterized by fine-grained body motions.  ...  " of the German Excellence Initiative and the Max Planck Center for Visual Computing and Communication.  ... 
doi:10.1007/s11263-015-0851-8 fatcat:2xck42za7va2dldyvmyfaqrzsq
« Previous Showing results 1 — 15 out of 3,876 results