中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Large Scale Visual Food Recognition

文献类型：期刊论文

作者Min, Weiqing1,3; Wang, Zhiling1,3; Liu, Yuxin1,3; Luo, Mengjiang1,3; Kang, Liping2; Wei, Xiaoming2; Wei, Xiaolin2; Jiang, Shuqiang1,3
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2023-08-01
卷号45期号:8页码:9932-9949
ISSN号0162-8828
关键词Image recognition Visualization Task analysis Benchmark testing Representation learning Training Semantics Food dataset food recognition large-scale datasets fine-grained recognition
DOI10.1109/TPAMI.2023.3237871
英文摘要Food recognition plays an important role in food choice and intake, which is essential to the health and well-being of humans. It is thus of importance to the computer vision community, and can further support many food-oriented vision and multimodal tasks, e.g., food detection and segmentation, cross-modal recipe retrieval and generation. Unfortunately, we have witnessed remarkable advancements in generic visual recognition for released large-scale datasets, yet largely lags in the food domain. In this paper, we introduce Food2K, which is the largest food recognition dataset with 2,000 categories and over 1 million images. Compared with existing food recognition datasets, Food2K bypasses them in both categories and images by one order of magnitude, and thus establishes a new challenging benchmark to develop advanced models for food visual representation learning. Furthermore, we propose a deep progressive region enhancement network for food recognition, which mainly consists of two components, namely progressive local feature learning and region feature enhancement. The former adopts improved progressive training to learn diverse and complementary local features, while the latter utilizes self-attention to incorporate richer context with multiple scales into local features for further local feature enhancement. Extensive experiments on Food2K demonstrate the effectiveness of our proposed method. More importantly, we have verified better generalization ability of Food2K in various tasks, including food image recognition, food image retrieval, cross-modal recipe retrieval, food detection and segmentation. Food2K can be further explored to benefit more food-relevant tasks including emerging and more complex ones (e.g., nutritional understanding of food), and the trained models on Food2K can be expected as backbones to improve the performance of more food-relevant tasks. We also hope Food2K can serve as a large scale fine-grained visual recognition benchmark, and contributes to the development of large scale fine-grained visual analysis.
资助项目National Natural Science Foundation of China[61972378] ; National Natural Science Foundation of China[62125207] ; National Natural Science Foundation of China[U1936203] ; National Natural Science Foundation of China[U19B2040]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE COMPUTER SOC
WOS记录号WOS:001022958600044
源URL[http://119.78.100.204/handle/2XEOYT63/21335]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Jiang, Shuqiang
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Meituan Grp, Beijing 100102, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Min, Weiqing,Wang, Zhiling,Liu, Yuxin,et al. Large Scale Visual Food Recognition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(8):9932-9949.
APA Min, Weiqing.,Wang, Zhiling.,Liu, Yuxin.,Luo, Mengjiang.,Kang, Liping.,...&Jiang, Shuqiang.(2023).Large Scale Visual Food Recognition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(8),9932-9949.
MLA Min, Weiqing,et al."Large Scale Visual Food Recognition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.8(2023):9932-9949.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。