机构

• 计算技术研究所 [3]
• 长春光学精密机械与物... [1]

采集方式

• OAI收割 [4]

内容类型

• 期刊论文 [3]
• 会议论文 [1]

发表日期

• 2024 [1]
• 2023 [1]
• 2020 [1]
• 2011 [1]

学科主题

筛选

浏览/检索结果: 共4条，第1-4条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 Convolution-Enhanced Bi-Branch Adaptive Transformer With Cross-Task Interaction for Food Category and Ingredient Recognition 期刊论文  OAI收割 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 卷号: 33, 页码: 2572-2586 作者:  Liu, Yuxin;  Min, Weiqing;  Jiang, Shuqiang;  Rui, Yong   |  收藏  |  浏览/下载：11/0  |  提交时间：2024/05/20 Semantics  Visualization  Transformers  Task analysis  Feature extraction  Image recognition  Fish  Food recognition  ingredient recognition  food computing  fine-grained recognition  multi-label recognition   Multi-state Ingredient Recognition via Adaptive Multi-centric Network 期刊论文  OAI收割 IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 页码: 10 作者:  Wen, Min;  Song, Jiajun;  Min, Weiqing;  Xiao, Weimin;  Han, Lin   |  收藏  |  浏览/下载：12/0  |  提交时间：2024/05/20 Ingredient recognition  intelligent cooking device   Multi-Scale Multi-View Deep Feature Aggregation for Food Recognition 期刊论文  OAI收割 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 265-276 作者:  Jiang, Shuqiang;  Min, Weiqing;  Liu, Linhu;  Luo, Zhengdong   |  收藏  |  浏览/下载：155/0  |  提交时间：2019/12/10 Food recognition  ingredient knowledge  feature aggregation  convolutional neural networks   Design for target classifier based on semi-supervised learning (EI CONFERENCE) 会议论文  OAI收割 2011 International Conference on Electric Information and Control Engineering, ICEICE 2011, April 15, 2011 - April 17, 2011, Wuhan, China Jiangrui K. 收藏  |  浏览/下载：28/0  |  提交时间：2013/03/25 The target classifier is an ingredient of the target recognition system. In order to achieve the automation and computerization of target recognition  a method for training target classifier based on semi-supervised learning is provided. It adopts CFS algorithm for dada feature selection  and uses semi-supervised learning algorithm  Co-training to construct the target classifiers. The final classifier was produced through integration learning method. Experimental results show that the performance of the target classifier based on semi-supervised learning trained is superior to the traditional target classifier. 2011 IEEE.