QQ客服 官方微博 反馈留言

浏览/检索结果: 共2条，第1-2条 帮助 已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 Markovian Policy Network for Efficient Robot Learning 期刊 创刊日期: 2022, 作者:  Zhang FY(张丰一), Yurou Chen, Zhiyong Liu 收藏  |  浏览/下载：6/0  |  提交时间：2023/01/12 Efficient robot learning  Structural prior knowledge  Reinforcement learning  Graph neural network   TextureGrow: Object recognition and segmentation with limit prior knowledge (EI CONFERENCE) 会议论文 2011 International Conference on Network Computing and Information Security, NCIS 2011, May 14, 2011 - May 15, 2011, Guilin, Guangxi, China Yao Z.; Han Q. 收藏  |  浏览/下载：15/0  |  提交时间：2013/03/25 In this paper we present a new method for automatically visual recognition and semantic segmentation of photographs. Our automatically and rapidly approach based on Cellular Automation. Most of the analysis and description of recognition and segmentation are based on statistical or structural properties of this attribute  most of them need plenty of samples and prior Knowledge. In this paper  within a few evident samples (not too many)  we can first get the texture feature of each component and the structures  then select the approximately location randomly of the objects or patches of them  then we use the Cellular Automata algorithm to "grow" based on texture of different objects. The grow progress will stop When texture grow to the boundary. By this steps a new method is found which allow us use very few samples and low lever experience and get a rapidly and accuracy way to recognize and segment objects. We found that this new propose gives competitive results with limited experience and samples. 2011 IEEE.