QQ客服 官方微博 反馈留言

浏览/检索结果: 共6条，第1-6条 帮助 限定条件 内容类型：会议论文     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 Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation 会议论文 Shenzhen, China, 2021-6 作者:  Deng, Shuang;  Liu, Bo;  Dong, Qiulei;  Hu, Zhanyi 收藏  |  浏览/下载：50/0  |  提交时间：2022/09/21 A Deformable Convolutional Neural Network with Oriented Response for Fine-Grained Visual Classification 会议论文 Virtual, Online, China, 2021-02-26 作者:  Ruan, Shangxian;  Yang, Jiating;  Chen, Jianbo 收藏  |  浏览/下载：27/0  |  提交时间：2021/07/20 Fine-grained visual classification  Deformable convolution  Oriented response  Weakly supervised   Proxy Graph Matching with Proximal Matching Networks 会议论文 线上远程会议, 2021-2-7 作者:  Tan HR(檀昊儒);  Wang C(王闯);  Wu ST(吴思彤);  Wang TQ(王铁强);  Zhang XY(张煦尧) 收藏  |  浏览/下载：43/0  |  提交时间：2021/07/01 Graph Matching  Combinatorial Optimization  Deep Learning   Rotaion and Scale-invariant Object Detector for High Resolution Optical Remote Sensing Images 会议论文 日本横滨, 2019年7月29日-2019年8月2日 作者:  Huang H(黄河);  Huo CL(霍春雷);  Wei FL(魏飞龙);  Pan CH(潘春洪) 收藏  |  浏览/下载：61/0  |  提交时间：2019/06/24 Rotation-invariant  Scale-invariant  Convolutional Neural Network  Optical Remote Sensing  Object Detection   Fast and light manifold CNN based 3D facial expression recognition across pose variations 会议论文 MM 2018 - Proceedings of the 2018 ACM Multimedia Conference 作者:  Chen, Z.;  Wang, Y.;  Huang, D.;  Chen, L. 收藏  |  浏览/下载：11/0  |  提交时间：2019/12/30 Deep learning  Gesture recognition  Neural networks  Trees (mathematics)  3-D facial expression recognition  Convolutional neural network  Encoding strategy  Geometry representation  Pre-processing method  Rotation invariance  Rotation invariant  Shape characteristics  Face recognition   An object recognition method based on fuzzy theory and BP networks (EI CONFERENCE) 会议论文 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China Chuan W.; Ming Z.; Dong Y. 收藏  |  浏览/下载：14/0  |  提交时间：2013/03/25 It is difficult to choose eigenvectors when neural network recognizes object. It is possible that the different object eigenvectors is similar or the same object eigenvectors is different under scaling  shifting  rotation if eigenvectors can not be chosen appropriately. In order to solve this problem  the image is edged  the membership function is reconstructed and a new threshold segmentation method based on fuzzy theory is proposed to get the binary image. Moment invariant of binary image is extracted and normalized. Some time moment invariant is too small to calculate effectively so logarithm of moment invariant is taken as input eigenvectors of BP network. The experimental results demonstrate that the proposed approach could recognize the object effectively  correctly and quickly.