中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共9条，第1-9条

帮助

条数/页：排序方式：
	Context Disentangling and Prototype Inheriting for Robust Visual Grounding 期刊论文 OAI收割 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 卷号: 46, 期号: 5, 页码: 3213-3229 作者: Tang, Wei; Li, Liang; Liu, Xuejing; Jin, Lu; Tang, Jinhui \| 收藏 \| 浏览/下载：22/0 \| 提交时间：2024/05/20 Visualization Grounding Prototypes Transformers Task analysis Linguistics Feature extraction Context disentangling open-vocabulary scene prototype discovering robust grounding visual grounding (VG)
	Towards Human-Machine Recognition Alignment: An Adversarilly Robust Multimodal Retrieval Hashing Framework 期刊论文 OAI收割 IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2022, 页码: 13 作者: Zhang, Xingwei; Zheng, Xiaolong; Liu, Bin; Wang, Xiao; Mao, Wenji \| 收藏 \| 浏览/下载：51/0 \| 提交时间：2022/11/14 Training Task analysis Semantics Perturbation methods Feature extraction Computational modeling Robustness Adversarial perturbation adversarially robust training deep hashing multimodal retrieval
	Common Spatial Pattern with L21-Norm 期刊论文 OAI收割 NEURAL PROCESSING LETTERS, 2021 作者: Gu, Jingyu; Wei, Mengting; Guo, Yiyun; Wang, Haixian \| 收藏 \| 浏览/下载：163/0 \| 提交时间：2021/07/19 Brain-computer interfaces (BCI) Common spatial pattern (CSP) L21-norm Robust feature extraction
	Low-Rank 2-D Neighborhood Preserving Projection for Enhanced Robust Image Representation 期刊论文 OAI收割 IEEE TRANSACTIONS ON CYBERNETICS, 2019, 卷号: 49, 期号: 5, 页码: 1859–1872 作者: Lu, Yuwu; Lai, Zhihui; Li, Xuelong; Wong, Wai Keung; Yuan, Chun \| 收藏 \| 浏览/下载：60/0 \| 提交时间：2019/04/12 2-D neighborhood preserving projection (2DNPP) image representation low-rank robust feature extraction
	Matryoshka Peek: Toward Learning Fine-Grained, Robust, Discriminative Features for Product Search 期刊论文 OAI收割 IEEE TRANSACTIONS ON MULTIMEDIA, 2017, 卷号: 19, 期号: 6, 页码: 1272-1284 作者: Kyaw, Zawlin; Qi, Shuhan; Gao, Ke; Zhang, Hanwang; Zhang, Luming \| 收藏 \| 浏览/下载：14/0 \| 提交时间：2019/12/12 Feature extraction image representation robust learning image retrieval
	Extracting sea-sky-line based on improved local complexity (EI CONFERENCE) 会议论文 OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China 作者: Zhang Y.-F. 收藏 \| 浏览/下载：24/0 \| 提交时间：2013/03/25 Sea-sky-line extraction under complicated sea-sky background is an important aspect of long-range target tracking research. An algorithm based on improved local complexity is proposed according to the feature that the sky and the sea usually show up at different gray levels in sea-sky background images. Median filter is applied first to remove peak noise and then the point set of sea-sky-line region which has the greatest change in image is obtained by calculating the local complexity of image and selecting a segmentation threshold. Finally Hough transform is used to extract the sea-sky-line. The experiment results indicate that this method can extract sea-sky-line under simple and complicated sea-sky backgrounds which is robust and can improve noise immunity of the algorithm. 2010 IEEE.
	非参数核密度聚类与特征提取算法研究学位论文 OAI收割工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2009 作者: 袁晓彤收藏 \| 浏览/下载：90/0 \| 提交时间：2015/09/02 聚类分析非参数核密度估计均值漂移半二次优化随机梯度学习特征提取 Renyi熵鲁棒统计学 Cluster Analysis Non-Parametric Kernel Density Estimation Mean-Shift Half-Quadratic Optimization Stochastic Gradient Learning Feature Extraction Renyi's Entropy Robust Statistics
	Joint transform correlator based on joint image feature extraction using swarm intelligence method (EI CONFERENCE) 会议论文 OAI收割 2009 IEEE International Conference on Mechatronics and Automation, ICMA 2009, August 9, 2009 - August 12, 2009, Changchun, China 作者: Wang Y.; Wang Y.; Wang Y.; Wang Y.; Wang Y. 收藏 \| 浏览/下载：15/0 \| 提交时间：2013/03/25 An image feature extraction method based on Swarm Intelligence is used in the preprocessing of joint image in joint transform correlator. The Swarm Intelligence based image processing method is superior to the conventional image processing method in its robust flexible fault tolerant scalable and highly parallelizable characteristic. The output results from the classical JTC without image preprocessing and the JTC with Sobel operator based joint image feature extraction are compared with that of the JTC when using the Swarm Intelligence to extract the feature of joint image. Experiment results show the performance improvement of JTC using the feature extraction method based on Swarm Intelligence. 2009 IEEE.
	听觉计算模型及其在鲁棒性语音识别中的应用学位论文 OAI收割工学博士, 中国科学院自动化研究所: 中国科学院自动化研究所, 1999 作者: 卢绪刚收藏 \| 浏览/下载：54/0 \| 提交时间：2015/09/02 听觉计算模型语音信号特征提取鲁棒性 HMM 动态非线性前向掩蔽效应时间机理部位机理尺度谱分析侧抑制 Computational Auditory Model Speech Feature's Extraction Robust HMM Dynamic Nonlinear Forward Masking Effect Temporal Mechanism