基于高斯连接回归模型的电影票房预测

J Duan, X Ding, T Liu - Science China Information Sciences, 2017 - Springer
… distributions of movies, ranging from the actors, directors and budgets before the releases
… Afterwards, we perform a non-parametric kernel-based cumulative distribution estimation on …

[HTML][HTML] 半监督两个视角的多示例聚类模型

蔡昊, 刘波 - 广东工业大学学报, 2021 - xml-data.org
… Firstly, the proposed model embeds Concept Factorization and multi-instance kernel into
a joint … 其一为NUS-WIDE1数据集,该数据集包含6种混合图像(actor,car_racing,fruit,insect,leopard,…

基于全景帧和典型局部特征的影视场景识别

高广宇, 马华东 - 计算机科学技术学报, 2014 - jcst.ict.ac.cn
… scene detection method using kernel canonical correlation analysis based feature fusion[20]…
, especially for a dynamic shot with larger motion of actor or camera[21-22]. However, these …

网络视频人脸—姓名关联: 大规模数据库, 基准实验和开放性问题

陈智能, 杨宗桦, 张炜, 曹娟, 姜育刚 - 计算机科学技术学报, 2014 - jcst.ict.ac.cn
… a set of famous football stars, while the celebrities in communities highlighted by red and
blue dotted circles are about the judges and contestants in “Britain’s Got Talent”, and the actors

国* 国Library and Archives Canada

N la thèse ni CleS eXtraits, SUS Ce - 2006 - library-archives.canada.ca
… legend as the kernel of the contemporary legend … kernel that is present when the contemporary
legend is cast in a written text and it is this core upon which any interpretations are based

基于图的多层次注意力事实验证算法.

谢艺菲, 卢琪, 刘鑫, 胡亚豪… - Journal of Computer …, 2021 - search.ebscohost.com
… And the kernel attention mechanism contributes to information propagation and verification.
Experimental results on a large-scale benchmark dataset FEVER demonstrate that GHAN …

[PDF][PDF] 基于视觉的人体动作识别综述

胡琼, 秦磊, 黄庆明 - 计算机学报, 2013 - academia.edu
… 他们利用多个高斯 混合模型来描述成对特征点之间相对坐标的时空上 下文分布关系,且对表观
特征也用高斯混合模型来 进行描述,最后他们用多核学习的方法(Multiple Kernel Learning)来把两…

跨媒体智能关联分析与语义理解理论与技术研究进展

于俊清, 王鑫, 况琨, 刘偲, 张新峰, 宋子恺 - 计算机辅助设计与图形学学报, 2023 - jcad.cn
… 在CCA 的基础上, 有许多后续的研究, 如 核典型相关性分析(kernel … Context modulated
dynamic networks for actor and action … Asymmetric cross-guided attention network for actor and …