% 字体族设置(罗马字体,无衬线字体,打字机字体) \textrm{Roman Family} % 罗马字体 \textsf{Sans Serif Family} % 无衬线字体 \texttt{Typewriter Family} % 打字机字体 \rmfamily Roman Family % 字体声明: 声明后面字体为罗马字体 {\sffamily Sans Serif Family} {\ttfamily Typewriter Family} {\sffamily Video object segmentation (VOS) is a fundamental task in computer vision, with important applications including video editing, robotics, and selfdriving cars. According to whether the ground-truth mask of the target objects is given for the first frame, VOS task can be seen as semi-supervised VOS and unsupervised VOS. } {\rmfamily Given the mask of the target objects for the first frame, algorithm for semi-supervised VOS focuses on using it to model the appearance of the objects of interest, such as fine-tuning the model using the first frame or matching the pixel or superpixel of following frames with the first frame. Motion cue or temporal information is considered to be complementary information to enhance performance. While the information for the object of interest is unknown, the method of unsupervised VOS leverages the motion cue and the general appearance model to get dominant feature and segment the salient object .} % 字体形状设置(直立,斜体,伪斜体,小型大写) \textup{Upright Shape} \textit{Italic Shape} \textsl{Slanted Shape} \textsc{ Small Caps Shape} {\upshape Upright Shape } {\itshape Italic Shape } {\slshape Slanted Shape} {\scshape Small Caps Shape} % 中文字体设置 \noindent 我是全局字体,我使用的是宋体\\ {\kaishu 我是ctex已定义好的字体,我使用的楷体}\\ {\heiti 我是ctex已定义好的字体,我使用的黑体}\\ {\fangsong 我是ctex已定义好的字体,我使用的仿宋}\\ % 设置字体大小 {\tiny Hello} \\ {\scriptsize Hello} \\ {\footnotesize Hello} \\ {\small Hello} \\ {\normalsize Hello} \\ {\large Hello} \\ {\Large Hello} \\ {\LARGE Hello} \\ {\huge Hello} \\ {\Huge Hello} \\ % 中文字体字号 \zihao{4} 你好 \myfont \end{document}
\begin{document} % 多行公式 带编号 \begin{gather} a + b = b + a \\ ab ba \end{gather} % 多行公式 %不带编号 \begin{gather*} a + b = b + a \\ ab ba \end{gather*} \end{document}