begin{table*}[ht]
processtable{Some of the works with their contributions to the field and their recognition rateslabel{tbl:0}}
{begin{tabular*}{20pc}{@{extracolsep{fill}}lll@{}}toprule
Method    & Contribution    & Recognition Rate for 6 Expressions  \
midrule
Lopes et. al.  & Generating synthetic samples to broaden the database for CNN learning process & 98.92  \
BDBN & A set of weak classifiers that each is responsible for classifying one expression.  & 96.70  \
AUDP  & Decomposing a facial expression into Micro-Action-Patterns and grouping them for higher level representation & 93.70  \
Fan & Tjahjadi  & spatial–temporal framework based on histogram of gradients and optical flow & 83.70  \
Zhong et. al.  & two-stage multi-task sparse learning (MTSL) framework to efficiently locate the discriminative patches that discloses the expressions  & 93.30  \
Liu et. al.  & manifold modeling of videos based on a proposed mid-level representation, i.e. expressionlet & 94.19  \
Gu et. al. & A radial encoding strategy for efficiently downsampling Gabor filter outputs and a new classifier combination method by extracting information from local classifiers. & 91.51  \
Proposed & asdsa & 99 \
botrule
end{tabular*}}{}
end{table*}