Key frame extraction based on sparse coding can reduce the redundancy of continuous frames and concisely express the entire video.However,how to develop a key frame extraction algorithm that can automatically extract a few frames with a low reconstruction error remains a challenge.In this paper,we propose a novel model of structured sparse-coding-based key frame extraction,wherein a nonconvex group log-reg-ularizer is used with strong sparsity and a low reconstruction error.To automatically extract key frames,a decomposition scheme is designed to separate the sparse coefficient matrix by rows.The rows enforced by the nonconvex group log-regularizer become zero or nonzero,leading to the learning of the structured sparse coefficient matrix.To solve the nonconvex problems due to the log-regularizer,the difference of convex algorithm(DCA)is employed to decompose the log-regularizer into the difference of two convex functions related to the I1 norm,which can be directly obtained through the proximal operator.Therefore,an efficient structured sparse coding algorithm with the group log-regular-izer for key frame extraction is developed,which can automati-cally extract a few frames directly from the video to represent the entire video with a low reconstruction error.Experimental results demonstrate that the proposed algorithm can extract more accu-rate key frames from most SumMe videos compared to the state-of-the-art methods.Furthermore,the proposed algorithm can obtain a higher compression with a nearly 18％increase com-pared to sparse modeling representation selection(SMRS)and an 8％increase compared to SC-det on the VSUMM dataset.

Zhenni Li;Yujie Li;Benying Tan;Shuxue Ding;Shengli Xie

School of Automation,Guangdong University of Technology,Guangzhou 510006,and also with the Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing,Guangdong University of Technology(GDUT),Guangzhou 510006,China;School of Artificial Intelligence,Guilin University of Electronic Technology,Guilin 541004,China,and also with the National Institute of Advanced Industrial Science and Technology,Tsukuba,Ibaraki 305-8560,Japan;School of Artificial Intelligence,Guilin University of Electronic Technology,Guilin 541004,China;Key Laboratory of Intelligent Information Processing and System Integration of IoT(GDUT),Ministry of Education,and with Guangdong Key Laboratory of IoT Information Technology(GDUT),Guangzhou 510006,China

自动化学报（英文版）

[1]Zhenni Li;Yujie Li;Benying Tan;Shuxue Ding;Shengli Xie-.Structured Sparse Coding With the Group Log-regularizer for Key Frame Extraction)[J].自动化学报（英文版）,2022(10):1818-1830

regularizer,ularizer,izer,automati,SumMe,VSUMM

Structured,Sparse,Coding,With,Group,Log,Key,Frame,Extraction,extraction,sparse,coding,can,reduce,redundancy,continuous,frames,concisely,express,entire,However,how,key,algorithm,that,automatically,few,low,reconstruction,error,remains,challenge,In,this,paper,novel,structured,wherein,nonconvex,group,log,used,strong,sparsity,To,decomposition,scheme,designed,separate,coefficient,matrix,by,rows,enforced,become,nonzero,leading,learning,solve,problems,due,difference,DCA,employed,decompose,into,two,functions,related,I1,norm,which,directly,obtained,through,proximal,operator,Therefore,developed,from,Experimental,results,demonstrate,proposed,accu,most,videos,compared,state,art,methods,Furthermore,higher,compression,nearly,increase,modeling,representation,selection,SMRS,SC,det,dataset

0.435772