Visual recognition is currently one of the most important and active research areas in computer vision,pattern recognition,and even the general field of artificial intelligence.It has great fundamental importance and strong industrial needs,particularly the modern deep neural networks(DNNs)and some brain-inspired methodologies,have largely boosted the recognition performance on many concrete tasks,with the help of large amounts of training data and new powerful computation resources.Although recognition ac-curacy is usually the first concern for new progresses,efficiency is actually rather important and sometimes critical for both academic re-search and industrial applications.Moreover,insightful views on the opportunities and challenges of efficiency are also highly required for the entire community.While general surveys on the efficiency issue have been done from various perspectives,as far as we are aware,scarcely any of them focused on visual recognition systematically,and thus it is unclear which progresses are applicable to it and what else should be concerned.In this survey,we present the review of recent advances with our suggestions on the new possible directions to-wards improving the efficiency of DNN-related and brain-inspired visual recognition approaches,including efficient network compres-sion and dynamic brain-inspired networks.We investigate not only from the model but also from the data point of view(which is not the case in existing surveys)and focus on four typical data types(images,video,points,and events).This survey attempts to provide a sys-tematic summary via a comprehensive survey that can serve as a valuable reference and inspire both researchers and practitioners work-ing on visual recognition problems.

Yang Wu;Ding-Heng Wang;Xiao-Tong Lu;Fan Yang;Man Yao;Wei-Sheng Dong;Jian-Bo Shi;Guo-Qi Li

Applied Research Center Laboratory,Tencent Platform and Content Group,Shenzhen 518057,China;School of Automation Science and Engineering,Faculty of Electronic and Information Engineering,Xi'an Jiaotong University,Xi'an 710049,China;School of Artificial Intelligence,Xidian University,Xi'an 710071,China;Division of Information Science,Nara Institute of Science and Technology,Nara 6300192,Japan;Peng Cheng Laboratory,Shenzhen 518000,China;Department of Computer and Information Science,University of Pennsylvania,Philadelphia PA 19104-6389,USA;Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100190,China

机器智能研究（英文）

[1]Yang Wu;Ding-Heng Wang;Xiao-Tong Lu;Fan Yang;Man Yao;Wei-Sheng Dong;Jian-Bo Shi;Guo-Qi Li-.Efficient Visual Recognition:A Survey on Recent Advances and Brain-inspired Methodologies)[J].机器智能研究（英文）,2022(05):366-411

Efficient,Visual,Recognition,Survey,Recent,Advances,Brain,inspired,Methodologies,recognition,currently,most,important,active,areas,computer,vision,pattern,general,field,artificial,intelligence,It,has,great,fundamental,importance,strong,industrial,needs,particularly,modern,deep,neural,networks,DNNs,brain,methodologies,have,largely,boosted,performance,many,concrete,tasks,help,amounts,training,data,new,powerful,computation,resources,Although,curacy,usually,first,progresses,efficiency,actually,rather,sometimes,critical,both,academic,applications,Moreover,insightful,views,opportunities,challenges,also,highly,required,entire,community,While,surveys,issue,been,done,from,various,perspectives,far,aware,scarcely,them,focused,visual,systematically,thus,unclear,which,applicable,what,else,should,concerned,In,this,present,review,recent,advances,suggestions,possible,directions,wards,improving,related,approaches,including,efficient,compres,dynamic,We,investigate,not,only,model,but,case,existing,four,typical,types,images,video,points,events,This,attempts,provide,summary,via,comprehensive,that,can,serve,valuable,reference,researchers,practitioners,problems

0.606593