Matches in SemOpenAlex for { <https://semopenalex.org/work/W3148388528> ?p ?o ?g. }
- W3148388528 endingPage "129" @default.
- W3148388528 startingPage "106" @default.
- W3148388528 abstract "Multi-view learning (MVL) has attracted increasing attention and achieved great practical success by exploiting complementary information of multiple features or modalities. Recently, due to the remarkable performance of deep models, deep MVL has been adopted in many domains, such as machine learning, artificial intelligence and computer vision. This paper presents a comprehensive review on deep MVL from the following two perspectives: MVL methods in deep learning scope and deep MVL extensions of traditional methods. Specifically, we first review the representative MVL methods in the scope of deep learning, such as multi-view auto-encoder, conventional neural networks and deep brief networks. Then, we investigate the advancements of the MVL mechanism when traditional learning methods meet deep learning models, such as deep multi-view canonical correlation analysis, matrix factorization and information bottleneck. Moreover, we also summarize the main applications, widely-used datasets and performance comparison in the domain of deep MVL. Finally, we attempt to identify some open challenges to inform future research directions." @default.
- W3148388528 created "2021-04-13" @default.
- W3148388528 creator A5006580423 @default.
- W3148388528 creator A5016638014 @default.
- W3148388528 creator A5045940041 @default.
- W3148388528 creator A5078088762 @default.
- W3148388528 creator A5087316018 @default.
- W3148388528 date "2021-08-01" @default.
- W3148388528 modified "2023-10-14" @default.
- W3148388528 title "Deep multi-view learning methods: A review" @default.
- W3148388528 cites W1655434153 @default.
- W3148388528 cites W1925417509 @default.
- W3148388528 cites W1975077471 @default.
- W3148388528 cites W1984983329 @default.
- W3148388528 cites W1995680626 @default.
- W3148388528 cites W1997201895 @default.
- W3148388528 cites W2007972815 @default.
- W3148388528 cites W2025768430 @default.
- W3148388528 cites W2045156863 @default.
- W3148388528 cites W2055513867 @default.
- W3148388528 cites W2063971957 @default.
- W3148388528 cites W2083095455 @default.
- W3148388528 cites W2083670761 @default.
- W3148388528 cites W2085789144 @default.
- W3148388528 cites W2108119513 @default.
- W3148388528 cites W2116341502 @default.
- W3148388528 cites W2130055251 @default.
- W3148388528 cites W2132914434 @default.
- W3148388528 cites W2166049352 @default.
- W3148388528 cites W2166267120 @default.
- W3148388528 cites W2168103112 @default.
- W3148388528 cites W2279323413 @default.
- W3148388528 cites W2295584157 @default.
- W3148388528 cites W2481240925 @default.
- W3148388528 cites W2487852963 @default.
- W3148388528 cites W2504559372 @default.
- W3148388528 cites W2524399695 @default.
- W3148388528 cites W2550200318 @default.
- W3148388528 cites W2588127243 @default.
- W3148388528 cites W2590019597 @default.
- W3148388528 cites W2605793178 @default.
- W3148388528 cites W2619383789 @default.
- W3148388528 cites W2735680049 @default.
- W3148388528 cites W2753372987 @default.
- W3148388528 cites W2757312963 @default.
- W3148388528 cites W2758611985 @default.
- W3148388528 cites W2767290858 @default.
- W3148388528 cites W2789938689 @default.
- W3148388528 cites W2795832645 @default.
- W3148388528 cites W2889162782 @default.
- W3148388528 cites W2893277817 @default.
- W3148388528 cites W2894170005 @default.
- W3148388528 cites W2897746180 @default.
- W3148388528 cites W2898658722 @default.
- W3148388528 cites W2903712458 @default.
- W3148388528 cites W2905579172 @default.
- W3148388528 cites W2909502737 @default.
- W3148388528 cites W2914383137 @default.
- W3148388528 cites W2918930673 @default.
- W3148388528 cites W2919115771 @default.
- W3148388528 cites W2920873876 @default.
- W3148388528 cites W2946165673 @default.
- W3148388528 cites W2947223061 @default.
- W3148388528 cites W2950499001 @default.
- W3148388528 cites W2963536842 @default.
- W3148388528 cites W2964368963 @default.
- W3148388528 cites W2965901996 @default.
- W3148388528 cites W2967066800 @default.
- W3148388528 cites W2968370607 @default.
- W3148388528 cites W2971370265 @default.
- W3148388528 cites W2972028571 @default.
- W3148388528 cites W2972477132 @default.
- W3148388528 cites W2980008268 @default.
- W3148388528 cites W2989570255 @default.
- W3148388528 cites W2995206248 @default.
- W3148388528 cites W3004639522 @default.
- W3148388528 cites W3007863152 @default.
- W3148388528 cites W3010199114 @default.
- W3148388528 cites W3011943167 @default.
- W3148388528 cites W3012376705 @default.
- W3148388528 cites W3026016908 @default.
- W3148388528 cites W3027458137 @default.
- W3148388528 cites W3035770885 @default.
- W3148388528 cites W3045692700 @default.
- W3148388528 cites W3082334751 @default.
- W3148388528 cites W3088403078 @default.
- W3148388528 cites W3093006710 @default.
- W3148388528 cites W3099268463 @default.
- W3148388528 cites W3103428075 @default.
- W3148388528 cites W3105204788 @default.
- W3148388528 cites W3107191128 @default.
- W3148388528 cites W3118635606 @default.
- W3148388528 cites W3122451732 @default.
- W3148388528 cites W3126983570 @default.
- W3148388528 cites W375304271 @default.
- W3148388528 cites W81573328 @default.
- W3148388528 doi "https://doi.org/10.1016/j.neucom.2021.03.090" @default.
- W3148388528 hasPublicationYear "2021" @default.