Matches in SemOpenAlex for { <https://semopenalex.org/work/W3179871102> ?p ?o ?g. }
- W3179871102 abstract "Micro-expression recognition (textbf{MER}) has attracted lots of researchers' attention in a decade. However, occlusion will occur for MER in real-world scenarios. This paper deeply investigates an interesting but unexplored challenging issue in MER, ie, occlusion MER. First, to research MER under real-world occlusion, synthetic occluded micro-expression databases are created by using various mask for the community. Second, to suppress the influence of occlusion, a underline{R}egion-inspired underline{R}elation underline{R}easoning underline{N}etwork (textbf{RRRN}) is proposed to model relations between various facial regions. RRRN consists of a backbone network, the Region-Inspired (textbf{RI}) module and Relation Reasoning (textbf{RR}) module. More specifically, the backbone network aims at extracting feature representations from different facial regions, RI module computing an adaptive weight from the region itself based on attention mechanism with respect to the unobstructedness and importance for suppressing the influence of occlusion, and RR module exploiting the progressive interactions among these regions by performing graph convolutions. Experiments are conducted on handout-database evaluation and composite database evaluation tasks of MEGC 2018 protocol. Experimental results show that RRRN can significantly explore the importance of facial regions and capture the cooperative complementary relationship of facial regions for MER. The results also demonstrate RRRN outperforms the state-of-the-art approaches, especially on occlusion, and RRRN acts more robust to occlusion." @default.
- W3179871102 created "2021-07-19" @default.
- W3179871102 creator A5021875517 @default.
- W3179871102 creator A5029771864 @default.
- W3179871102 creator A5068470372 @default.
- W3179871102 creator A5082109737 @default.
- W3179871102 creator A5083815471 @default.
- W3179871102 date "2021-07-13" @default.
- W3179871102 modified "2023-09-27" @default.
- W3179871102 title "Region attention and graph embedding network for occlusion objective class-based micro-expression recognition" @default.
- W3179871102 cites W1578985305 @default.
- W3179871102 cites W1600550542 @default.
- W3179871102 cites W1625255723 @default.
- W3179871102 cites W1854318472 @default.
- W3179871102 cites W1981265375 @default.
- W3179871102 cites W2006426145 @default.
- W3179871102 cites W2044459166 @default.
- W3179871102 cites W2052442078 @default.
- W3179871102 cites W2093033615 @default.
- W3179871102 cites W2108598243 @default.
- W3179871102 cites W2139916508 @default.
- W3179871102 cites W2156489769 @default.
- W3179871102 cites W2170735791 @default.
- W3179871102 cites W2194775991 @default.
- W3179871102 cites W2237362194 @default.
- W3179871102 cites W2263218431 @default.
- W3179871102 cites W2342983306 @default.
- W3179871102 cites W234798790 @default.
- W3179871102 cites W2395363464 @default.
- W3179871102 cites W2413757304 @default.
- W3179871102 cites W2426188534 @default.
- W3179871102 cites W2478411578 @default.
- W3179871102 cites W2526853616 @default.
- W3179871102 cites W2527254703 @default.
- W3179871102 cites W2538953432 @default.
- W3179871102 cites W2623355927 @default.
- W3179871102 cites W2760370272 @default.
- W3179871102 cites W2793245122 @default.
- W3179871102 cites W2805502563 @default.
- W3179871102 cites W2806880187 @default.
- W3179871102 cites W2808103905 @default.
- W3179871102 cites W2900180747 @default.
- W3179871102 cites W2904483377 @default.
- W3179871102 cites W2933584359 @default.
- W3179871102 cites W2941472776 @default.
- W3179871102 cites W2959639774 @default.
- W3179871102 cites W2962162344 @default.
- W3179871102 cites W2962802777 @default.
- W3179871102 cites W2962835968 @default.
- W3179871102 cites W2963230974 @default.
- W3179871102 cites W2963966377 @default.
- W3179871102 cites W2964606879 @default.
- W3179871102 cites W2968870756 @default.
- W3179871102 cites W2978010459 @default.
- W3179871102 cites W2982407353 @default.
- W3179871102 cites W2998669675 @default.
- W3179871102 cites W3003720578 @default.
- W3179871102 cites W3006198072 @default.
- W3179871102 cites W3016683136 @default.
- W3179871102 cites W3022342192 @default.
- W3179871102 cites W3025779837 @default.
- W3179871102 cites W3035613124 @default.
- W3179871102 cites W3080524962 @default.
- W3179871102 cites W3080663431 @default.
- W3179871102 cites W3080756971 @default.
- W3179871102 cites W3089657753 @default.
- W3179871102 cites W3092753574 @default.
- W3179871102 cites W3092956019 @default.
- W3179871102 cites W3094151137 @default.
- W3179871102 cites W3096596051 @default.
- W3179871102 cites W3100728255 @default.
- W3179871102 cites W3106342476 @default.
- W3179871102 cites W3161219163 @default.
- W3179871102 doi "https://doi.org/10.48550/arxiv.2107.05904" @default.
- W3179871102 hasPublicationYear "2021" @default.
- W3179871102 type Work @default.
- W3179871102 sameAs 3179871102 @default.
- W3179871102 citedByCount "0" @default.
- W3179871102 crossrefType "posted-content" @default.
- W3179871102 hasAuthorship W3179871102A5021875517 @default.
- W3179871102 hasAuthorship W3179871102A5029771864 @default.
- W3179871102 hasAuthorship W3179871102A5068470372 @default.
- W3179871102 hasAuthorship W3179871102A5082109737 @default.
- W3179871102 hasAuthorship W3179871102A5083815471 @default.
- W3179871102 hasBestOaLocation W31798711021 @default.
- W3179871102 hasConcept C132525143 @default.
- W3179871102 hasConcept C153180895 @default.
- W3179871102 hasConcept C154945302 @default.
- W3179871102 hasConcept C164705383 @default.
- W3179871102 hasConcept C2776268601 @default.
- W3179871102 hasConcept C2987714656 @default.
- W3179871102 hasConcept C31510193 @default.
- W3179871102 hasConcept C41008148 @default.
- W3179871102 hasConcept C41608201 @default.
- W3179871102 hasConcept C71924100 @default.
- W3179871102 hasConcept C80444323 @default.
- W3179871102 hasConceptScore W3179871102C132525143 @default.
- W3179871102 hasConceptScore W3179871102C153180895 @default.
- W3179871102 hasConceptScore W3179871102C154945302 @default.
- W3179871102 hasConceptScore W3179871102C164705383 @default.