FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035981757> ?p ?o ?g. }

• W3035981757 abstract "Composite-database micro-expression recognition is attracting increasing attention as it is more practical to real-world applications. Though the composite database provides more sample diversity for learning good representation models, the important subtle dynamics are prone to disappearing in the domain shift such that the models greatly degrade their performance, especially for deep models. In this paper, we analyze the influence of learning complexity, including the input complexity and model complexity, and discover that the lower-resolution input data and shallower-architecture model are helpful to ease the degradation of deep models in composite-database task. Based on this, we propose a recurrent convolutional network (RCN) to explore the shallower-architecture and lower-resolution input data, shrinking model and input complexities simultaneously. Furthermore, we develop three parameter-free modules (i.e., wide expansion, shortcut connection and attention unit) to integrate with RCN without increasing any learnable parameters. These three modules can enhance the representation ability in various perspectives while preserving not-very-deep architecture for lower-resolution data. Besides, three modules can further be combined by an automatic strategy (a neural architecture search strategy) and the searched architecture becomes more robust. Extensive experiments on MEGC2019 dataset (composited of existing SMIC, CASME II and SAMM datasets) have verified the influence of learning complexity and shown that RCNs with three modules and the searched combination outperform the state-of-the-art approaches." @default.
• W3035981757 created "2020-06-25" @default.
• W3035981757 creator A5001972993 @default.
• W3035981757 creator A5019479187 @default.
• W3035981757 creator A5020220235 @default.
• W3035981757 creator A5038175380 @default.
• W3035981757 creator A5082301986 @default.
• W3035981757 date "2020-06-17" @default.
• W3035981757 modified "2023-09-26" @default.
• W3035981757 title "Revealing the Invisible with Model and Data Shrinking for Composite-database Micro-expression Recognition" @default.
• W3035981757 cites W1998391547 @default.
• W3035981757 cites W2000810120 @default.
• W3035981757 cites W2006426145 @default.
• W3035981757 cites W2033959528 @default.
• W3035981757 cites W2044106642 @default.
• W3035981757 cites W2044459166 @default.
• W3035981757 cites W2059068649 @default.
• W3035981757 cites W2093033615 @default.
• W3035981757 cites W2111999896 @default.
• W3035981757 cites W2137030524 @default.
• W3035981757 cites W2156489769 @default.
• W3035981757 cites W2194775991 @default.
• W3035981757 cites W2196663747 @default.
• W3035981757 cites W2237362194 @default.
• W3035981757 cites W2263218431 @default.
• W3035981757 cites W2295107390 @default.
• W3035981757 cites W2342983306 @default.
• W3035981757 cites W2395363464 @default.
• W3035981757 cites W2410124390 @default.
• W3035981757 cites W2426188534 @default.
• W3035981757 cites W2526853616 @default.
• W3035981757 cites W2623355927 @default.
• W3035981757 cites W2726381870 @default.
• W3035981757 cites W2769429431 @default.
• W3035981757 cites W2779656294 @default.
• W3035981757 cites W2793245122 @default.
• W3035981757 cites W2795270851 @default.
• W3035981757 cites W2806880187 @default.
• W3035981757 cites W2808064875 @default.
• W3035981757 cites W2810075754 @default.
• W3035981757 cites W2891138649 @default.
• W3035981757 cites W2910652840 @default.
• W3035981757 cites W2954688322 @default.
• W3035981757 cites W2956918801 @default.
• W3035981757 cites W2958471948 @default.
• W3035981757 cites W2963446712 @default.
• W3035981757 cites W2963840672 @default.
• W3035981757 cites W2964606879 @default.
• W3035981757 cites W2969299247 @default.
• W3035981757 cites W2971368391 @default.
• W3035981757 cites W3100951556 @default.
• W3035981757 cites W3103539074 @default.
• W3035981757 cites W3106342476 @default.
• W3035981757 cites W565148957 @default.
• W3035981757 doi "https://doi.org/10.48550/arxiv.2006.09674" @default.
• W3035981757 hasPublicationYear "2020" @default.
• W3035981757 type Work @default.
• W3035981757 sameAs 3035981757 @default.
• W3035981757 citedByCount "0" @default.
• W3035981757 crossrefType "posted-content" @default.
• W3035981757 hasAuthorship W3035981757A5001972993 @default.
• W3035981757 hasAuthorship W3035981757A5019479187 @default.
• W3035981757 hasAuthorship W3035981757A5020220235 @default.
• W3035981757 hasAuthorship W3035981757A5038175380 @default.
• W3035981757 hasAuthorship W3035981757A5082301986 @default.
• W3035981757 hasBestOaLocation W30359817571 @default.
• W3035981757 hasConcept C108583219 @default.
• W3035981757 hasConcept C119857082 @default.
• W3035981757 hasConcept C123657996 @default.
• W3035981757 hasConcept C124101348 @default.
• W3035981757 hasConcept C134306372 @default.
• W3035981757 hasConcept C142362112 @default.
• W3035981757 hasConcept C153180895 @default.
• W3035981757 hasConcept C153349607 @default.
• W3035981757 hasConcept C154945302 @default.
• W3035981757 hasConcept C162324750 @default.
• W3035981757 hasConcept C17744445 @default.
• W3035981757 hasConcept C187736073 @default.
• W3035981757 hasConcept C199360897 @default.
• W3035981757 hasConcept C199539241 @default.
• W3035981757 hasConcept C2776359362 @default.
• W3035981757 hasConcept C2780451532 @default.
• W3035981757 hasConcept C33923547 @default.
• W3035981757 hasConcept C36503486 @default.
• W3035981757 hasConcept C41008148 @default.
• W3035981757 hasConcept C77088390 @default.
• W3035981757 hasConcept C81363708 @default.
• W3035981757 hasConcept C90559484 @default.
• W3035981757 hasConcept C94625758 @default.
• W3035981757 hasConceptScore W3035981757C108583219 @default.
• W3035981757 hasConceptScore W3035981757C119857082 @default.
• W3035981757 hasConceptScore W3035981757C123657996 @default.
• W3035981757 hasConceptScore W3035981757C124101348 @default.
• W3035981757 hasConceptScore W3035981757C134306372 @default.
• W3035981757 hasConceptScore W3035981757C142362112 @default.
• W3035981757 hasConceptScore W3035981757C153180895 @default.
• W3035981757 hasConceptScore W3035981757C153349607 @default.
• W3035981757 hasConceptScore W3035981757C154945302 @default.
• W3035981757 hasConceptScore W3035981757C162324750 @default.
• W3035981757 hasConceptScore W3035981757C17744445 @default.

• next