Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385890299> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4385890299 abstract "Facial Action Unit (AU) detection is a crucial task in affective computing and social robotics as it helps to identify emotions expressed through facial expressions. Anatomically, there are innumerable correlations between AUs, which contain rich information and are vital for AU detection. Previous methods used fixed AU correlations based on expert experience or statistical rules on specific benchmarks, but it is challenging to comprehensively reflect complex correlations between AUs via hand-crafted settings. There are alternative methods that employ a fully connected graph to learn these dependencies exhaustively. However, these approaches can result in a computational explosion and high dependency with a large dataset. To address these challenges, this paper proposes a novel self-adjusting AU-correlation learning (SACL) method with less computation for AU detection. This method adaptively learns and updates AU correlation graphs by efficiently leveraging the characteristics of different levels of AU motion and emotion representation information extracted in different stages of the network. Moreover, this paper explores the role of multi-scale learning in correlation information extraction, and design a simple yet effective multi-scale feature learning (MSFL) method to promote better performance in AU detection. By integrating AU correlation information with multi-scale features, the proposed method obtains a more robust feature representation for the final AU detection. Extensive experiments show that the proposed method outperforms the state-of-the-art methods on widely used AU detection benchmark datasets, with only 28.7% and 12.0% of the parameters and FLOPs of the best method, respectively. The code for this method is available at url{https://github.com/linuxsino/Self-adjusting-AU}." @default.
- W4385890299 created "2023-08-17" @default.
- W4385890299 creator A5017662559 @default.
- W4385890299 creator A5033035049 @default.
- W4385890299 creator A5057647276 @default.
- W4385890299 creator A5062522283 @default.
- W4385890299 creator A5063288559 @default.
- W4385890299 creator A5064150384 @default.
- W4385890299 creator A5077422209 @default.
- W4385890299 date "2023-08-15" @default.
- W4385890299 modified "2023-09-27" @default.
- W4385890299 title "Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection" @default.
- W4385890299 doi "https://doi.org/10.48550/arxiv.2308.07770" @default.
- W4385890299 hasPublicationYear "2023" @default.
- W4385890299 type Work @default.
- W4385890299 citedByCount "0" @default.
- W4385890299 crossrefType "posted-content" @default.
- W4385890299 hasAuthorship W4385890299A5017662559 @default.
- W4385890299 hasAuthorship W4385890299A5033035049 @default.
- W4385890299 hasAuthorship W4385890299A5057647276 @default.
- W4385890299 hasAuthorship W4385890299A5062522283 @default.
- W4385890299 hasAuthorship W4385890299A5063288559 @default.
- W4385890299 hasAuthorship W4385890299A5064150384 @default.
- W4385890299 hasAuthorship W4385890299A5077422209 @default.
- W4385890299 hasBestOaLocation W43858902991 @default.
- W4385890299 hasConcept C117220453 @default.
- W4385890299 hasConcept C119857082 @default.
- W4385890299 hasConcept C121332964 @default.
- W4385890299 hasConcept C132525143 @default.
- W4385890299 hasConcept C13280743 @default.
- W4385890299 hasConcept C138885662 @default.
- W4385890299 hasConcept C153180895 @default.
- W4385890299 hasConcept C154945302 @default.
- W4385890299 hasConcept C162324750 @default.
- W4385890299 hasConcept C177264268 @default.
- W4385890299 hasConcept C185798385 @default.
- W4385890299 hasConcept C187736073 @default.
- W4385890299 hasConcept C199360897 @default.
- W4385890299 hasConcept C205649164 @default.
- W4385890299 hasConcept C2524010 @default.
- W4385890299 hasConcept C2776401178 @default.
- W4385890299 hasConcept C2776760102 @default.
- W4385890299 hasConcept C2780451532 @default.
- W4385890299 hasConcept C2780791683 @default.
- W4385890299 hasConcept C33923547 @default.
- W4385890299 hasConcept C41008148 @default.
- W4385890299 hasConcept C41895202 @default.
- W4385890299 hasConcept C52622490 @default.
- W4385890299 hasConcept C62520636 @default.
- W4385890299 hasConcept C80444323 @default.
- W4385890299 hasConceptScore W4385890299C117220453 @default.
- W4385890299 hasConceptScore W4385890299C119857082 @default.
- W4385890299 hasConceptScore W4385890299C121332964 @default.
- W4385890299 hasConceptScore W4385890299C132525143 @default.
- W4385890299 hasConceptScore W4385890299C13280743 @default.
- W4385890299 hasConceptScore W4385890299C138885662 @default.
- W4385890299 hasConceptScore W4385890299C153180895 @default.
- W4385890299 hasConceptScore W4385890299C154945302 @default.
- W4385890299 hasConceptScore W4385890299C162324750 @default.
- W4385890299 hasConceptScore W4385890299C177264268 @default.
- W4385890299 hasConceptScore W4385890299C185798385 @default.
- W4385890299 hasConceptScore W4385890299C187736073 @default.
- W4385890299 hasConceptScore W4385890299C199360897 @default.
- W4385890299 hasConceptScore W4385890299C205649164 @default.
- W4385890299 hasConceptScore W4385890299C2524010 @default.
- W4385890299 hasConceptScore W4385890299C2776401178 @default.
- W4385890299 hasConceptScore W4385890299C2776760102 @default.
- W4385890299 hasConceptScore W4385890299C2780451532 @default.
- W4385890299 hasConceptScore W4385890299C2780791683 @default.
- W4385890299 hasConceptScore W4385890299C33923547 @default.
- W4385890299 hasConceptScore W4385890299C41008148 @default.
- W4385890299 hasConceptScore W4385890299C41895202 @default.
- W4385890299 hasConceptScore W4385890299C52622490 @default.
- W4385890299 hasConceptScore W4385890299C62520636 @default.
- W4385890299 hasConceptScore W4385890299C80444323 @default.
- W4385890299 hasLocation W43858902991 @default.
- W4385890299 hasOpenAccess W4385890299 @default.
- W4385890299 hasPrimaryLocation W43858902991 @default.
- W4385890299 hasRelatedWork W1964120219 @default.
- W4385890299 hasRelatedWork W2000165426 @default.
- W4385890299 hasRelatedWork W2114557664 @default.
- W4385890299 hasRelatedWork W2144059113 @default.
- W4385890299 hasRelatedWork W2146076056 @default.
- W4385890299 hasRelatedWork W2385132419 @default.
- W4385890299 hasRelatedWork W2546942002 @default.
- W4385890299 hasRelatedWork W2772780115 @default.
- W4385890299 hasRelatedWork W2811390910 @default.
- W4385890299 hasRelatedWork W3003836766 @default.
- W4385890299 isParatext "false" @default.
- W4385890299 isRetracted "false" @default.
- W4385890299 workType "article" @default.