Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319073169> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4319073169 endingPage "131" @default.
- W4319073169 startingPage "122" @default.
- W4319073169 abstract "Micro-expressions (MEs) can reveal the hidden but real emotion and are usually caused spontaneously. However, the characteristics of subtlety and temporariness with the lack of sufficient ME datasets make it hard for recognition. In this paper, we propose an adaptively temporal augmented momentum contrastive learning to alleviate these problems. For the small scale, we pre-train the model on a new interpolated dataset via contrastive learning with momentum contrast (MoCo). For the subtle and rapid facial movements, we augment the temporal dynamics using an adaptive dropout operation to redundant frames. Specifically, we use a recursive way to create a new interpolated dataset from raw datasets firstly. Then we design a shallow model with an inflated inception module as the encoder of the contrastive learning. Afterward, we pre-train the model on the new dataset via momentum contrastive learning. During the pre-training, we propose adaptively temporal augmentation via generative adversarial learning. After the pre-training, we take the encoder out and finetune it for recognition. Finally, we perform extensive experiments and ablation studies on three ME datasets. The results demonstrate the effectiveness of the MoCo-like pre-training and the temporal augmentation for recognition. Moreover, the pre-trained model outperforms other state-of-the-art models based on optical flow." @default.
- W4319073169 created "2023-02-04" @default.
- W4319073169 creator A5005741793 @default.
- W4319073169 creator A5063402368 @default.
- W4319073169 date "2023-03-01" @default.
- W4319073169 modified "2023-09-24" @default.
- W4319073169 title "Temporal augmented contrastive learning for micro-expression recognition" @default.
- W4319073169 cites W1854318472 @default.
- W4319073169 cites W1993065982 @default.
- W4319073169 cites W2003238582 @default.
- W4319073169 cites W2006426145 @default.
- W4319073169 cites W2087550562 @default.
- W4319073169 cites W2139916508 @default.
- W4319073169 cites W2156489769 @default.
- W4319073169 cites W2269299223 @default.
- W4319073169 cites W2426188534 @default.
- W4319073169 cites W2478411578 @default.
- W4319073169 cites W2526853616 @default.
- W4319073169 cites W2571743746 @default.
- W4319073169 cites W2726381870 @default.
- W4319073169 cites W2963230974 @default.
- W4319073169 cites W2996310233 @default.
- W4319073169 cites W3045994539 @default.
- W4319073169 cites W3080756971 @default.
- W4319073169 cites W3096596051 @default.
- W4319073169 cites W3098002894 @default.
- W4319073169 cites W3103539074 @default.
- W4319073169 cites W3139546544 @default.
- W4319073169 cites W3195543922 @default.
- W4319073169 cites W4254816946 @default.
- W4319073169 cites W4312399808 @default.
- W4319073169 doi "https://doi.org/10.1016/j.patrec.2023.02.003" @default.
- W4319073169 hasPublicationYear "2023" @default.
- W4319073169 type Work @default.
- W4319073169 citedByCount "2" @default.
- W4319073169 countsByYear W43190731692023 @default.
- W4319073169 crossrefType "journal-article" @default.
- W4319073169 hasAuthorship W4319073169A5005741793 @default.
- W4319073169 hasAuthorship W4319073169A5063402368 @default.
- W4319073169 hasConcept C101738243 @default.
- W4319073169 hasConcept C108583219 @default.
- W4319073169 hasConcept C119857082 @default.
- W4319073169 hasConcept C153180895 @default.
- W4319073169 hasConcept C154945302 @default.
- W4319073169 hasConcept C2776145597 @default.
- W4319073169 hasConcept C28490314 @default.
- W4319073169 hasConcept C41008148 @default.
- W4319073169 hasConceptScore W4319073169C101738243 @default.
- W4319073169 hasConceptScore W4319073169C108583219 @default.
- W4319073169 hasConceptScore W4319073169C119857082 @default.
- W4319073169 hasConceptScore W4319073169C153180895 @default.
- W4319073169 hasConceptScore W4319073169C154945302 @default.
- W4319073169 hasConceptScore W4319073169C2776145597 @default.
- W4319073169 hasConceptScore W4319073169C28490314 @default.
- W4319073169 hasConceptScore W4319073169C41008148 @default.
- W4319073169 hasFunder F4320321001 @default.
- W4319073169 hasLocation W43190731691 @default.
- W4319073169 hasOpenAccess W4319073169 @default.
- W4319073169 hasPrimaryLocation W43190731691 @default.
- W4319073169 hasRelatedWork W2292254049 @default.
- W4319073169 hasRelatedWork W2669956259 @default.
- W4319073169 hasRelatedWork W2897995864 @default.
- W4319073169 hasRelatedWork W2939353110 @default.
- W4319073169 hasRelatedWork W2998168123 @default.
- W4319073169 hasRelatedWork W3165463024 @default.
- W4319073169 hasRelatedWork W4287178339 @default.
- W4319073169 hasRelatedWork W4287995534 @default.
- W4319073169 hasRelatedWork W4327774331 @default.
- W4319073169 hasRelatedWork W4380075502 @default.
- W4319073169 hasVolume "167" @default.
- W4319073169 isParatext "false" @default.
- W4319073169 isRetracted "false" @default.
- W4319073169 workType "article" @default.