Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Facial micro-expression recognition (MER) is a challenging problem, due to transient and subtle micro-expression (ME) actions. Most existing methods depend on hand-crafted features, key frames like onset, apex, and offset frames, or deep networks limited by small-scale and low-diversity datasets. In this paper, we propose an end-to-end micro-action-aware deep learning framework with advantages from transformer, graph convolution, and vanilla convolution. In particular, we propose a novel F5C block composed of fully-connected convolution and channel correspondence convolution to directly extract local-global features from a sequence of raw frames, without the prior knowledge of key frames. The transformer-style fully-connected convolution is proposed to extract local features while maintaining global receptive fields, and the graph-style channel correspondence convolution is introduced to model the correlations among feature patterns. Moreover, MER, optical flow estimation, and facial landmark detection are jointly trained by sharing the local-global features. The two latter tasks contribute to capturing facial subtle action information for MER, which can alleviate the impact of insufficient training data. Extensive experiments demonstrate that our framework (i) outperforms the state-of-the-art MER methods on CASME II, SAMM, and SMIC benchmarks, (ii) works well for optical flow estimation and facial landmark detection, and (iii) can capture facial subtle muscle actions in local regions associated with MEs. The code is available at https://github.com/CYF-cuber/MOL.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2025.3581162DOI Listing

Publication Analysis

Top Keywords

optical flow
12
key frames
8
fully-connected convolution
8
channel correspondence
8
correspondence convolution
8
local-global features
8
flow estimation
8
estimation facial
8
facial landmark
8
landmark detection
8

Similar Publications

Human beings have the ability to continuously analyze a video and immediately extract the motion components. We want to adopt this paradigm to provide a coherent and stable motion segmentation over the video sequence. In this perspective, we propose a novel long-term spatio-temporal model operating in a totally unsupervised way.

View Article and Find Full Text PDF

Titanium dioxide (TiO) thin films were deposited on glass substrates under HV conditions at room temperature by the physical vapor deposition method. Produced titanium thin films were post-annealed at 573 K at different oxygen flows (0, 9 and 23 cm/s). The influence of different oxygen flows on nano-structure, crystallography, and optical parameters of TiO films was investigated by XRD, AFM, and spectrophotometer in the UV-VIS wavelength range.

View Article and Find Full Text PDF

Background: Invasive coronary physiology including fractional flow reserve (FFR), instantaneous wave-free ratio (iFR), and coronary flow reserve (CFR) are guideline-endorsed tools to guide the management of coronary artery disease (CAD). Complex factors impact and confound these assessments, and discordance between modalities complicates clinical management. iEquate is a prospective observational trial that combines multi-modality coronary physiology and optical coherence tomography (OCT) to identify the determinants of pressure-wire derived myocardial ischemia and iFR-FFR discordance.

View Article and Find Full Text PDF

Introduction: Autoimmune uveitis is a sight-threatening inflammatory eye disease driven by immune dysregulation. We previously introduced a therapeutic strategy involving the induction of retinal-antigen-specific regulatory T cells (Tregs) via αCD4 antibody injection followed by administration of the retinal self-peptide IRBP1-20, which effectively suppresses inflammation during the onset of experimental autoimmune uveitis (EAU).

Methods: We evaluated the long-term therapeutic efficacy of this approach in a chronic EAU model.

View Article and Find Full Text PDF

Background: Lung ischemia-reperfusion injury (LIRI) is a pathological condition characterized by aggravated oxidative-inflammatory tissue damage that occurs upon blood flow restoration after ischemia. LIRI can lead to severe complications, including primary graft dysfunction in lung transplants and multi-organ failure. However, current treatments remain limited.

View Article and Find Full Text PDF