4 research outputs found
SG-DSN : a Semantic Graph-based Dual-Stream Network for facial expression recognition
No full textAbstractFacial expression recognition (FER) is a crucial task for human emotion analysis and has attracted wide interest in the field of computer vision and affective computing. General convolutional-based FER methods rely on the powerful pattern abstraction of deep models, but they lack the ability to use semantic information behind significant facial areas in physiological anatomy and cognitive neurology. In this work, we propose a novel approach for expression feature learning called Semantic Graph-based Dual-Stream Network (SG-DSN), which designs a graph representation to model key appearance and geometric facial changes as well as their semantic relationships. A dual-stream network (DSN) with stacked graph convolutional attention blocks (GCABs) is introduced to automatically learn discriminative features from the organized graph representation and finally predict expressions. Experiments on three lab-controlled datasets and two in-the-wild datasets demonstrate that the proposed SG-DSN achieves competitive performance compared with several latest methods.Abstract
Facial expression recognition (FER) is a crucial task for human emotion analysis and has attracted wide interest in the field of computer vision and affective computing. General convolutional-based FER methods rely on the powerful pattern abstraction of deep models, but they lack the ability to use semantic information behind significant facial areas in physiological anatomy and cognitive neurology. In this work, we propose a novel approach for expression feature learning called Semantic Graph-based Dual-Stream Network (SG-DSN), which designs a graph representation to model key appearance and geometric facial changes as well as their semantic relationships. A dual-stream network (DSN) with stacked graph convolutional attention blocks (GCABs) is introduced to automatically learn discriminative features from the organized graph representation and finally predict expressions. Experiments on three lab-controlled datasets and two in-the-wild datasets demonstrate that the proposed SG-DSN achieves competitive performance compared with several latest methods
SG-DSN:a Semantic Graph-based Dual-Stream Network for facial expression recognition
No full textAbstract
Facial expression recognition (FER) is a crucial task for human emotion analysis and has attracted wide interest in the field of computer vision and affective computing. General convolutional-based FER methods rely on the powerful pattern abstraction of deep models, but they lack the ability to use semantic information behind significant facial areas in physiological anatomy and cognitive neurology. In this work, we propose a novel approach for expression feature learning called Semantic Graph-based Dual-Stream Network (SG-DSN), which designs a graph representation to model key appearance and geometric facial changes as well as their semantic relationships. A dual-stream network (DSN) with stacked graph convolutional attention blocks (GCABs) is introduced to automatically learn discriminative features from the organized graph representation and finally predict expressions. Experiments on three lab-controlled datasets and two in-the-wild datasets demonstrate that the proposed SG-DSN achieves competitive performance compared with several latest methods
Cluster-Dominated Electrochemiluminescence of Tertiary Amines in Polyethyleneimine Nanoparticles: Mechanism Insights and Sensing Application
No full textDesigning and screening highly efficient and cost-effective
luminophores
have always been a challenge to develop sensitive electrochemiluminescence
(ECL) biosensors. Herein, polyethyleneimine nanoparticles (PEI NPs),
a kind of nonconjugated polymer (NCP) NPs with tertiary amine clusters,
were developed as an ECL luminophore. Specifically, PEI NPs were synthesized
by a one-step hydrothermal method using PEI and formaldehyde. The
properties of PEI NPs were investigated in detail using photochemical
and electrochemical techniques. The results showed cluster-dominated
luminescence of tertiary amines in PEI NPs via “through-space
conjugation”. This non-negligible ECL performance (at 631 nm)
was also verified by the initiated reduction–oxidation process.
With persulfate as a coreactant, PEI NPs acted as both the luminophore
and coreaction accelerator to enhance the ECL intensity remarkably,
which was eightfold higher than that of isolated PEI. Moreover, choosing
dopamine as the model target, a highly sensitive “signal off”
ternary ECL sensor was constructed utilizing PEI NPs as the luminophore.
Dopamine could be oxidized to benzoquinone at the sensing interface,
quenching the signal via ECL energy transfer. Free from any signal
amplification, the proposed sensor achieved a low detection limit
(4.3 nM) for target monitoring with good selectivity and stability.
This strategy not only provides a unique perspective for designing
novel efficient and facile ECL luminophores of tertiary amines but
also broadens the biological application of NCP NPs
