Multimodal Emotion Distribution Learning

Jia, Xiuyi; Shen, Xiaoxia

doi:10.1007/s12559-021-09927-5

Cited by 5 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[9] showed that multimodal learning approaches could be beneficial to improve one modality feature representation. The approach was recently applied to a wide variety of applications, such as emotion analysis [10], scene change detection [11] and medicine [12], to cite a few. Regarding audiovisual (AV) data processing, Adeel et al [13] suggested an integration of Internet of Things (IoT) and 5G Cloud-Radio Access Network to create a chaotic encryption-based lightweight model for lip-reading driven hearing aids.…”

Section: Related Workmentioning

confidence: 99%

Multimodal audio-visual information fusion using canonical-correlated Graph Neural Network for energy-efficient speech enhancement

et al. 2023

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Multimodal audio-visual information fusion using canonical-correlated Graph Neural Network for energy-efficient speech enhancement

et al. 2023

View full text Add to dashboard Cite

“…Although distributed learning [19,20] has many similarities to federal learning, in distributed learning, the worker nodes have no decision-making power, and everything is controlled by a central node. Each worker node in federated learning has full autonomy over the local data and can autonomously decide when and how to join federated learning for modeling, and federated learning places more emphasis on protecting data privacy.…”

Section: Federal Learning Workmentioning

confidence: 99%

Optimization of Suzhou Garden Infrastructure Layout Based on Federal Learning

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Along with the accelerating urbanization process in China, the problem of urban infrastructure layout has become increasingly prominent. The high density of buildings and the extremely unreasonable distribution of infrastructure make the development face great resistance. This paper reveals the problems in the layout of garden infrastructure by studying and analyzing the theoretical foundations of federal learning and distributed learning and provides an in-depth analysis and elaboration of the problem. The paper uses the shape index and landscape index of green infrastructure (green space, arable land, and water bodies), the average width of roads, road network density, and weighted buildings to conduct a comparative study through the differences in ventilation speed and temperature at different layout garden scales. According to the problems existing in the garden layout in the experimental results, corresponding improvement measures are targeted, and the infrastructure layout of the garden is combined with ecology to make the layout within the garden more suitable.

show abstract

“…Because the face is an essential aspect of human identity, machine‐assisted facial analysis has become a trending topic in a variety of applications. Facial super‐resolution is progressively being used in various applications, including face identification (Grm et al, 2019), intelligent surveillance, emotion detection (Jia & Shen, 2021; Li et al, 2021; Tian et al, 2020; Wang et al, 2021) and identity verification. It is useful in a variety of facial analysis applications, including face alignment (Bulat et al, 2018; Liu et al, 2016; Mi et al, 2023; Xu, Zhou, et al, 2022; Zhou et al, 2022), face recognition (Cheng et al, 2016; Li et al, 2019; Lin et al, 2023; Singh et al, 2018; Yang et al, 2016; Zhang et al, 2018), and E‐commerce platforms (Huang et al, 2018; Sagar et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

A novel generative adversarial network‐based super‐resolution approach for face recognition

Chougule,

Kolte,

Chamola

et al. 2024

Expert Systems

View full text Add to dashboard Cite

Face recognition is an essential feature required for a range of computer vision applications such as security, attendance systems, emotion detection, airport check‐in, and many others. The super‐resolution of subject images is an important and challenging element in numerous scenarios. At times the images are low resolution and need to be processed through super‐resolution techniques to gain more accurate results. For the problem of image super‐resolution, deep learning‐based face recognition systems have been explored in recent years; however, low‐resolution face recognition remains an arduous task. Generative adversarial network (GAN) based models are a promising approach to address this challenge. However, conventional GAN‐based models may generate images that differ significantly from an original high‐resolution image in the test set to the point that the identity of the target face may be changed. To address this shortcoming, we propose a novel U‐Net style generator architecture, where skip‐connections between the encoder and decoder layer can help in preserving the facial characteristics of the input image in the generated image, thus curbing the generator's ability to generate an entirely new image and training it to generate an image more similar in characteristics to the original image. In addition to statistical metrics like structural similarity index measure and Fréchet inception distance, we compute the pixel‐wise distance between the original and model‐generated images to ascertain that our model generates as close to the original images as possible. While we train the model for 4× super‐resolution (64 × 64 images to 256 × 256), our architecture can also be trained for an arbitrary resizing scale. Finally, the number of faces detected over high‐resolution images generated by our model is shown to be higher than state‐of‐the‐art high‐resolution image creation models for face recognition tasks.

show abstract

Multimodal Emotion Distribution Learning

Cited by 5 publications

References 42 publications

Multimodal audio-visual information fusion using canonical-correlated Graph Neural Network for energy-efficient speech enhancement

Multimodal audio-visual information fusion using canonical-correlated Graph Neural Network for energy-efficient speech enhancement

Optimization of Suzhou Garden Infrastructure Layout Based on Federal Learning

A novel generative adversarial network‐based super‐resolution approach for face recognition

Contact Info

Product

Resources

About