RGB-D action recognition based on discriminative common structure learning model

Liu, Tianshan; Kong, Jun; Jiang, Min; Huo, Hongtao

doi:10.1117/1.jei.28.2.023012

Cited by 8 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Domestic scholars have also made many contributions to image aesthetics assessment. Liu et al [17] extracted lowlevel visual features, high-level aesthetic features, and visual area features from the overall area and visually critical areas of an image and established an image aesthetic classifier and an aesthetic score assessment model.…”

Section: Research Statusmentioning

confidence: 99%

Design of Packaging Design Evaluation Architecture Based on Deep Learning

Shi

2022

Scientific Programming

View full text Add to dashboard Cite

Most researchers use visual communication symbols to achieve the purpose of information dissemination, which is also a very important marketing tool for the current era of packaging design. And the use of visual communication technology to make better product packaging design has become one of most the important means for major enterprises to sell their products and construct a good brand image. In this paper, we use a deep CNN-based aesthetic classification method for splash screens and a deep learning-based NIMA neural network to predict the aesthetic evaluation distribution of splash screen images, respectively. The connotation of visual communication and packaging design and the impact of the role of visual communication technology on packaging design are analyzed.

show abstract

Section: Research Statusmentioning

confidence: 99%

Design of Packaging Design Evaluation Architecture Based on Deep Learning

Shi

2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Most of the existing RGB-D-based methods only stitch the original heterogeneous features but do not find the potential relationship between different modes. Liu et al 20 . extracted deep learning-based features and hand-crafted features from multimodal data (skeleton, depth, and RGB) and used generalized ensemble matrix decomposition to learn shared features between different modalities.…”

Section: Related Workmentioning

confidence: 99%

Feature difference and feature correlation learning mechanism for skeleton-based action recognition

2023

Self Cite

View full text Add to dashboard Cite

.In recent years, skeleton-based action recognition has become increasingly popular in the field of human action recognition, and graph convolutional networks (GCNs) have shown better advantages in this task. Many GCN-based methods are insufficient in the latent relationship between features, which affects the discriminability of features being not rich enough. These potential feature relationships can manifest as feature differences that change due to actions and feature correlations that interact with each other. Therefore, we propose a feature difference and feature correlation learning mechanism to learn discriminative augmentation features, including feature differences in actions and feature correlations between joints. First, we propose a temporal feature difference and correlation learning module (FDCL) (TFDCL). In adjacent temporal frames, we extract feature correlations between related parts. Feature differences are captured through changes in joints over the overall long-term timeline. Second, we propose a channel FDCL module. Different channels contain different types of features for actions. We use convolution operations to interact between channels, continuously extracting the strongest features to obtain feature maps. Third, we propose a temporal channel context topology (TCCT) module to dynamically learn global contextual features of all joints during motion. Finally, experiments are conducted on the NTU-RGBD 60 dataset and the kinetics-skeleton 400 dataset to verify the effectiveness of the network.

show abstract

“…To increase the stability of the CAE KNN, we propose a novel algorithm, namely attCAE KNN, which is the first time to explore the attention strategy to CAE. Attention strategy (Xu et al 2015;Gregor et al 2015) kNN Module The first part is the encoder that consists of the channel attention block and the spatial attention block (Liu et al 2019), which differs from the classical encoder in inserting CBAM, as shown in Fig. 4.…”

Section: The Attention-cae-knn-based Approachmentioning

confidence: 99%

“…makes the attCAE KNN focus on 'what' is meaningful for given astronomical images so that attCAE KNN could ignore the background noise. We build attCAE KNN by adopting a convolutional block attention module (CBAMLiu et al 2019). Its architecture is shown in Fig.3, including encoder, decoder, and KNN module.The decoder and KNN module have been described in Sect.…”

mentioning

confidence: 99%

Identifying outliers in astronomical images with unsupervised machine learning

Han,

Zou,

et al. 2022

Preprint

View full text Add to dashboard Cite

Astronomical outliers, such as unusual, rare or unknown types of astronomical objects or phenomena, constantly lead to the discovery of genuinely unforeseen knowledge in astronomy. More unpredictable outliers will be uncovered in principle with the increment of the coverage and quality of upcoming survey data. However, it is a severe challenge to mine rare and unexpected targets from enormous data with human inspection due to a significant workload. Supervised learning is also unsuitable for this purpose since designing proper training sets for unanticipated signals is unworkable. Motivated by these challenges, we adopt unsupervised machine learning approaches to identify outliers in the data of galaxy images to explore the paths for detecting astronomical outliers. For comparison, we construct three methods, which are built upon the k-nearest neighbors (KNN), Convolutional Auto-Encoder (CAE) + KNN, and CAE + KNN + Attention Mechanism (attCAE KNN) separately. Testing sets are created based on the Galaxy Zoo image data published online to evaluate the performance of the above methods. Results show that attCAE KNN achieves the best recall (78%), which is 53% higher than the classical KNN method and 22% higher than CAE+KNN. The efficiency

show abstract

RGB-D action recognition based on discriminative common structure learning model

Cited by 8 publications

References 0 publications

Design of Packaging Design Evaluation Architecture Based on Deep Learning

Design of Packaging Design Evaluation Architecture Based on Deep Learning

Feature difference and feature correlation learning mechanism for skeleton-based action recognition

Identifying outliers in astronomical images with unsupervised machine learning

Contact Info

Product

Resources

About