A novel technique is proposed for the analysis and modeling of timbre perception features, including a new terminology system for evaluating timbre in musical instruments. This database consists of 16 expert and novice evaluation terms, including five pairs with opposite polarity. In addition, a material library containing 72 samples (including 37 Chinese orchestral instruments, 11 Chinese minority instruments, and 24 Western orchestral instruments) and a 54-sample objective acoustic parameter set were developed as part of the study. The method of successive categories was applied to each term for subjective assessment. A mathematical model of timbre perception features (i.e., bright or dark, raspy or mellow, sharp or vigorous, coarse or pure, and hoarse or consonant) was then developed for the first time using linear regression, support vector regression, a neural network, and random forest algorithms. Experimental results showed the proposed model accurately predicted these attributes. Finally, an improved technique for 3D timbre space construction is proposed. Auditory perception attributes for this 3D timbre space were determined by analyzing the correlation between each spatial dimension and the 16 timbre evaluation terms.

Skeleton-based action recognition is a research hotspot in the field of computer vision. Currently, the mainstream method is based on Graph Convolutional Networks (GCNs). Although there are many advantages of GCNs, GCNs mainly rely on graph topologies to draw dependencies between the joints, which are limited in capturing long-distance dependencies. Meanwhile, Transformer-based methods have been applied to skeleton-based action recognition because they effectively capture long-distance dependencies. However, existing Transformer-based methods lose the inherent connection information of human skeleton joints because they do not yet focus on initial graph structure information. This paper aims to improve the accuracy of skeleton-based action recognition. Therefore, a Graph Skeleton Transformer network (GSTN) for action recognition is proposed, which is based on Transformer architecture to extract global features, while using undirected graph information represented by the symmetric matrix to extract local features. Two encodings are utilized in feature processing to improve joints’ semantic and centrality features. In the process of multi-stream fusion strategies, a grid-search-based method is used to assign weights to each input stream to optimize the fusion results. We tested our method using three action recognition datasets: NTU RGB+D 60, NTU RGB+D 120, and NW-UCLA. The experimental results show that our model’s accuracy is comparable to state-of-the-art approaches.

This article investigated the timbre of musical sound and visual color; comprehensively used experimental psychology, audio information processing and other experimental methods and technical means; and conducted research on the relationship between timbre attributes and visual color. First, we designed and implemented a subjective perception experiment based on audiovisual cross-modal timbre-color correlation. Through the statistical analysis of the experimental data, we obtained a complete timbre-color cross-modal correlation dataset. Second, through the visual processing and correlation analysis of the timbre-color correlation data, it is proven that there is a certain correlation between the timbre dimension and the color dimension. On this basis, we used three algorithms to construct a timbre-color correlation model, namely, multiple linear regression, BP neural network and SVR, and we verified the accuracy of the three models. The timbre-color correlation dataset constructed in this paper can provide basic data support for audiovisual cross-modal research. The timbre-color correlation model constructed in this paper can provide a theoretical basis for cross-modal audiovisual applications. In addition, the timbre-color cross-modality research method in this paper can provide new research ideas for audio-visual cross-modality research.

Skeleton-based human action recognition based on Neural Architecture Search (NAS.) adopts a one-shot NAS strategy. It improves the speed of evaluating candidate models in the search space through weight sharing, which has attracted significant attention. However, directly applying the one-shot NAS method for skeleton recognition requires training a super-net with a large search space that traverses various combinations of model parameters, which often leads to overly large network models and high computational costs. In addition, when training this super-net, the one-shot NAS needs to traverse the entire search space of the complete skeleton recognition task. Furthermore, the traditional method does not consider the optimization of the search strategy. As a result, a significant amount of search time is required to obtain a better skeleton recognition network model. A more efficient weighting model, a NAS skeleton recognition model based on the Single Path One-shot (SNAS-GCN) strategy, is proposed to address the above challenges. First, to reduce the model search space, a simplified four-category search space is introduced to replace the mainstream multi-category search space. Second, to improve the model search efficiency, a single-path one-shot approach is introduced, through which the model randomly samples one architecture at each step of the search training optimization. Finally, an adaptive Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is proposed to obtain a candidate structure of the perfect model automatically. With these three steps, the entire network architecture of the recognition model (and its weights) is fully and equally trained significantly. The search and training costs will be greatly reduced. The search-out model is trained by the NTU-RGB + D and Kinetics datasets to evaluate the performance of the proposed model’s search strategy. The experimental results show that the search time of the proposed method in this paper is 0.3 times longer than that of the state-of-the-art method. Meanwhile, the recognition accuracy is roughly comparable compared to that of the SOTA NAS-GCN method.

Color harmony is the hotspot of many researchers in the fields of art and design which is widely used in various artworks and design activities. As for psychology, color harmony is closely related to human’s perception and cognition, although, the research of its generation process has not been fully focused on. With experimental psychology with artificial intelligence technology combined together, our aim is to investigate the factors affecting color harmony on the basis of the generation process from perception to cognition, and construct a mathematical model to predict its degree, so as to realize the quantitatively analysis and measurement of color harmony. We classify the factors affecting color harmony into objective and subjective ones. Among them, the objective factors are constructed based on the three principle elements of color with a total of 21-dimensional color-pair objective physical features extracted. And the subjective factors are divided into direct psychological effects and indirect psychological effects. 180 two-color combinations were evaluated by 30 subjects based on color harmony and its subjective factors on discrete scales ranging from −2 to 2. Correlation analysis reveals that color harmony is not only affected by objective factors, but also by subjective factors which has a stronger correlation than that of the objective ones. Finally, machine learning algorithms were adopted to construct a mathematical model, which has been proved that the linear relationship can well explain the generation mechanism of color harmony.