Most musical compositions utilize repetition as a fundamental element to create captivating aesthetic experiences. However, the potential of repetition in machine-learning-based algorithmic composition has not been thoroughly investigated. This article aims to make an initial attempt at repetition modeling by generating motif-level repetitions and integrating them into music through a combination of example-based and domain knowledge–based learning techniques. The article presents a new Motif-to-music Generation Model (MGM) that combines a motif-level repetition generator (MRG) and an outline-to-music generator (O2MG). To train this model, a new music repetition dataset (MRD) has been created, which includes 584,329 samples from various categories of motif repetition and 3,545 outline-music sequences from pop piano music. The MRG uses a Transformer encoder to learn the representation of music notes from MRD, while the repetition-aware learner in MRG takes advantage of the unique characteristics of repetitions based on music theory. The O2MG applies a novel outline-to-music learning strategy to learn the relationships among motif-level repetitions in the music and generate music based on these repetitions. The experiments show that MGM can generate a variety of beautiful repetitions with any given motif, improving the music quality and structure of machine-composed music.

3D human pose estimation has been researched for decades with promising fruits. 3D human pose lifting is one of the promising research directions toward the task where both estimated pose and ground truth pose data are used for training. Existing pose lifting works mainly focus on improving the performance of estimated pose, but they usually underperform when testing on the ground truth pose data. We observe that the performance of the estimated pose can be easily improved by preparing good quality 2D pose, such as fine-tuning the 2D pose or using advanced 2D pose detectors. As such, we concentrate on improving the 3D human pose lifting via ground truth data for the future improvement of more quality estimated pose data. Towards this goal, a simple yet effective model called Global-local Adaptive Graph Convolutional Network (GLA-GCN) is proposed in this work. Our GLA-GCN globally models the spatiotemporal structure via a graph representation and backtraces local joint features for 3D human pose estimation via individually connected layers. To validate our model design, we conduct extensive experiments on three benchmark datasets: Human3.6M, HumanEva-I, and MPI-INF-3DHP. Experimental results show that our GLA-GCN1implemented with ground truth 2D poses significantly outperforms state-of-the-art methods (e.g., up to 3%, 17%, and 14% error reductions on Human3.6M, HumanEva-I, and MPI-INF-3DHP, respectively).

User preference music transfer (UPMT) is a new problem in music style transfer that can be applied to many scenarios but remains understudied. Transferring an arbitrary song to fit a user’s preferences increases musical diversity and improves user engagement, which can greatly benefit individuals’ mental health. Most music style transfer approaches rely on data-driven methods. In general, however, constructing a large training dataset is challenging because users can rarely provide enough of their favorite songs. To address this problem, this paper proposes a novel hybrid method called User Preference Transformer (UP-Transformer) which uses prior knowledge of only one piece of a user’s favorite music. Based on the distribution of music events in the provided music, we propose a new favorite-aware loss function to fine-tune the Transformer-based model. Two steps are proposed in the transfer phase to achieve UPMT based on the extracted music pattern in a user’s favorite music. Additionally, to alleviate the problem of evaluating melodic similarity in music style transfer, we propose a new concept called pattern similarity (PS) to measure the similarity between two pieces of music. Statistical tests indicate that the results of PS are consistent with the similarity score in a qualitative experiment. Furthermore, experimental results on subjects show that the transferred music achieves better performance in musicality, similarity, and user preferences.

Repetition, a basic form of artistic creation, appears in most musical works and delivers enthralling aesthetic experiences. However, repetition remains underexplored in terms of automatic music composition. As an initial effort in repetition modelling, this paper focuses on generating motif-level repetitions via domain knowledge-based and example-based learning techniques. A novel repetition transformer (R-Transformer) that combines a Transformer encoder and a repetition-aware learner is trained on a new repetition dataset with 584,329 samples from different categories of motif repetition. The Transformer encoder learns the representation among music notes from the repetition dataset; the novel repetition-aware learner exploits repetitions' unique characteristics based on music theory. Experiments show that, with any given motif, R-Transformer can generate a large number of variable and beautiful repetitions. With ingenious fusion of these high-quality pieces, the musicality and appeal of machine-composed music have been greatly improved.

The class imbalance problem is characterized by the unequal distribution of different class samples, usually resulting in a learning bias toward the majority class. In the past decades, kinds of techniques have been proposed to alleviate this problem. Among those approaches, one promising method, interpolation-based oversampling, proposes to generate synthetic minority samples based on selected reference data, which can effectively solve the skewed distribution of data samples. However, there are several unsolved issues in interpolation-based oversampling. Existing methods often suffer from noisy synthetic samples due to improper data clustering and unsatisfactory reference selection. In this paper, we propose the position-aware safe boundary interpolation oversampling algorithm (PABIO) to address such issues. We firstly introduce a combined clustering algorithm for minority samples to overcome the shortage of clustering methods which are only distance-based or density-based. Then a position-aware interpolation-based oversampling algorithm is proposed for different minority clusters. Especially, we develop a novel method to leverage the majority class information to learn a safe boundary for generating synthetic points. The proposed PABIO is evaluated on multiple imbalanced datasets classified by two base classifiers: support vector machine (SVM) and C4.5 decision tree classifier. Experimental results show that our proposed PABIO outperforms other baselines among benchmark datasets.