Capturing intricate and subtle variations in human expressiveness in music performance using computational approaches is challenging. In this paper, we propose a novel approach for reconstructing human expressiveness in piano performance with a multi-layer bi-directional Transformer encoder. To address the needs for large amounts of accurately captured and score-aligned performance data in training neural networks, we use transcribed scores obtained from an existing transcription model to train our model. We integrate pianist identities to control the sampling process and explore the ability of our system to model variations in expressiveness for different pianists. The system is evaluated through statistical analysis of generated expressive performances and a listening test. Overall, the results suggest that our method achieves state-of-the-art in generating human-like piano performances from transcribed scores, while fully and consistently reconstructing human expressiveness poses further challenges.
相關內容
Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs and outputs usually imply more tokens involved in computations. Directly removing the less attentive tokens has been discussed for the image classification task but can not be extended to semantic segmentation since a dense prediction is required for every patch. To this end, this work introduces a Dynamic Token Pruning (DToP) method based on the early exit of tokens for semantic segmentation. Motivated by the coarse-to-fine segmentation process by humans, we naturally split the widely adopted auxiliary-loss-based network architecture into several stages, where each auxiliary block grades every token's difficulty level. We can finalize the prediction of easy tokens in advance without completing the entire forward pass. Moreover, we keep $k$ highest confidence tokens for each semantic category to uphold the representative context information. Thus, computational complexity will change with the difficulty of the input, akin to the way humans do segmentation. Experiments suggest that the proposed DToP architecture reduces on average $20\% - 35\%$ of computational cost for current semantic segmentation methods based on plain vision transformers without accuracy degradation.
Person clustering with multi-modal clues, including faces, bodies, and voices, is critical for various tasks, such as movie parsing and identity-based movie editing. Related methods such as multi-view clustering mainly project multi-modal features into a joint feature space. However, multi-modal clue features are usually rather weakly correlated due to the semantic gap from the modality-specific uniqueness. As a result, these methods are not suitable for person clustering. In this paper, we propose a Relation-Aware Distribution representation Network (RAD-Net) to generate a distribution representation for multi-modal clues. The distribution representation of a clue is a vector consisting of the relation between this clue and all other clues from all modalities, thus being modality agnostic and good for person clustering. Accordingly, we introduce a graph-based method to construct distribution representation and employ a cyclic update policy to refine distribution representation progressively. Our method achieves substantial improvements of +6% and +8.2% in F-score on the Video Person-Clustering Dataset (VPCD) and VoxCeleb2 multi-view clustering dataset, respectively. Codes will be released publicly upon acceptance.
Location fingerprinting based on RSSI becomes a mainstream indoor localization technique due to its advantage of not requiring the installation of new infrastructure and the modification of existing devices, especially given the prevalence of Wi-Fi-enabled devices and the ubiquitous Wi-Fi access in modern buildings. The use of AI/ML technologies like DNNs makes location fingerprinting more accurate and reliable, especially for large-scale multi-building and multi-floor indoor localization. The application of DNNs for indoor localization, however, depends on a large amount of preprocessed and deliberately-labeled data for their training. Considering the difficulty of the data collection in an indoor environment, especially under the current epidemic situation of COVID-19, we investigate three different methods of RSSI data augmentation based on Multi-Output Gaussian Process (MOGP), i.e., by a single floor, by neighboring floors, and by a single building; unlike Single-Output Gaussian Process (SOGP), MOGP can take into account the correlation among RSSI observations from multiple Access Points (APs) deployed closely to each other (e.g., APs on the same floor of a building) by collectively handling them. The feasibility of the MOGP-based RSSI data augmentation is demonstrated through experiments based on the state-of-the-art RNN indoor localization model and the UJIIndoorLoc, i.e., the most popular publicly-available multi-building and multi-floor indoor localization database, where the RNN model trained with the UJIIndoorLoc database augmented by using the whole RSSI data of a building in fitting an MOGP model (i.e., by a single building) outperforms the other two augmentation methods as well as the RNN model trained with the original UJIIndoorLoc database, resulting in the mean three-dimensional positioning error of 8.42 m.
A learning-based modular motion planning pipeline is presented that is compliant, safe, and reactive to perturbations at task execution. A nominal motion plan, defined as a nonlinear autonomous dynamical system (DS), is learned offline from kinesthetic demonstrations using a Neural Ordinary Differential Equation (NODE) model. To ensure both stability and safety during inference, a novel approach is proposed which selects a target point at each time step for the robot to follow, using a time-varying target trajectory generated by the learned NODE. A correction term to the NODE model is computed online by solving a Quadratic Program that guarantees stability and safety using Control Lyapunov Functions and Control Barrier Functions, respectively. Our approach outperforms baseline DS learning techniques on the LASA handwriting dataset and is validated on real-robot experiments where it is shown to produce stable motions, such as wiping and stirring, while being robust to physical perturbations and safe around humans and obstacles.
Data uncertainties, such as sensor noise or occlusions, can introduce irreducible ambiguities in images, which result in varying, yet plausible, semantic hypotheses. In Machine Learning, this ambiguity is commonly referred to as aleatoric uncertainty. Latent density models can be utilized to address this problem in image segmentation. The most popular approach is the Probabilistic U-Net (PU-Net), which uses latent Normal densities to optimize the conditional data log-likelihood Evidence Lower Bound. In this work, we demonstrate that the PU- Net latent space is severely inhomogenous. As a result, the effectiveness of gradient descent is inhibited and the model becomes extremely sensitive to the localization of the latent space samples, resulting in defective predictions. To address this, we present the Sinkhorn PU-Net (SPU-Net), which uses the Sinkhorn Divergence to promote homogeneity across all latent dimensions, effectively improving gradient-descent updates and model robustness. Our results show that by applying this on public datasets of various clinical segmentation problems, the SPU-Net receives up to 11% performance gains compared against preceding latent variable models for probabilistic segmentation on the Hungarian-Matched metric. The results indicate that by encouraging a homogeneous latent space, one can significantly improve latent density modeling for medical image segmentation.
Combining computational technologies and humanities is an ongoing effort aimed at making resources such as texts, images, audio, video, and other artifacts digitally available, searchable, and analyzable. In recent years, deep neural networks (DNN) dominate the field of automatic text analysis and natural language processing (NLP), in some cases presenting a super-human performance. DNNs are the state-of-the-art machine learning algorithms solving many NLP tasks that are relevant for Digital Humanities (DH) research, such as spell checking, language detection, entity extraction, author detection, question answering, and other tasks. These supervised algorithms learn patterns from a large number of "right" and "wrong" examples and apply them to new examples. However, using DNNs for analyzing the text resources in DH research presents two main challenges: (un)availability of training data and a need for domain adaptation. This paper explores these challenges by analyzing multiple use-cases of DH studies in recent literature and their possible solutions and lays out a practical decision model for DH experts for when and how to choose the appropriate deep learning approaches for their research. Moreover, in this paper, we aim to raise awareness of the benefits of utilizing deep learning models in the DH community.
To achieve the highest perceptual quality, state-of-the-art diffusion models are optimized with objectives that look very different from the maximum likelihood and the Evidence Lower Bound (ELBO) objectives. In this work, we reveal that diffusion model objectives are actually closely related to the ELBO. Specifically, we show that all commonly used diffusion model objectives equate to a weighted integral of ELBOs over different noise levels, where the weighting depends on the specific objective used. Under the condition of monotonic weighting, the connection is even closer: the diffusion objective then equals the ELBO, combined with simple data augmentation, namely Gaussian noise perturbation. We show that this condition holds for a number of state-of-the-art diffusion models. In experiments, we explore new monotonic weightings and demonstrate their effectiveness, achieving state-of-the-art FID scores on the high-resolution ImageNet benchmark.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
Spectral clustering (SC) is a popular clustering technique to find strongly connected communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement pooling operations that aggregate nodes belonging to the same cluster. However, the eigendecomposition of the Laplacian is expensive and, since clustering results are graph-specific, pooling methods based on SC must perform a new optimization for each new sample. In this paper, we propose a graph clustering approach that addresses these limitations of SC. We formulate a continuous relaxation of the normalized minCUT problem and train a GNN to compute cluster assignments that minimize this objective. Our GNN-based implementation is differentiable, does not require to compute the spectral decomposition, and learns a clustering function that can be quickly evaluated on out-of-sample graphs. From the proposed clustering method, we design a graph pooling operator that overcomes some important limitations of state-of-the-art graph pooling techniques and achieves the best performance in several supervised and unsupervised tasks.
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191