Related papers: Pay (Cross) Attention to the Melody: Curriculum Ma…

We present Mirable's submission to the 2021 Emotions and Themes in Music challenge. In this work, we intend to address the question: can we leverage semi-supervised learning techniques on music emotion recognition? With that, we experiment…

Melody harmonization, which involves generating a chord progression that complements a user-provided melody, continues to pose a significant challenge. A chord progression must not only be in harmony with the melody, but also interdependent…

Recent years have witnessed the success of deep learning on the visual sound separation task. However, existing works follow similar settings where the training and testing datasets share the same musical instrument categories, which to…

Federated learning (FL) has emerged as a powerful approach to safeguard data privacy by training models across distributed edge devices without centralizing local data. Despite advancements in homogeneous data scenarios, maintaining…

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled…

Recent unified multi-modal encoders align a wide range of modalities into a shared representation space, enabling diverse cross-modal tasks. Despite their impressive capabilities, the robustness of these models under adversarial…

Federated learning is generally used in tasks where labels are readily available (e.g., next word prediction). Relaxing this constraint requires design of unsupervised learning techniques that can support desirable properties for federated…

This work presents novel methods to reduce computational and memory requirements for medical image segmentation with a large number of classes. We curiously observe challenges in maintaining state-of-the-art segmentation performance with…

Code language models have emerged as useful tools for various programming tasks, yet they often struggle when it comes to complex ones. In this paper, we explore the potential of curriculum learning in enhancing the performance of these…

Multi-pitch estimation is a decades-long research problem involving the detection of pitch activity associated with concurrent musical events within multi-instrument mixtures. Supervised learning techniques have demonstrated solid…

This paper explores sequential modelling of polyphonic music with deep neural networks. While recent breakthroughs have focussed on network architecture, we demonstrate that the representation of the sequence can make an equally significant…

Incremental learning aims to enable models to continuously acquire knowledge from evolving data streams while preserving previously learned capabilities. While current research predominantly focuses on unimodal incremental learning and…

Semi-supervised learning is of great significance in medical image segmentation by exploiting unlabeled data. Among its strategies, the co-training framework is prominent. However, previous co-training studies predominantly concentrate on…

Real-world applications of machine learning models often confront data distribution shifts, wherein discrepancies exist between the training and test data distributions. In the common multi-domain multi-class setup, as the number of classes…

Multi-frame depth estimation generally achieves high accuracy relying on the multi-view geometric consistency. When applied in dynamic scenes, e.g., autonomous driving, this consistency is usually violated in the dynamic areas, leading to…

Melody extraction in polyphonic musical audio is important for music signal processing. In this paper, we propose a novel streamlined encoder/decoder network that is designed for the task. We make two technical contributions. First, drawing…

We introduce a film score generation framework to harmonize visual pixels and music melodies utilizing a latent diffusion model. Our framework processes film clips as input and generates music that aligns with a general theme while offering…

Painterly image harmonization aims at seamlessly blending disparate visual elements within a single image. However, previous approaches often struggle due to limitations in training data or reliance on additional prompts, leading to…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…