相关论文: Peransformer: Improving Low-informed Expressive Pe…

Event cameras are sensors of great interest for many applications that run in low-resource and challenging environments. They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal…

One of the most significant challenges in Music Emotion Recognition (MER) comes from the fact that emotion labels can be heterogeneous across datasets with regard to the emotion representation, including categorical (e.g., happy, sad)…

The majority of recent progress in Optical Music Recognition (OMR) has been achieved with Deep Learning methods, especially models following the end-to-end paradigm, reading input images and producing a linear sequence of tokens.…

The distortion-perception (DP) tradeoff reveals a fundamental conflict between distortion metrics (e.g., MSE and PSNR) and perceptual quality. Recent research has increasingly concentrated on evaluating denoising algorithms within the DP…

While subgroup disparities and performance bias are increasingly studied in computational research, fairness in categorical Speech Emotion Recognition (SER) remains underexplored. Existing methods often rely on explicit demographic labels,…

Music can be represented in multiple forms, such as in the audio form as a recording of a performance, in the symbolic form as a computer readable score, or in the image form as a scan of the sheet music. Music synchronisation provides a…

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the…

Given a text query, partially relevant video retrieval (PRVR) seeks to find untrimmed videos containing pertinent moments in a database. For PRVR, clip modeling is essential to capture the partial relationship between texts and videos.…

Micro-expression recognition plays a pivotal role in understanding hidden emotions and has applications across various fields. Traditional recognition methods assume access to all training data at once, but real-world scenarios involve…

Surface wave dispersion curve inversion is crucial for estimating subsurface shear-wave velocity (vs), yet traditional methods often face challenges related to computational cost, non-uniqueness, and sensitivity to initial models. While…

Recently proposed pyramidal models decompose the conventional forward and backward diffusion processes into multiple stages operating at varying resolutions. These models handle inputs with higher noise levels at lower resolutions, while…

Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…

Recent advances in multimodal Parameter-Efficient Fine-Tuning (PEFT) have significantly improved performance on downstream tasks such as few-shot retrieval. However, most existing approaches focus on task-specific gains while neglecting the…

Human Activity Recognition (HAR) with wearable sensors is challenged by limited interpretability, which significantly impacts cross-dataset generalization. To address this challenge, we propose Motion-Primitive Transformer (MoPFormer), a…

Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including…

The expression of emotion is highly individualistic. However, contemporary speech emotion recognition (SER) systems typically rely on population-level models that adopt a `one-size-fits-all' approach for predicting emotion. Moreover,…

The traditional Transformer model encounters challenges with variable-length input sequences, particularly in Hyperspectral Image Classification (HSIC), leading to efficiency and scalability concerns. To overcome this, we propose a…

Predicting linearized Abstract Meaning Representation (AMR) graphs using pre-trained sequence-to-sequence Transformer models has recently led to large improvements on AMR parsing benchmarks. These parsers are simple and avoid explicit…

Despite recent achievements of deep learning automatic music generation algorithms, few approaches have been proposed to evaluate whether a single-track music excerpt is composed by automatons or Homo sapiens. To tackle this problem, we…

Electronic health records (EHR) contain a wealth of biomedical information, serving as valuable resources for the development of precision medicine systems. However, privacy concerns have resulted in limited access to high-quality and…