Related papers: Frequency-Aware Masked Autoencoders for Multimodal…
Learning a robust Variational Autoencoder (VAE) is a fundamental step for many deep learning applications in medical image analysis, such as MRI synthesizes. Existing brain VAEs predominantly focus on single-modality data (i.e., T1-weighted…
Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines. Prior efforts in this field mainly fall into supervised learning paradigm, which is severely restricted by the limited…
Biological signals, such as electroencephalograms (EEG), play a crucial role in numerous clinical applications, exhibiting diverse data formats and quality profiles. Current deep learning models for biosignals are typically specialized for…
Broadcast and media organizations increasingly rely on artificial intelligence to automate the labor-intensive processes of content indexing, tagging, and metadata generation. However, existing AI systems typically operate on a single…
Biological signals, such as electroencephalograms (EEGs) and electrocardiograms (ECGs), play a pivotal role in numerous clinical practices, such as diagnosing brain and cardiac arrhythmic diseases. Existing methods for biosignal…
Masked Autoencoders (MAEs) learn rich semantic representations in audio classification through an efficient self-supervised reconstruction task. However, general-purpose models fail to generalize well when applied directly to fine-grained…
Objective: fMRI and derived measures such as functional connectivity (FC) have been used to predict brain age, general fluid intelligence, psychiatric disease status, and preclinical neurodegenerative disease. However, it is not always…
Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, it is not uncommon that some FL participants…
Masked autoencoders (MAEs) have recently shown promise for self-supervised representation learning of resting-state brain functional connectivity (FC). However, a fundamental question remains unresolved: how should FC matrices be tokenized…
Multimodal pretraining is effective for building general-purpose representations, but in many practical deployments, only one modality is heavily used during downstream fine-tuning. Standard pretraining strategies treat all modalities…
Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based…
While model architectures and training strategies have become more generic and flexible with respect to different data modalities over the past years, a persistent limitation lies in the assumption of fixed quantities and arrangements of…
There has been a longstanding belief that generation can facilitate a true understanding of visual data. In line with this, we revisit generatively pre-training visual representations in light of recent interest in denoising diffusion…
In this paper, we address the problem of multimodal emotion recognition from multiple physiological signals. We demonstrate that a Transformer-based approach is suitable for this task. In addition, we present how such models may be…
Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different…
How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…
Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…
Self-supervised learning through masked autoencoders has attracted great attention for remote sensing (RS) foundation model (FM) development, enabling improved representation learning across diverse sensors and downstream tasks. However,…
Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or…
Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT,…