Related papers: SkeletonMAE: Spatial-Temporal Masked Autoencoders …
In this paper, we address self-supervised representation learning from human skeletons for action recognition. Previous methods, which usually learn feature presentations from a single reconstruction task, may come across the overfitting…
Self-supervised learning guided by masked image modelling, such as Masked AutoEncoder (MAE), has attracted wide attention for pretraining vision transformers in remote sensing. However, MAE tends to excessively focus on pixel details,…
Strong gravitational lensing can reveal the influence of dark-matter substructure in galaxies, but analyzing these effects from noisy, low-resolution images poses a significant challenge. In this work, we propose a masked autoencoder (MAE)…
Wearable sensors provide abundant physiological time series, yet the principles governing their predictive utility remain unclear. We hypothesize that temporal resolution is a fundamental axis of representation learning, with different…
Action recognition via 3D skeleton data is an emerging important topic in these years. Most existing methods either extract hand-crafted descriptors or learn action representations by supervised learning paradigms that require massive…
We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these…
The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various…
Electrocardiograms (ECG) are widely employed as a diagnostic tool for monitoring electrical signals originating from a heart. Recent machine learning research efforts have focused on the application of screening various diseases using ECG…
Redshift prediction is a fundamental task in astronomy, essential for understanding the expansion of the universe and determining the distances of astronomical objects. Accurate redshift prediction plays a crucial role in advancing our…
Human social behaviors are inherently multimodal necessitating the development of powerful audiovisual models for their perception. In this paper, we present Social-MAE, our pre-trained audiovisual Masked Autoencoder based on an extended…
Masked Autoencoders (MAEs) have emerged as a dominant strategy for self-supervised representation learning in natural images, where models are pre-trained to reconstruct masked patches with a pixel-wise mean squared error (MSE) between…
Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the…
Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data…
We propose Denoising Masked Autoencoder (Deno-MAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of masked autoencoders by incorporating multiple input modalities,…
Masked Image Modeling has been one of the most popular self-supervised learning paradigms to learn representations from large-scale, unlabeled Earth Observation images. While incorporating multi-modal and multi-temporal Earth Observation…
An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn…
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,…
3D skeleton-based action recognition (3D SAR) has gained significant attention within the computer vision community, owing to the inherent advantages offered by skeleton data. As a result, a plethora of impressive works, including those…
In this report, we introduce a novel self-supervised learning method for extracting latent embeddings from behaviors of larval zebrafish. Drawing inspiration from Masked Modeling techniquesutilized in image processing with Masked…
Person re-identification via 3D skeletons is an emerging topic with great potential in security-critical applications. Existing methods typically learn body and motion features from the body-joint trajectory, whereas they lack a systematic…