Related papers: Social-MAE: Social Masked Autoencoder for Multi-pe…

Autoencoders have emerged as powerful models for visualization and dimensionality reduction based on the fundamental assumption that high-dimensional data is generated from a low-dimensional manifold. A critical challenge in autoencoder…

Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the predominant approaches…

Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video…

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…

The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph autoencoders (GAEs). In…

We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online feature as extra BERT…

Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational…

The volume of unlabelled Earth observation (EO) data is huge, but many important applications lack labelled training data. However, EO data offers the unique opportunity to pair data from different modalities and sensors automatically based…

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,…

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…

Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by…

Self-supervised learning (SSL) has recently emerged as a key strategy for building foundation models in remote sensing, where the scarcity of annotated data limits the applicability of fully supervised approaches. In this work, we introduce…

Leveraging multimodal information from biosignals is vital for building a comprehensive representation of people's physical and mental states. However, multimodal biosignals often exhibit substantial distributional shifts between…

Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

Masked autoencoders (MAE) have shown tremendous potential for self-supervised learning (SSL) in vision and beyond. However, point clouds from LiDARs used in automated driving are particularly challenging for MAEs since large areas of the 3D…

Human face exhibits an inherent hierarchy in its representations (i.e., holistic facial expressions can be encoded via a set of facial action units (AUs) and their intensity). Variational (deep) auto-encoders (VAE) have shown great results…

Compared to 2D data, the scale of point cloud data in different domains available for training, is quite limited. Researchers have been trying to combine these data of different domains for masked autoencoder (MAE) pre-training to leverage…

Multi-person interactive motion generation, a critical yet under-explored domain in computer character animation, poses significant challenges such as intricate modeling of inter-human interactions beyond individual motions and generating…