Related papers: CMAE-V: Contrastive Masked Autoencoders for Video …
Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly…
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…
Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations. Moreover, they could be further used in downstream tasks such as classification. As previous work…
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. However, state-of-the-art…
Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…
Continuous dynamical systems are cornerstones of many scientific and engineering disciplines. While machine learning offers powerful tools to model these systems from trajectory data, challenges arise when these trajectories are captured as…
Recently, self-supervised Masked Autoencoders (MAE) have attracted unprecedented attention for their impressive representation learning ability. However, the pretext task, Masked Image Modeling (MIM), reconstructs the missing local patches,…
Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we…
This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…
Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus…
We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to improve the compression…
Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…
Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a…
Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the…
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially…
Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities in multi-modality settings. In this work, we focus on point…
Transformer-based architectures have become competitive across a variety of visual domains, most notably images and videos. While prior work studies these modalities in isolation, having a common architecture suggests that one can train a…
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…
Self-supervised learning through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) image representation learning, and thus embodies a significant potential for content-based image retrieval (CBIR)…
In this study, a deep learning based conditional density estimation technique known as conditional variational auto-encoder (CVAE) is used to fill gaps typically observed in particle image velocimetry (PIV) measurements in combustion…