Related papers: Self-supervised Video Representation Learning with…

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,…

Masked Autoencoders (MAE) play a pivotal role in learning potent representations, delivering outstanding results across various 3D perception tasks essential for autonomous driving. In real-world driving scenarios, it's commonplace to…

Motions are reflected in videos as the movement of pixels, and actions are essentially patterns of inconsistent motions between the foreground and the background. To well distinguish the actions, especially those with complicated…

Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for 3D mesh data analysis based…

Self-supervised learning (SSL) techniques have recently produced outstanding results in learning visual representations from unlabeled videos. Despite the importance of motion in supervised learning techniques for action recognition, SSL…

Many recent inpainting works have achieved impressive results by leveraging Deep Neural Networks (DNNs) to model various prior information for image restoration. Unfortunately, the performance of these methods is largely limited by the…

We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks…

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…

We approached the goal of applying meta-learning to self-supervised masked autoencoders for spatiotemporal learning in three steps. Broadly, we seek to understand the impact of applying meta-learning to existing state-of-the-art…

The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows better generalization capability than fully supervised training…

Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends…

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…

Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D…

Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for both 2D and 3D computer vision. Nevertheless, existing MAE-based methods still have certain drawbacks. Firstly, the functional decoupling…

Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have…

We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks. The learning of the representations is…

We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a…

Large-scale self-supervised pre-training Transformer architecture have significantly boosted the performance for various tasks in natural language processing (NLP) and computer vision (CV). However, there is a lack of researches on…

Current Facial Action Unit (FAU) detection methods generally encounter difficulties due to the scarcity of labeled video training data and the limited number of training face IDs, which renders the trained feature extractor insufficient…

Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed…