Related papers: Understanding Masked Autoencoders From a Local Con…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

In the realm of digital forensics and document authentication, writer identification plays a crucial role in determining the authors of documents based on handwriting styles. The primary challenge in writer-id is the "open-set scenario",…

To achieve reliable mining results for massive vessel trajectories, one of the most important challenges is how to efficiently compute the similarities between different vessel trajectories. The computation of vessel trajectory similarity…

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.…

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…

Unsupervised learning of vision transformers seeks to pretrain an encoder via pretext tasks without labels. Among them is the Masked Image Modeling (MIM) aligned with pretraining of language transformers by predicting masked patches as a…

Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoencoder (MVMAE), a self-supervised framework that leverages…

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…

In this paper, we propose a new progressive pre-training method for image understanding tasks which leverages RGB-D datasets. The method utilizes Multi-Modal Contrastive Masked Autoencoder and Denoising techniques. Our proposed approach…

Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised…

Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target…

In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain. Specifically, we evaluate the effectiveness of Masked Autoencoding as a pretraining scheme, and explore Momentum…

Deep neural networks have achieved remarkable progress in enhancing low-light images by improving their brightness and eliminating noise. However, most existing methods construct end-to-end mapping networks heuristically, neglecting the…

Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…

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…

Anomaly detection without priors of the anomalies is challenging. In the field of unsupervised anomaly detection, traditional auto-encoder (AE) tends to fail based on the assumption that by training only on normal images, the model will not…

Affective video facial analysis (AVFA) has emerged as a key research field for building emotion-aware intelligent systems, yet this field continues to suffer from limited data availability. In recent years, the self-supervised learning…

With the ever-increasing amount of data, the central challenge in multimodal learning involves limitations of labelled samples. For the task of classification, techniques such as meta-learning, zero-shot learning, and few-shot learning…

Masked image modeling (MIM) is a highly popular and effective self-supervised learning method for image understanding. Existing MIM-based methods mostly focus on spatial feature modeling, neglecting spectral feature modeling. Meanwhile,…

Neural solvers for partial differential equations (PDEs) have great potential to generate fast and accurate physics solutions, yet their practicality is currently limited by their generalizability. PDEs evolve over broad scales and exhibit…