Related papers: HaloAE: An HaloNet based Local Transformer Auto-En…

Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data…

Auto-encoder is an important architecture to understand point clouds in an encoding and decoding procedure of self reconstruction. Current auto-encoder mainly focuses on the learning of global structure by global shape reconstruction, while…

Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Nevertheless, vision transformers treat an image as 1D sequence…

While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution…

We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. The novelty of the proposed model is threefold. First, we introduce an approach to weight tokens based…

As a substantial amount of multivariate time series data is being produced by the complex systems in Smart Manufacturing, improved anomaly detection frameworks are needed to reduce the operational risks and the monitoring burden placed on…

Human-object interaction (HOI) detection is essential for accurately localizing and characterizing interactions between humans and objects, providing a comprehensive understanding of complex visual scenes across various domains. However,…

Anomalies in the domain of autonomous driving are a major hindrance to the large-scale deployment of autonomous vehicles. In this work, we focus on high-resolution camera data from urban scenes that include anomalies of various types and…

The human-object interaction (HOI) detection task refers to localizing humans, localizing objects, and predicting the interactions between each human-object pair. HOI is considered one of the fundamental steps in truly understanding complex…

Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. However, it still remains an open question on how to exploit masked autoencoding for learning 3D representations…

Tabular data remains a challenging domain for generative models. In particular, the standard Variational Autoencoder (VAE) architecture, typically composed of multilayer perceptrons, struggles to model relationships between features,…

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…

Networks are ubiquitous in the real world such as social networks and communication networks, and anomaly detection on networks aims at finding nodes whose structural or attributed patterns deviate significantly from the majority of…

Unsupervised learning has been widely applied to various tasks in particle physics. However, existing models lack precise control over their learned representations, limiting physical interpretability and hindering their use for accurate…

Transformers have achieved remarkable success in medical image analysis owing to their powerful capability to use flexible self-attention mechanism. However, due to lacking intrinsic inductive bias in modeling visual structural information,…

The goal of anomaly detection is to identify examples that deviate from normal or expected behavior. We tackle this problem for images. We consider a two-phase approach. First, using normal examples, a convolutional autoencoder (CAE) is…

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…

Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field is essential for…

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a…

This paper aims to conduct a comparative analysis of contemporary Variational Autoencoder (VAE) architectures employed in anomaly detection, elucidating their performance and behavioral characteristics within this specific task. The…