-
Hollywood2Tubes
Hollywood2Tubes dataset contains 1,707 videos from 10 action categories. -
METTES, SNOEK, CHANG: ACTION LOCALIZATION WITH PSEUDO-ANNOTATIONS
The goal of this paper is to determine the spatio-temporal location of actions in video. Where training from hard to obtain box annotations is the norm, we propose an intuitive... -
Domain Adaptation
The dataset used in this paper for unsupervised domain adaptation. -
Unsupervised Video Encoding Task
The dataset used in the paper is a unsupervised video encoding task. -
Fabric Defect Detection Dataset
A dataset for automatic unsupervised fabric defect detection based on self-feature comparison. -
Custom Carpet Dataset
A custom dataset of four unique types of carpet textures was created to thoroughly test state-of-the-art unsupervised detection models. -
Improving Unsupervised Domain Adaptation with Mixup Training
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. -
Synthia→Cityscapes
The Synthia→Cityscapes task is a domain adaptation task for semantic segmentation, where the source domain is Synthia and the target domain is Cityscapes. -
Anomaly Detection
The dataset is used for anomaly detection in various fields. -
Robust unsupervised anomaly detection via multi-time scale dcgans with forget...
The dataset used in this paper for log parsing evaluation -
Identification of Anomalous Diffusion Sources by Unsupervised Learning
Fractional Brownian motion (fBm) is a ubiquitous diffusion process in which the memory effects of the stochastic transport result in the mean squared particle displacement... -
Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with ...
The dataset used in the paper is a large-scale dataset for unsupervised learning on diffusion-generated images. -
SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight
Wearable Human Activity Recognition (WHAR) models usually face performance degradation on the new user due to user variance. Unsupervised domain adaptation (UDA) becomes the... -
An Unsupervised Adversarial Autoencoder for Cyber Attack Detection in Power D...
The proposed AAE learning-based approach employs LSTM in the architecture of the autoencoder for capturing the temporal correlation of the grid measurements to reconstruct the... -
Scaffold-A549
The dataset used for unsupervised cell nuclei segmentation in this paper.
