Related papers: Applying Adversarial Auto-encoder for Estimating H…

Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building…

Sequential recommendation as an emerging topic has attracted increasing attention due to its important practical significance. Models based on deep learning and attention mechanism have achieved good performance in sequential…

This paper presents a deep learning based approach to the problem of human pose estimation. We employ generative adversarial networks as our learning paradigm in which we set up two stacked hourglass networks with the same architecture, one…

Autoencoder networks are unsupervised approaches aiming at combining generative and representational properties by learning simultaneously an encoder-generator map. Although studied extensively, the issues of whether they have the same…

Deep generative models are attracting great attention as a new promising approach for molecular design. All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN). Here we propose a…

Human activity recognition (HAR) is an important research field in ubiquitous computing where the acquisition of large-scale labeled sensor data is tedious, labor-intensive and time consuming. State-of-the-art unsupervised remedies…

Anomaly driving detection is an important problem in advanced driver assistance systems (ADAS). It is important to identify potential hazard scenarios as early as possible to avoid potential accidents. This study proposes an unsupervised…

Point cloud compression significantly reduces data volume but sacrifices reconstruction quality, highlighting the need for advanced quality enhancement techniques. Most existing approaches focus primarily on point-to-point fidelity, often…

Attitude determination using the smartphone's inertial sensors poses a major challenge due to the sensor low-performance grade and variate nature of the walking pedestrian. In this paper, data-driven techniques are employed to address that…

Motion ability is one of the most important human properties, including gait as a basis of human transitional movement. Gait, as a biometric for recognizing human identities, can be non-intrusively captured signals using wearable or…

Gait recognition i.e. identification of an individual from his/her walking pattern is an emerging field. While existing gait recognition techniques perform satisfactorily in normal walking conditions, there performance tend to suffer…

We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE). We guarantee the stable training of the generator by preventing the faster convergence of the…

Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mode collapse. In this…

Through-wall radars are researched and developed for the detection, localization, and tracking of human activities in indoor environments. Electromagnetic wave propagation through walls introduces refraction, attenuation, multipath, and…

We propose a novel filter for sparse big data, called an integrated autoencoder (IAE), which utilizes auxiliary information to mitigate data sparsity. The proposed model achieves an appropriate balance between prediction accuracy,…

Gesture-based authentication has emerged as a non-intrusive, effective means of authenticating users on mobile devices. Typically, such authentication techniques have relied on classical machine learning techniques, but recently, deep…

Generative Adversarial Networks (GANs) have shown great success in many applications. In this work, we present a novel method that leverages human annotations to improve the quality of generated images. Unlike previous paradigms that…

Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton…

Autoencoders (AE) have recently been widely employed to approach the novelty detection problem. Trained only on the normal data, the AE is expected to reconstruct the normal data effectively while fail to regenerate the anomalous data,…

Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes. In this paper, we demonstrate that adversarial examples can also be utilized for good to improve the…