• Publications
  • Influence
Robust Algorithm for Exemplar-based Image Inpainting
This paper presents a robust algorithm for exemplar-based image inpainting. We focus on the development of a generic priority function to provide robust performance. With user intervention, theExpand
  • 113
  • 13
  • PDF
Human action recognition and retrieval using sole depth information
TLDR
We proposed the use of simple depth descriptors without learning optimization to achieve promising performances as compatible to those of the leading color images and videos, and can be effectively applied for real-time applications. Expand
  • 59
  • 10
Joint Enhancement and Denoising Method via Sequential Decomposition
TLDR
In this paper, we introduce a joint low-light enhancement and denoising strategy, aimed at obtaining well-enhanced low- light images while getting rid of the inherent noise issue simultaneously. Expand
  • 35
  • 9
  • PDF
Computer-aided classification of lung nodules on computed tomography images via deep learning technique
TLDR
We introduced models of a deep belief network and a convolutional neural network in the context of nodule classification in computed tomography images. Expand
  • 278
  • 8
  • PDF
FingerPad: private and subtle interaction using fingertips
TLDR
We present FingerPad, a nail-mounted device that turns the tip of the index finger into a touchpad, allowing private and subtle interaction while on the move. Expand
  • 138
  • 8
  • PDF
Semantic context detection based on hierarchical audio models
TLDR
We propose a novel hierarchical approach that models the statistical characteristics of several audio events, over a time series, to accomplish semantic context detection. Expand
  • 84
  • 8
Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks
TLDR
We propose a novel prediction framework called Deep Temporal Context Networks (DTCN) by incorporating both temporal context and temporal attention into account. Expand
  • 55
  • 6
  • PDF
BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative Network
TLDR
We propose BeautyGlow to decompose the latent vectors derived from the Glow model into makeup and nonmakeup latent vectors. Expand
  • 22
  • 4
  • PDF
Real-Time Human Movement Retrieval and Assessment With Kinect Sensor
TLDR
We propose an action tutor system which enables the user to interactively retrieve a learning exemplar of the target action movement and to acquire motion instructions while learning it in front of the Kinect. Expand
  • 54
  • 3
Unfolding Temporal Dynamics: Predicting Social Media Popularity Using Multi-scale Temporal Decomposition
TLDR
We propose a novel framework based on matrix factorization called Multi-scale Temporal Decomposition (MTD), which decomposes the popularity matrix in latent spaces based on contextual associations, including user activeness variability and photo prevalence variability. Expand
  • 77
  • 3
  • PDF