-
Chapter and Conference Paper
\(\mathrm {D^2ADA}\) : Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation
In the field of domain adaptation, a trade-off exists between the model performance and the number of target domain annotations. Active learning, maximizing model performance with few informative labeled data,...
-
Chapter and Conference Paper
Efficient and Phase-Aware Video Super-Resolution for Cardiac MRI
Cardiac Magnetic Resonance Imaging (CMR) is widely used since it can illustrate the structure and function of the heart in a non-invasive and painless way. However, it is time-consuming and high-cost to acquir...
-
Chapter and Conference Paper
PIVTONS: Pose Invariant Virtual Try-On Shoe with Conditional Image Completion
Virtual try-on – synthesizing an almost-realistic image for dressing a target fashion item provided the source human photo – has growing needs due to the prevalence of e-commerce and the development of deep le...
-
Chapter and Conference Paper
Super-Identity Convolutional Neural Network for Face Hallucination
Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information. However, previous face hallucination approac...
-
Chapter and Conference Paper
Approximating Weighted Hamming Distance by Probabilistic Selection for Multiple Hash Tables
With the large growth of photos on the Internet, the need for large-scale, real-time image retrieval systems is emerging. Current state-of-the-art approaches in these systems leverage binary features (e.g., ha...
-
Chapter and Conference Paper
Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval
Recently, promising results have been shown on face recognition researches. However, face recognition and retrieval across age is still challenging. Unlike prior methods using complex models with strong parame...
-
Chapter and Conference Paper
Snap2Read: Automatic Magazine Capturing and Analysis for Adaptive Mobile Reading
The rise of electronic book services and the prevalence of mobile devices reveal the needs for mobile reading and the booming business opportunities in e-book developments. However, incompatible e-book readers...
-
Chapter and Conference Paper
Visual Cue Cluster Construction via Information Bottleneck Principle and Kernel Density Estimation
Recent research in video analysis has shown a promising direction, in which mid-level features (e.g., people, anchor, indoor) are abstracted from low-level features (e.g., color, texture, motion, etc.) and use...
