-
Chapter and Conference Paper
End-to-End Streaming Customizable Keyword Spotting Based on Text-Adaptive Neural Search
Streaming keyword spotting (KWS) is an important technique for voice assistant wake-up. While KWS with a preset fixed keyword has been well studied, test-time customizable keyword spotting in streaming mode re...
-
Chapter and Conference Paper
3RE-Net: Joint Loss-REcovery and Super-REsolution Neural Network for REal-Time Video
Real-time video over the Internet suffers from packet loss and low network bandwidth. The receiving side may receive down-sampled video with damaged frames. In this work, we are motivated to enhance the qualit...
-
Chapter and Conference Paper
Preliminary Experiment for Measuring the Anxiety Level Using Heart Rate Variability
Anxiety is one of the most significant health issues. Generally, there are four levels of anxiety: mild anxiety, moderate anxiety, severe anxiety, and panic level anxiety
-
Chapter and Conference Paper
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been pro...
-
Chapter and Conference Paper
Semantic Enhancement Framework for Robust Speech Recognition
Auto speech recognition (ASR) has been widely used in dialogue systems of various domains, performing as a crucial part of technology. Since the output of the ASR system will provide input to the subsequent sy...
-
Chapter and Conference Paper
A Fast Stain Normalization Network for Cervical Papanicolaou Images
The domain shift between different styles of stain images greatly challenges the generalization of computer-aided diagnosis (CAD) algorithms. To bridge the gap, color normalization is a prerequisite for most C...
-
Chapter and Conference Paper
Single Cross-domain Semantic Guidance Network for Multimodal Unsupervised Image Translation
Multimodal image-to-image translation has received great attention due to its flexibility and practicality. The existing methods lack the generality of effective style representation, and cannot capture differ...
-
Chapter and Conference Paper
VERTEX: VEhicle Reconstruction and TEXture Estimation from a Single Image Using Deep Implicit Semantic Template Map**
We introduce VERTEX, an effective solution to recovering the 3D shape and texture of vehicles from uncalibrated monocular inputs under real-world street environments. To fully utilize the semantic prior of veh...
-
Chapter and Conference Paper
A Deep Attention Transformer Network for Pain Estimation with Facial Expression Video
Since pain often causes deformations in the facial structure, analysis of facial expressions has received considerable attention for automatic pain estimation in recent years. This study proposes a deep attent...
-
Chapter and Conference Paper
Integrating Task Information into Few-Shot Classifier by Channel Attention
It has been increasingly recognized that meta-learning-based approaches provide a promising way to handle challenges to few-shot learning. In this paper, we incorporate the channel attention in the main framew...
-
Chapter and Conference Paper
Stacked Sparse Autoencoder for Audio Object Coding
Compared with channel-based audio coding, the object-based audio coding has a definite advantage in meeting the user’s demands of personalized control. However, in the conventional Spatial Audio Object Coding ...
-
Chapter and Conference Paper
A Metagraph-Based Model for Predicting Drug-Target Interaction on Heterogeneous Network
Determining drug-target interactions (DTIs) is an important task in drug discovery and drug relocalization. Currently, different models have been proposed to predict the potential interactions between drugs an...
-
Chapter and Conference Paper
EMRM: Enhanced Multi-source Review-Based Model for Rating Prediction
Rating prediction, whose goal is to predict user preference for unconsumed items, has become one of the core tasks in recommendation systems. Recently, many deep learning-based methods have been applied to the...
-
Chapter and Conference Paper
Metric Learning for Categorical and Ambiguous Features: An Adversarial Method
Metric learning learns a distance metric from data and has significantly improved the classification accuracy of distance-based classifiers such as k-nearest neighbors. However, metric learning has rarely been ap...
-
Chapter and Conference Paper
Multi-step Coding Structure of Spatial Audio Object Coding
The spatial audio object coding (SAOC) is an effective meth-od which compresses multiple audio objects and provides flexibility for personalized rendering in interactive services. It divides each frame signal ...
-
Chapter and Conference Paper
Synthesizing Large-Scale Datasets for License Plate Detection and Recognition in the Wild
License Plate Detection and Recognition (LPDR) plays a key role in modern intelligent transportation systems. Recent state-of-the-art methods of LPDR are based on deep convolutional neural networks (DCNN), whi...
-
Chapter and Conference Paper
Imputation of Incomplete Data Based on Attribute Cross Fitting Model and Iterative Missing Value Variables
The problem of missing values is often encountered in tasks such as machine learning, and imputation of missing values has become an important research content in incomplete data analysis. In this paper, we p...
-
Chapter and Conference Paper
Perceptual Localization of Virtual Sound Source Based on Loudspeaker Triplet
When using a loudspeaker triplet for virtual sound localization, the traditional conversion method will result in inaccurate localization. In this paper, we constructed a perceptual localization distortion mod...
-
Chapter and Conference Paper
HMM-Based Person Re-identification in Large-Scale Open Scenario
This paper aims to tackle person re-identification (person re-ID) in large-scale open scenario, which differs from the conventional person re-ID tasks but is significant for some real suspect investigation ca...
-
Chapter and Conference Paper
NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image
We propose NormalGAN, a fast adversarial learning-based method to reconstruct the complete and detailed 3D human from a single RGB-D image. Given a single front-view RGB-D image, NormalGAN performs two steps: ...