-
Chapter and Conference Paper
An Investigation of CNN-CARU for Image Captioning
The goal of an image description is to extract essential information and a description of the content of a media feature from an image. This description can be obtained directly from a human-understandable des...
-
Article
SMigraPH: a perceptually retained method for passive haptics-based migration of MR indoor scenes
To enhance users’ immersion in the mixed reality (MR) cross-scene environment, it is imperative to make geometric modifications to arbitrary multi-scale virtual scenes, including adjustments to layout and size...
-
Article
Real-scene-constrained virtual scene layout synthesis for mixed reality
Given a real source scene and a virtual target scene, the real-scene-constrained virtual scene layout synthesis problem is defined as how to re-synthesize the layout of the virtual furniture in the virtual sce...
-
Article
Open AccessSpeech emotion recognition based on Graph-LSTM neural network
Currently, Graph Neural Networks have been extended to the field of speech signal processing. It is the more compact and flexible way to represent speech sequences by graphs. However, the structures of the rel...
-
Chapter
Automatic Speech Recognition for Portuguese with Small Data Set
Voice recognition has become more and more popular in various systems and applications. To further promote Macau tourism worldwide, a mobile Macau tourism APP is being develo** that supports voice control to...
-
Article
Multiple classifier for concatenate-designed neural network
This article introduces a multiple classifier method to improve the performance of concatenate-designed neural networks, such as ResNet and DenseNet, with the purpose of alleviating the pressure on the final c...
-
Chapter and Conference Paper
Robust Pedestrian Detection: Faster Deployments with Fusion of Models
Pedestrian detection has a wide range of real-world critical applications including security and management of emergency scenarios. In critical applications, detection recall and precision are both essential ...
-
Chapter and Conference Paper
CARU: A Content-Adaptive Recurrent Unit for the Transition of Hidden State in NLP
This article introduces a novel RNN unit inspired by GRU, namely the Content-Adaptive Recurrent Unit (CARU). The design of CARU contains all the features of GRU but requires fewer training parameters. We make ...
-
Chapter and Conference Paper
Variable-Depth Convolutional Neural Network for Text Classification
This article introduces a recurrent CNN based framework for the classification of arbitrary length text in natural sentence. In our model, we present a complete CNN design with recurrent structure to capture t...
-
Chapter and Conference Paper
Fast Grid-Based Fluid Dynamics Simulation with Conservation of Momentum and Kinetic Energy on GPU
Since the computation of fluid animation is often too heavy to run in real-time simulation, we propose a fast grid-based method with parallel acceleration. In order to reduce the cost of computation kee** a ...
-
Article
Improved rate-distortion optimized video coding using non-integer bit estimation and multiple Lambda search
Many modern video encoders use the Lagrangian rate-distortion optimization (RDO) algorithm for mode decisions during the compression procedure. For each encoding stage, this approach involves minimizing a cost...