164 Result(s)
within
English
Computer Science
Artificial Intelligence
Image Processing and Computer Vision
**ao-**g **a
Conference Paper
-
Chapter and Conference Paper
Analysis of Human Factor in Air Traffic Control Unsafe Events Based on Improved DECIDE Model
In order to deeply analyze the human factors of air traffic control unsafe events, air traffic control unsafe event information collected by the Civil Aviation Administration of China in 2018 is used as the s...
-
Chapter and Conference Paper
Applying Holo360 Video and Image Super-Resolution Generative Adversarial Networks to Virtual Reality Immersion
Super-resolution deep learning methods focus on image processing solutions and discussions in two-dimensional super-resolution image processing NOT for 360 equirectangular images. Therefore, the motivation of ...
-
Chapter and Conference Paper
A JIT Compiler for Neural Network Inference
This paper describes a C++ library that compiles neural network models at runtime into machine code that performs inference. This approach in general promises to achieve the best performance possible since it...
-
Chapter and Conference Paper
Research on the Key Techniques of Semantic Mining of Information Digest in the Field of Agricultural Major Crops Based on Deep Learning
Nowadays application scopes of deep learning research in the machine learning subfield have been gradually expanded, mainly in the field of computer vision and natural language processing. However, in the latt...
-
Chapter and Conference Paper
Development and Usability Evaluation of a Prototype Conversational Interface for Biological Information Retrieval via Bioinformatics
Bioinformatics is an interdisciplinary area strongly driven by the advancement of technology and data generation. It applies concepts and methodologies derived from computer science, engineering, and statistic...
-
Chapter and Conference Paper
B-Human 2019 – Complex Team Play Under Natural Lighting Conditions
In the RoboCup Standard Platform League 2019, the team B-Human won the main competition and, together with Berlin United - Nao-Team Humboldt, the Mixed Team Competition. For being successful in such a competi...
-
Chapter and Conference Paper
ToBI - Team of Bielefeld Enhancing the Robot Capabilities of the Social Standard Platform Pepper
In this paper, we describe the joint effort of the Team of Bielefeld (ToBI) winning the RoboCup@Home Social Standard Platform League (@Home SSPL) at the world cup in Montreal 2018. The @Home competition consis...
-
Chapter and Conference Paper
Optimized Rigid Motion Correction from Multiple Non-simultaneous X-Ray Angiographic Projections
X-ray angiography is the most commonly used medical imaging modality for the high resolution visualization of lumen structure in coronary arteries. Since the interpretation of 3D vascular geometry using multip...
-
Chapter and Conference Paper
Optimization Heuristics for Computing the Voronoi Skeleton
A skeletal representation of geometrical objects is widely used in computer graphics, computer vision, image processing, and pattern recognition. Therefore, efficient algorithms for computing planar skeletons...
-
Chapter and Conference Paper
Exploration of Ideal Interaction Scheme on Smart TV: Based on User Experience Research of Far-Field Speech and Mid-air Gesture Interaction
TV, as an important entertainment appliance in family, its interaction is typical of other screen-equipped devices. Far-field speech and mid-air gesture are the new trends in smart TV interaction. Previous st...
-
Chapter and Conference Paper
On the Optimization of Advanced DCF-Trackers
Trackers based on discriminative correlation filters (DCF) have recently seen widespread success and in this work we dive into their numerical core. DCF-based trackers interleave learning of the target detecto...
-
Chapter and Conference Paper
Concept Factorization with Optimal Graph Learning for Data Representation
In recent years, concept factorization methods become a popular data representation technique in many real applications. However, conventional concept factorization methods cannot capture the intrinsic geometr...
-
Chapter and Conference Paper
Human Action Recognition Based on Temporal Pose CNN and Multi-dimensional Fusion
To take advantage of recent advances in human pose estimation from images, we develop a deep neural network model for action recognition from videos by computing temporal human pose features with a 3D CNN mode...
-
Chapter and Conference Paper
Salient Points Driven Pedestrian Group Retrieval
Groups are the primary constituent units of crowd and the study on groups can help us better understand the collective phenomena in public area. In this paper, collection of stable individuals with some social...
-
Chapter and Conference Paper
MSDNet for Medical Image Fusion
Considering the DenseFuse only works in a single scale, we propose a multi-scale DenseNet (MSDNet) for medical image fusion. The main architecture of network is constructed by encoding network, fusion layer an...
-
Chapter and Conference Paper
Online Handwritten Diagram Recognition with Graph Attention Networks
Handwritten text recognition has been extensively researched over decades and achieved extraordinary success in recent years. However, handwritten diagram recognition is still a challenging task because of the...
-
Chapter and Conference Paper
Compression of Deep Convolutional Neural Networks Using Effective Channel Pruning
Pruning is a promising technology for convolutional neural networks (CNNs) to address the problems of high computational complexity and high memory requirement. However, there is a principal challenge in chann...
-
Chapter and Conference Paper
Research on Knowledge Discovery in Database of Traffic Flow State Based on Attribute Reduction
Recognizing and diagnosing the state of traffic flow is an important research area, which is the basis of improving the level of traffic management and the quality of traffic information services. However, due...
-
Chapter and Conference Paper
Non-negative Representation Based Discriminative Dictionary Learning for Face Recognition
In this paper, we propose a non-negative representation based discriminative dictionary learning algorithm (NRDL) for multicategory face classification. In contrast to traditional dictionary learning methods, ...
-
Chapter and Conference Paper
A Novel Partition Method for Busy Urban Area Based on Spatial-Temporal Information
Finding the regions where people appear plays a key role in many fields like user behavior analysis, urban planning, etc. Therefore, how to partition the world, especially the urban areas where people are crow...
