386 Result(s)
-
Chapter and Conference Paper
Integrating Human Parsing and Pose Network for Human Action Recognition
Human skeletons and RGB sequences are both widely-adopted input modalities for human action recognition. However, skeletons lack appearance features and color data suffer large amount of irrelevant depiction. ...
-
Chapter and Conference Paper
An Analysis of the Generalized Tit-for-Tat Strategy Within the Framework of Memory-One Strategies
The Tit-for-tat strategy is a traditional strategy in game theory. In the Prisoner’s Dilemma, the TFT strategy has been proven to be strong. However, within a four-component Memory-One strategy framework, the ...
-
Chapter and Conference Paper
Deformable CNN with Position Encoding for Arbitrary-Scale Super-Resolution
Implicit neural representation (INR) has been widely used to learn continuous representation of images, as it enables arbitrary-scale super-resolution (SR). However, most existing INR-based arbitrary-scale SR ...
-
Chapter and Conference Paper
Improving Knowledge Graph Embedding Using Dynamic Aggregation of Neighbor Information
Knowledge graph embedding represents the embedding of entities and relations in the knowledge graph into a low-dimensional vector space to accomplish the knowledge graph complementation task. Most existing kno...
-
Chapter and Conference Paper
GAN-Based Image Compression with Improved RDO Process
GAN-based image compression schemes have shown remarkable progress lately due to their high perceptual quality at low bit rates. However, there are two main issues, including 1) the reconstructed image percept...
-
Chapter and Conference Paper
Dual Fusion Network for Hyperspectral Semantic Segmentation
With the development of imaging technology, it becomes increasingly easy to obtain hyperspectral images (HSI) containing rich spectral information. The application of hyperspectral images in autonomous driving...
-
Chapter and Conference Paper
Data Representation and Clustering with Double Low-Rank Constraints
High-dimensional data are usually drawn from an union of multiple low-dimensional subspaces. Low-rank representation (LRR), as a multi-subspace structure learning method, uses low rank constraints to extract t...
-
Chapter and Conference Paper
Graph Convolutional Neural Network Based on Channel Graph Fusion for EEG Emotion Recognition
To represent the unstructured relationships among EEG channels, graph neural networks are proposed to classify EEG signal. Currently most graph neural networks learn the relationships between EEG channels usin...
-
Chapter and Conference Paper
A Novel Homogenized Chaotic System of Compressed Sensing Image Encryption Algorithm
Aimed at the problems of limited range, uneven distribution, and insufficient complexity of traditional one-dimensional chaotic map**. In this paper, a method for constructing chaotic measurement matrices is...
-
Chapter and Conference Paper
Lightweight Image Compression Based on Deep Learning
Deep learning based image compression (DLIC) algorithms have achieved higher compression gain than conventional algorithms. However, the large parameters and float-point operations (FLOPs) of DLIC severely lim...
-
Chapter and Conference Paper
A Novel Device-Free Localization Approach Based on Deep Dictionary Learning
As an emerging technology, device-free localization (DFL) has a wide range of application scenarios in the field of the internet of things. However, most of the existing DFL methods take the mode of learning f...
-
Chapter and Conference Paper
A Multi-branch Cascade Transformer Network (MBCT–Net) for Hand Gesture Segmentation in Cluttered Background
Hand gesture segmentation is an initial and essential step to classify hand gestures, which provides a simple, intuitive, concise and natural way for human–computer interaction, human–robot interaction. Howeve...
-
Chapter and Conference Paper
Evolutionary Multitasking for Coarse-to-Fine Point Cloud Registration with Chaotic Opposition Search Strategy
Point cloud registration is a challenging task in both computer vision and pattern recognition. In general, the success of well-known registration algorithms depends heavily on the assumption of an initial nea...
-
Chapter and Conference Paper
Incomplete Cigarette Code Recognition via Unified SPA Features and Graph Space Constraints
Cigarette code is a 32-character string printed on a cigarette package, which can be used by tobacco administrations to determine the legality of distribution. Unfortunately, the recognition task for incomplet...
-
Chapter and Conference Paper
Molecular Activity Prediction Based on Graph Attention Network
Spatial convolutional models of Graph Neural Networks (GNNs) updates embeddings of nodes by the neighborhood aggregation, it has obvious advantages in reducing time complexity and improving accuracy. Therefore...
-
Chapter and Conference Paper
Spatial-Temporal Contextual Feature Fusion Network for Movie Description
The movie description task aims to generate narrative textual descriptions that match the content of the movie. Most of the current methods lack the ability to consider comprehensive visual content analysis an...
-
Chapter and Conference Paper
Planar Motion Estimation for Multi-camera System
In this paper, we propose efficient solutions to relative pose estimation with a multi-camera system. We focus on the case where the system navigates under planar motion, and propose two new algorithms: the no...
-
Chapter and Conference Paper
The Computer Measurement Method Research on Shaft’s Size by the Platform of the Optoelectronic Imaging
The measurement of shaft’s size by computer is the significant basis of the automatic industrial measurement and detection, this paper establishes the optoelectronic imaging instrument of the shaft, and the im...
-
Chapter and Conference Paper
A Transformer-Based Model for Low-Resource Event Detection
Event detection is an important task in natural language processing, which identifies event trigger words in a given sentence. Previous work use traditional RNN/CNN based text encoders, failing to remember lon...
-
Chapter and Conference Paper
Generic Image Segmentation in Fully Convolutional Networks by Superpixel Merging Map
Recently, the Fully Convolutional Network (FCN) has been adopted in image segmentation. However, existing FCN-based segmentation algorithms were designed for semantic segmentation. Before learning-based algori...