☆ 4.7 Article

Relationship aware context adaptive deep learning for image parsing

INFORMATION SCIENCES (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

RELAXNet: Residual efficient learning and attention expected fusion network for real-time semantic segmentation

Jin Liu et al.

Summary: This paper proposes a lightweight semantic segmentation method based on attention mechanism to achieve a trade-off between segmentation accuracy and inference speed. It introduces novel modules and attention mechanism to extract information and fusion features, achieving competitive results in terms of both accuracy and speed.

NEUROCOMPUTING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

FPANet: Feature pyramid aggregation network for real-time semantic segmentation

Yun Wu et al.

Summary: This study presents the FPANet model, which uses the novel SeBiFPN and lightweight feature pyramid fusion module, and addresses border segmentation issues through BRM, achieving high-quality real-time semantic segmentation with a better balance of speed and accuracy compared to state-of-the-art methods.

APPLIED INTELLIGENCE (2022)

添加到收藏夹

Article Multidisciplinary Sciences

A union of deep learning and swarm-based optimization for 3D human action recognition

Hritam Basak et al.

Summary: This paper proposes a human action recognition model DSwarm-Net based on 3D skeleton data. By encoding skeleton data into images and using deep learning and metaheuristic methods for feature extraction and optimization, competitive results are achieved on multiple HAR datasets.

SCIENTIFIC REPORTS (2022)

添加到收藏夹

Article Automation & Control Systems

Lightweight Convolutional Neural Network Model for Human Face Detection in Risk Situations

Michal Wieczorek et al.

Summary: This article proposes a face detection model in risk situations to aid rescue teams, utilizing a lightweight CNN to accurately detect faces in various circumstances. The model is designed for simplicity and mobile device compatibility.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Lookahead adversarial learning for near real-time semantic segmentation

Hadi Jamali-Rad et al.

Summary: The study integrates a state-of-the-art segmentation model into a conditional adversarial network and introduces a novel lookahead adversarial learning method to improve semantic segmentation quality, addressing convergence and stability issues while achieving significant performance improvements on standard datasets.

COMPUTER VISION AND IMAGE UNDERSTANDING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep learning-based aerial image segmentation with open data for disaster impact assessment

Ananya Gupta et al.

Summary: Satellite images are valuable for post-natural disaster assessments, with a proposed framework using segmentation neural networks to identify affected areas and roads, utilizing pretrained ImageNet and OpenStreetMap data for training. Experimental results show that pretraining on ImageNet usually improves segmentation performance, utilizing graph theory to update road network data and detect changes caused by natural disasters.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Feature selection using Fisher score and multilabel neighborhood rough sets for multilabel classification

Lin Sun et al.

Summary: A novel feature selection method is proposed in this study using Fisher score and multilabel neighborhood rough sets to identify label correlations, automatically select neighborhood radius, and reduce complexity of multilabel data, leading to improved classification performance.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Information Systems

Hyperspectral image classification based on spatial and spectral kernels generation network

Wenping Ma et al.

Summary: This paper proposes a spatial and spectral kernels generation network (SSKNet) to tackle the classification of hyperspectral images, achieving more efficient feature extraction and fusion through the generation of spatial and spectral convolution kernels. Experimental results demonstrate that this method outperforms existing ones in terms of classification accuracy and generalization performance.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Information Systems

Feature selection based on label distribution and fuzzy mutual information

Chuanzhen Xiong et al.

Summary: This paper proposes a method that integrates label distribution learning into multi-label feature selection to mine supervised information ignored by equivalence relations in multi-label data, which achieves significant improvement over existing algorithms.

INFORMATION SCIENCES (2021)

添加到收藏夹

Review Computer Science, Information Systems

CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances

Yuzhu Ji et al.

Summary: This paper investigates the application of convolutional neural network-based encoder-decoder models in the field of salient object detection. Through extensive experimental research on encoder-decoder models with different parameters, new baseline models that can outperform state-of-the-art performance were discovered.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Information Systems

DFFNet: An IoT-perceptive dual feature fusion network for general real-time semantic segmentation

Xiangyan Tang et al.

Summary: Semantic segmentation research in IoT has been challenging, with recent trends focused on fusing multi-level features and multi-scale context information. However, existing literature faces issues of resource-consuming feature extraction and semantic gap between multi-layer features. To address these challenges, a novel IoT-perceptive Dual Feature Fusion Network (DFFNet) is proposed for effective utilization of features and context information.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Information Systems

Mirrored conditional random field model for object recognition in indoor environments

Haotian Chen et al.

Summary: This study proposed a new type of conditional random field model, called Mirror-CRF, to effectively address the issue of incomplete knowledge in object recognition caused by appearance changes. The introduction of mirror nodes allows the model to consider relationships between objects during training and testing, thereby improving the stability and accuracy of the model.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Information Systems

Scene Semantic Recognition Based on Modified Fuzzy C-Mean and Maximum Entropy Using Object-to-Object Relations

Ahmad Jalal et al.

Summary: The study introduces a novel scene semantic recognition framework, which intelligently segments object locations, generates a novel Bag of Features, and utilizes Maximum Entropy for scene recognition. During experiments, the system demonstrated high accuracy rates on various datasets and shows promising applications in different fields.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Bag of contour fragments for improvement of object segmentation

Qian Yu et al.

APPLIED INTELLIGENCE (2020)

添加到收藏夹

Article Computer Science, Information Systems

Multi-modal medical image segmentation based on vector-valued active contour models

Lingling Fang et al.

INFORMATION SCIENCES (2020)

添加到收藏夹

Article Computer Science, Information Systems

A novel framework for semantic segmentation with generative adversarial network

Xiaobin Zhu et al.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Liang-Chieh Chen et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Structured Learning of Tree Potentials in CRF for Image Segmentation

Fayao Liu et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CRF learning with CNN features for image segmentation

Fayao Liu et al.

PATTERN RECOGNITION (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Associative Hierarchical Random Fields

L'ubor Ladicky et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Learning Hierarchical Features for Scene Labeling

Clement Farabet et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2013)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

Radhakrishna Achanta et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2012)

添加到收藏夹

Article Computer Science, Artificial Intelligence

An Efficient Approach to Semantic Segmentation

Gabriela Csurka et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Semantic object classes in video: A high-definition ground truth database

Gabriel J. Brostow et al.

PATTERN RECOGNITION LETTERS (2009)

添加到收藏夹

Article Computer Science, Artificial Intelligence

TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

Jamie Shotton et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2009)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Multi-class segmentation with relative location prior

Stephen Gould et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2008)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.