Graph-Boosted Attentive Network for Semantic Body Parsing

Wang, Tinghuai; Wang, Huiling

doi:10.1007/978-3-030-30508-6_22

Cited by 5 publications

(4 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graphical models and graph neural networks (GNNs) have emerged as powerful tools in the field of computer vision [54,42,28,44,63,75,60,45,69], offering a versatile framework for representing and processing complex visual data. These approaches leverage the inherent structure and relationships within images [61,59,41,56,66,10] and videos [50,48,43,5], allowing for more nuanced and context-aware analysis.…”

Section: Related Workmentioning

confidence: 99%

Holistically-Nested Structure-Aware Graph Neural Network for Road Extraction

Wang¹,

Wang²,

Tan³

2021

Advances in Visual Computing

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have made significant advances in detecting roads from satellite images. However, existing CNN approaches are generally repurposed semantic segmentation architectures and suffer from the poor delineation of long and curved regions. Lack of overall road topology and structure information further deteriorates their performance on challenging remote sensing images. This paper presents a novel multi-task graph neural network (GNN) which simultaneously detects both road regions and road borders; the inter-play between these two tasks unlocks superior performance from two perspectives: (1) the hierarchically detected road borders enable the network to capture and encode holistic road structure to enhance road connectivity (2) identifying the intrinsic correlation of semantic landcover regions mitigates the difficulty in recognizing roads cluttered by regions with similar appearance. Experiments on challenging dataset demonstrate that the proposed architecture can improve the road border delineation and road extraction accuracy compared with the existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Holistically-Nested Structure-Aware Graph Neural Network for Road Extraction

Wang¹,

Wang²,

Tan³

2021

Advances in Visual Computing

View full text Add to dashboard Cite

show abstract

“…Graphical models and graph neural networks (GNNs) have emerged as powerful tools in the field of computer vision [49,51,38,48,27,40,57,64,65,54,41,59], offering a versatile framework for representing and processing complex visual data. These approaches leverage the inherent structure and relationships within images [55,53,37,50,58,11] and videos [45,43,2], allowing for more nuanced and context-aware analysis.…”

Section: Introductionmentioning

confidence: 99%

Spectral Graph Reasoning Network for Hyperspectral Image Classification

Wang

2020

Artificial Neural Networks and Machine Learning – ICANN 2020

View full text Add to dashboard Cite

In this paper, we propose a spectral-spatial graph reasoning network (SSGRN) for hyperspectral image (HSI) classification. Concretely, this network contains two parts that separately named spatial graph reasoning subnetwork (SAGRN) and spectral graph reasoning subnetwork (SEGRN) to capture the spatial and spectral graph contexts, respectively. Different from the previous approaches implementing superpixel segmentation on the original image or attempting to obtain the category features under the guide of label image, we perform the superpixel segmentation on intermediate features of the network to adaptively produce the homogeneous regions to get the effective descriptors. Then, we adopt a similar idea in spectral part that reasonably aggregating the channels to generate spectral descriptors for spectral graph contexts capturing. All graph reasoning procedures in SAGRN and SEGRN are achieved through graph convolution. To guarantee the global perception ability of the proposed methods, all adjacent matrices in graph reasoning are obtained with the help of non-local self-attention mechanism. At last, by combining the extracted spatial and spectral graph contexts, we obtain the SSGRN to achieve a high accuracy classification. Extensive quantitative and qualitative experiments on three public HSI benchmarks demonstrate the competitiveness of the proposed methods compared with other state-of-the-art approaches.

show abstract

“…Graphical models have become powerful tools in computer vision [9,10,11,12,13,14], providing a versatile framework for modeling contextual relationships. These approaches exploit the inherent structure and relationships within images [15,16,17] and videos [18,19,20], facilitating more sophisticated and context-aware analysis.…”

Section: Introductionmentioning

confidence: 99%

Context Propagation from Proposals for Semantic Video Object Segmentation

Wang

2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this paper, we propose a novel approach to learning semantic contextual relationships in videos for semantic object segmentation. Our algorithm derives the semantic contexts from video object proposals which encode the key evolution of objects and the relationship among objects over the spatio-temporal domain. This semantic contexts are propagated across the video to estimate the pairwise contexts between all pairs of local superpixels which are integrated into a conditional random field in the form of pairwise potentials and infers the per-superpixel semantic labels. The experiments demonstrate that our contexts learning and propagation model effectively improves the robustness of resolving visual ambiguities in semantic video object segmentation compared with the state-of-the-art methods.

show abstract

Graph-Boosted Attentive Network for Semantic Body Parsing

Cited by 5 publications

References 66 publications

Holistically-Nested Structure-Aware Graph Neural Network for Road Extraction

Holistically-Nested Structure-Aware Graph Neural Network for Road Extraction

Spectral Graph Reasoning Network for Hyperspectral Image Classification

Context Propagation from Proposals for Semantic Video Object Segmentation

Contact Info

Product

Resources

About