Update papers.bib

_bibliography/papers.bib

@@ -143,7 +143,8 @@ @article{lee2022hierarchically
   year={2023},
   arxiv={2208.10741},
   code={https://github.com/Jho-Yonsei/HD-GCN},
-  abstract={Graph convolutional networks (GCNs) are the most commonly used methods for skeleton-based action recognition and have achieved remarkable performance. Generating adjacency matrices with semantically meaningful edges is particularly important for this task, but extracting such edges is challenging problem. To solve this, we propose a hierarchically decomposed graph convolutional network (HD-GCN) architecture with a novel hierarchically decomposed graph (HD-Graph). The proposed HD-GCN effectively decomposes every joint node into several sets to extract major structurally adjacent and distant edges, and uses them to construct an HD-Graph containing those edges in the same semantic spaces of a human skeleton. In addition, we introduce an attention-guided hierarchy aggregation (A-HA) module to highlight the dominant hierarchical edge sets of the HD-Graph. Furthermore, we apply a new six-way ensemble method, which uses only joint and bone stream without any motion stream. The proposed model is evaluated and achieves state-of-the-art performance on three large, popular datasets: NTU-RGB+D 60, NTU-RGB+D 120, and Northwestern-UCLA. Finally, we demonstrate the effectiveness of our model with various comparative experiments.}
+  abstract={Graph convolutional networks (GCNs) are the most commonly used methods for skeleton-based action recognition and have achieved remarkable performance. Generating adjacency matrices with semantically meaningful edges is particularly important for this task, but extracting such edges is challenging problem. To solve this, we propose a hierarchically decomposed graph convolutional network (HD-GCN) architecture with a novel hierarchically decomposed graph (HD-Graph). The proposed HD-GCN effectively decomposes every joint node into several sets to extract major structurally adjacent and distant edges, and uses them to construct an HD-Graph containing those edges in the same semantic spaces of a human skeleton. In addition, we introduce an attention-guided hierarchy aggregation (A-HA) module to highlight the dominant hierarchical edge sets of the HD-Graph. Furthermore, we apply a new six-way ensemble method, which uses only joint and bone stream without any motion stream. The proposed model is evaluated and achieves state-of-the-art performance on three large, popular datasets: NTU-RGB+D 60, NTU-RGB+D 120, and Northwestern-UCLA. Finally, we demonstrate the effectiveness of our model with various comparative experiments.},
+  preview={HD-GCN.gif}
 }
 
 @inproceedings{lee2022edgeconv,
@@ -201,7 +202,8 @@ @article{lee2022leveraging
   booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
   year={2023},
   arxiv={2212.04761},
-  abstract={Skeleton-based action recognition has attracted considerable attention due to its compact skeletal structure of the human body. Many recent methods have achieved remarkable performance using graph convolutional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored, spatio-temporal dependency is rarely considered. In this paper, we propose the Inter-Frame Curve Network (IFC-Net) to effectively leverage the spatio-temporal dependency of the human skeleton. Our proposed network consists of two novel elements: 1) The Inter-Frame Curve (IFC) module; and 2) Dilated Graph Convolution (D-GC). The IFC module increases the spatio-temporal receptive field by identifying meaningful node connections between every adjacent frame and generating spatio-temporal curves based on the identified node connections. The D-GC allows the network to have a large spatial receptive field, which specifically focuses on the spatial domain. The kernels of D-GC are computed from the given adjacency matrices of the graph and reflect large receptive field in a way similar to the dilated CNNs. Our IFC-Net combines these two modules and achieves state-of-the-art performance on three skeleton-based action recognition benchmarks: NTU-RGB+D 60, NTU-RGB+D 120, and Northwestern-UCLA.}
+  abstract={Skeleton-based action recognition has attracted considerable attention due to its compact skeletal structure of the human body. Many recent methods have achieved remarkable performance using graph convolutional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored, spatio-temporal dependency is rarely considered. In this paper, we propose the Inter-Frame Curve Network (IFC-Net) to effectively leverage the spatio-temporal dependency of the human skeleton. Our proposed network consists of two novel elements: 1) The Inter-Frame Curve (IFC) module; and 2) Dilated Graph Convolution (D-GC). The IFC module increases the spatio-temporal receptive field by identifying meaningful node connections between every adjacent frame and generating spatio-temporal curves based on the identified node connections. The D-GC allows the network to have a large spatial receptive field, which specifically focuses on the spatial domain. The kernels of D-GC are computed from the given adjacency matrices of the graph and reflect large receptive field in a way similar to the dilated CNNs. Our IFC-Net combines these two modules and achieves state-of-the-art performance on three skeleton-based action recognition benchmarks: NTU-RGB+D 60, NTU-RGB+D 120, and Northwestern-UCLA.},
+  preview={STCNet.gif}
 }
 
 @inproceedings{Lee_2023_CVPR,