PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition

Zhao, Mengyi; Dai, Shi‐Lu; Zhu, Yongwei; Tang, Hao; Xie, Ping; Li, Yue; Zhang, Baochang

doi:10.1016/j.neucom.2022.06.070

Cited by 9 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Year Top-1(%) Top-5(%) ST-GCN [25] 2018 30.7 52.8 STGR-GCN [60] 2019 33.6 56.1 AS-GCN [50] 2019 34.8 56.5 2s-AGCN [26] 2019 36.1 58.7 DGNN [39] 2019 36.9 59.6 BAGCN [61] 2019 37.3 60.2 L-CAGCN [62] 2020 33.3 55.4 A-CAGCN [62] 2020 34.1 56.6 GCN-NAS [48] 2020 37.1 60.1 2s-AAGCN [27] 2020 37.4 60.4 CGCN [63] 2020 37.5 60.4 MS-AAGCN [27] 2020 37.8 61.0 Dynamic GCN [30] 2020 37.9 61.3 MS-G3D [28] 2020 38 60.9 MS-AAGCN+TEM [47] 2020 38 61.4 2s-AAGCN+TEM [47] 2020 38.6 61.6 PR-GCN [64] 2021 33.7 55.8 ST-TR [36] 2021 37 59.7 SEFN(Att) [31] 2021 37.7 N/A SEFN(Base) [31] 2021 37.8 N/A ST-TR-agcn [36] 2021 38 60.5 PB-GCN [65] 2022 30.9 52.8 PeGCN [66] 2022 34.8 57.2 Graph2Net [32] 2022 36.8 N/A EGCN [67] 2022 37.1 59.7 Sybio-GNN [33] 2022 37.2 58.1 TE-GCN [68] 2022 37. can be seen that the additional motion streams cannot bring evident improvement to the Kinetics-Skeleton dataset. Even, the MS-AAGCN+TEM is inferior to 2s-AAGCN+TEM by 0.6% top-1 accuracy.…”

Section: Methodsmentioning

confidence: 99%

“…Year CS(%) CV(%) GCA-LSTM [17] 2018 74.3 82.8 ST-GCN [25] 2018 81.5 88.3 SR-TSL [15] 2018 84.8 92.4 HCN [69] 2018 86.5 91.1 DPRL+GCNN [35] 2018 83.5 89.8 AS-GCN [50] 2019 86.8 94.2 AGC-LSTM [70] 2019 89.2 95.0 2s-AGCN [26] 2019 88.5 95.1 DGNN [39] 2019 89.9 96.1 BAGCN [61] 2019 90.3 96.3 STGR-GCN [60] 2019 86.9 92.3 TS-SAN [71] 2020 87.2 92.7 2s-AAGCN+TEM [47] 2020 88.7 95.8 SGN [72] 2020 89.0 94.5 2s-Shift-GCN [29] 2020 89.7 96 GCN-NAS [48] 2020 89.4 95.7 2s-AAGCN [27] 2020 89.4 96.0 MS-AAGCN [27] 2020 90.0 96.2 CGCN [63] 2020 90.3 96.4 4s-Shift-GCN [29] 2020 90.7 96.5 MS-AAGCN+TEM [47] 2020 91 96.5 Dynamic GCN [30] 2020 91.5 96 MS-G3D [28] 2020 91.5 96.2 PR-GCN [64] 2021 85.2 91.7 RA-GCN [49] 2021 87.3 93.6 SEFN(Base) [31] 2021 89.2 95.8 ST-TR [36] 2021 89.9 96.1 SEFN(Att) [31] 2021 90.2 96.1 ST-TR-agcn [36] 2021 90.3 96.3 MSTGNN [73] 2021 91.3 95.5 PB-GCN [65] 2022 83.8 91.3 PeGCN [66] 2022 85.6 93.4 LAGA [51] 2022 87.1 93.2 TE-GCN [68] 2022 88.7 95.4 EGCN [67] 2022 89.1 95.5 Graph2Net [32] 2022 90.1 96 Sybio-GNN [33] 2022 90.1 95.4 CD-GCN [34] 2022 90.1 96.5 Ta-CNN [24] 2022 90.7 95.1 FR-AGCN [52] 2022 90. is c...…”

Section: Methodsmentioning

confidence: 99%

“…Year CSv1(%) CSv2(%) ST-GCN [25] 2018 30.25 56.14 DGNN [39] 2019 29.9 N/A 2s-AGCN [26] 2019 34.84 66.68 HARD-Net [77] 2020 36.97 N/A 4s-Shift-GCN [29] 2020 37.98 67.04 AAGCN [27] 2020 41.43 N/A MS-G3D [28] 2020 43.94 N/A PB-GCN [65] 2022 37.48 N/A TE-GCN [68] 2022 42.5 68.2 FR-AGCN [52] 2022…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action Recognition

Huang

Dou

Lin

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Graph convolutional networks (GCN) have attracted increasing interest in action recognition in recent years. GCN models human skeleton sequences as spatio-temporal graphs. Also, attention mechanisms are often jointly used with GCNs to highlight important frames or body joints in a sequence. However, attention modules learn parameters offline and are fixed, so may not adapt well to various action samples. In this paper, we propose a simple but effective motion-driven spatial and temporal adaptation strategy to dynamically strengthen the features of important frames and joints for skeleton-based action recognition. The rationale is that the joints and frames with dramatic motions are generally more informative and discriminative. We decouple and combine the spatial and temporal refinements by using a two-branch structure, in which the joint and frame-wise feature refinements perform in parallel. Such a structure can also lead to learn more complementary feature representations. Moreover, we propose to use the fully connected graph convolution to learn the long-range spatial dependencies. Besides, we investigate two high-resolution skeleton graphs by creating virtual joints, aiming to improve the representation of skeleton features. By combining the above proposals, we develop a novel motion-driven spatial and temporal adaptive high-resolution GCN. Experimental results demonstrate that the proposed model achieves state-of-the-art (SOTA) results on the challenging large-scale Kinetics-Skeleton and UAV-Human datasets, and it is on par with the SOTA methods on the two NTU-RGB+D 60&120 datasets. Additionally, our motiondriven adaptation method shows encouraging performance when compared with the attention mechanisms.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action Recognition

Huang

Dou

Lin

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…The adjacency matrix was used as a shared topology for all channels, and the channelspecific correlations were used as a non-shared topology for each channel. Zhao et al [22] introduced two progressive binary graph convolutional networks, in which the filters and activations were binarized to decrease the parameters, which could improve the training and inference speed. Zhang [23] proposed a spatial attentive and temporal dilated (SATD) method, in which the spatial attention pooling module (SAP) is proposed to identify important vertices and to remove unimportant vertices, and the temporal dilated graph convolution module is used to expand the receptive field.…”

Section: Graph Covolutional Network For Skeleton-based Action Recogni...mentioning

confidence: 99%

2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition

et al. 2023

View full text Add to dashboard Cite

As human actions can be characterized by the trajectories of skeleton joints, skeleton-based action recognition techniques have gained increasing attention in the field of intelligent recognition and behavior analysis. With the emergence of large datasets, graph convolutional network (GCN) approaches have been widely applied for skeleton-based action recognition and have achieved remarkable performances. In this paper, a novel GCN-based approach is proposed by introducing a convolutional block attention module (CBAM)-based graph attention block to compute the semantic correlations between any two vertices. By considering semantic correlations, our model can effectively identify the most discriminative vertex connections associated with specific actions, even when the two vertices are physically unconnected. Experimental results demonstrate that the proposed model is effective and outperforms existing methods.

show abstract

Two Stream Multi-Attention Graph Convolutional Network for Skeleton-Based Action Recognition

Zhou,

Tian,

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition

Cited by 9 publications

References 13 publications

Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action Recognition

Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action Recognition

2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition

Two Stream Multi-Attention Graph Convolutional Network for Skeleton-Based Action Recognition

Contact Info

Product

Resources

About