Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition

• URL: http://arxiv.org/abs/2007.14690v1
• Date: Wed, 29 Jul 2020 09:12:06 GMT
• Title: Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition
• Authors: Fanfan Ye and Shiliang Pu and Qiaoyong Zhong and Chao Li and Di Xie and Huiming Tang
• Abstract summary: We propose Dynamic GCN, in which a novel convolutional neural network named Contextencoding Network (CeN) is introduced to learn skeleton topology automatically. CeN is extremely lightweight yet effective, and can be embedded into a graph convolutional layer. Dynamic GCN achieves better performance with $2times$$4times$ fewer FLOPs than existing methods.
• Score: 40.467040910143616
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Convolutional Networks (GCNs) have attracted increasing interests for the task of skeleton-based action recognition. The key lies in the design of the graph structure, which encodes skeleton topology information. In this paper, we propose Dynamic GCN, in which a novel convolutional neural network named Contextencoding Network (CeN) is introduced to learn skeleton topology automatically. In particular, when learning the dependency between two joints, contextual features from the rest joints are incorporated in a global manner. CeN is extremely lightweight yet effective, and can be embedded into a graph convolutional layer. By stacking multiple CeN-enabled graph convolutional layers, we build Dynamic GCN. Notably, as a merit of CeN, dynamic graph topologies are constructed for different input samples as well as graph convolutional layers of various depths. Besides, three alternative context modeling architectures are well explored, which may serve as a guideline for future research on graph topology learning. CeN brings only ~7% extra FLOPs for the baseline model, and Dynamic GCN achieves better performance with $2\times$~$4\times$ fewer FLOPs than existing methods. By further combining static physical body connections and motion modalities, we achieve state-of-the-art performance on three large-scale benchmarks, namely NTU-RGB+D, NTU-RGB+D 120 and Skeleton-Kinetics.

Related papers

• Graph Contrastive Learning for Skeleton-based Action Recognition [85.86820157810213]
  We propose a graph contrastive learning framework for skeleton-based action recognition. SkeletonGCL associates graph learning across sequences by enforcing graphs to be class-discriminative. SkeletonGCL establishes a new training paradigm, and it can be seamlessly incorporated into current graph convolutional networks.
  arXiv  Detail & Related papers  (2023-01-26T02:09:16Z)
• Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition [22.188135882864287]
  We propose a novel dynamic hypergraph convolutional networks (DHGCN) for skeleton-based action recognition. DHGCN uses hypergraph to represent the skeleton structure to effectively exploit the motion information contained in human joints.
  arXiv  Detail & Related papers  (2021-12-20T14:46:14Z)
• Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition [15.93566875893684]
  We propose a pure CNN architecture named Topology-aware CNN (Ta-CNN) in this paper. We develop a novel cross-channel feature augmentation module, which is a combo of map-attend-group-map operations. In particular, we develop a novel cross-channel feature augmentation module, which is a combo of map-attend-group-map operations.
  arXiv  Detail & Related papers  (2021-12-08T09:02:50Z)
• Convolutional Neural Network Dynamics: A Graph Perspective [39.81881710355496]
  We take a graph perspective and investigate the relationship between the graph structure of NNs and their performance. For the dynamic graph representation of NNs, we explore structural representations for fully-connected and convolutional layers. Our analysis shows that a simple summary of graph statistics can be used to accurately predict the performance of NNs.
  arXiv  Detail & Related papers  (2021-11-09T20:38:48Z)
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [72.16255675586089]
  We propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T07:18:57Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• Mix Dimension in Poincar\'{e} Geometry for 3D Skeleton-based Action Recognition [57.98278794950759]
  Graph Convolutional Networks (GCNs) have already demonstrated their powerful ability to model the irregular data. We present a novel spatial-temporal GCN architecture which is defined via the Poincar'e geometry. We evaluate our method on two current largest scale 3D datasets.
  arXiv  Detail & Related papers  (2020-07-30T18:23:18Z)
• Simple and Deep Graph Convolutional Networks [63.76221532439285]
  Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Despite their success, most of the current GCN models are shallow, due to the em over-smoothing problem. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques.
  arXiv  Detail & Related papers  (2020-07-04T16:18:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.