Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
This work addresses a critical flaw in GCNs for skeleton-based action recognition, offering a more efficient and accurate model for applications in human-computer interaction and surveillance.
The paper tackles the problem of topology agnosticism in Graph Convolutional Networks (GCNs) for skeleton-based action recognition, where joint optimization of adjacency matrices leads to loss of bone connectivity, and proposes BlockGCN, which uses graph distances, temporal means, and BlockGC to reduce parameters by over 40% while achieving high accuracy on datasets like NTU RGB+D 120.
Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacency matrix. However, an inherent flaw has come to light in these cutting-edge models: they tend to optimize the adjacency matrix jointly with the model weights. This process, while seemingly efficient, causes a gradual decay of bone connectivity data, culminating in a model indifferent to the very topology it sought to map. As a remedy, we propose a threefold strategy: (1) We forge an innovative pathway that encodes bone connectivity by harnessing the power of graph distances. This approach preserves the vital topological nuances often lost in conventional GCNs. (2) We highlight an oft-overlooked feature - the temporal mean of a skeletal sequence, which, despite its modest guise, carries highly action-specific information. (3) Our investigation revealed strong variations in joint-to-joint relationships across different actions. This finding exposes the limitations of a single adjacency matrix in capturing the variations of relational configurations emblematic of human movement, which we remedy by proposing an efficient refinement to Graph Convolutions (GC) - the BlockGC. This evolution slashes parameters by a substantial margin (above 40%), while elevating performance beyond original GCNs. Our full model, the BlockGCN, establishes new standards in skeleton-based action recognition for small model sizes. Its high accuracy, notably on the large-scale NTU RGB+D 120 dataset, stand as compelling proof of the efficacy of BlockGCN.