Make Skeleton-based Action Recognition Model Smaller, Faster and Better
Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To alleviate this issue, we analyze skeleton sequence properties to propose a Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition. By using a lightweight network structure (i.e., 0.15 million parameters), DD-Net can reach a super fast speed, as 3,500 FPS on one GPU, or, 2,000 FPS on one CPU. By employing robust features, DD-Net achieves the state-of-the-art performance on our experimental datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code will be released with this paper later.
Code (3)
Tasks
Action RecognitionCPUGPUHand Gesture RecognitionSkeleton Based Action RecognitionSimilar Papers 제목 키워드 기반
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to b…
Action RecognitionSkeleton Based Action RecognitionUNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
Action recognition based on skeleton data has recently witnessed increasing attention and progress. State-of-the-art approaches adopting Graph Convolutional networks (GCNs) can effectively extract features on human skele…
Action ClassificationAction RecognitionSkeleton Based Action RecognitionSkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition
Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contras…
Action RecognitionDecoderSelf-supervised Skeleton-based Action RecognitionSkeleton Based Action RecognitionHAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment
Human actions involve complex pose variations and their 2D projections can be highly ambiguous. Thus 3D spatio-temporal or 4D (i.e., 3D+T) human skeletons, which are photometric and viewpoint invariant, are an excellent …
Action RecognitionAtomic action recognitionSMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition
Abstract— This paper focuses on skeleton-based few-shot action recognition. Since skeleton is essentially a sparse representation of human action, the feature maps extracted from it, through a standard encoder network…
Action RecognitionFew-Shot action recognitionFew Shot Action Recognition