Joint Temporal Pooling for Improving Skeleton-based Action Recognition
In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame equally. However, in an action sequence, only a few segments of frames carry discriminative information related to the action. This paper presents a novel Joint Motion Adaptive Temporal Pooling (JMAP) method for improving skeleton-based action recognition. Two variants of JMAP, frame-wise pooling and joint-wise pooling, are introduced. The efficacy of JMAP has been validated through experiments on the popular NTU RGB+D 120 and PKU-MMD datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionSkeleton Based Action RecognitionTemporal Action LocalizationSimilar Papers 제목 키워드 기반
Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
Three dimensional convolutional neural networks (3D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied to video-base…
Action RecognitionTemporal Action LocalizationNeural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition
Skeleton-based human action recognition is becoming increasingly important in a variety of fields. Most existing works train a CNN or GCN based backbone to extract spatial-temporal features, and use temporal average/…
Action RecognitionSkeleton Based Action RecognitionTemporal Action LocalizationUnified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling
This paper simultaneously addresses three limitations associated with conventional skeleton-based action recognition; skeleton detection and tracking errors, poor variety of the targeted actions, as well as person-wise a…
Action LocalizationAction RecognitionActivity RecognitionData Augmentation+63Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
Many skeletal action recognition models use GCNs to represent the human body by 3D body joints connected body parts. GCNs aggregate one- or few-hop graph neighbourhoods, and ignore the dependency between not linked body …
Action RecognitionSkeleton Based Action RecognitionSkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition
Due to the availability of large-scale skeleton datasets, 3D human action recognition has recently called the attention of computer vision community. Many works have focused on encoding skeleton data as skeleton image re…
3D Action RecognitionAction RecognitionSkeleton Based Action RecognitionTemporal Action Localization