mlsanityData to 7 Oct 2026

Joint Temporal Pooling for Improving Skeleton-based Action Recognition

arXiv 2408.09356 ↗First posted 18 Aug 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 18 Aug 2024.

Builds on

23 of 37 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  3. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  4. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  5. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  6. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  7. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  8. 2018Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNcited by 142
  9. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  10. 2018AdaFrame: Adaptive Frame Selection for Fast Video Recognitioncited by 134
  11. 2019SCSampler: Sampling Salient Clips from Video for Efficient Action Recognitioncited by 133
  12. 2021VidTr: Video Transformer Without Convolutionscited by 112
11 more
  1. 2018Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregationcited by 106
  2. 2017PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understandingcited by 101
  3. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  4. 2021MGSampler: An Explainable Sampling Strategy for Video Action Recognitioncited by 49
  5. 2018Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learningcited by 47
  6. 2015Human Action Recognition using Factorized Spatio-Temporal Convolutional Networkscited by 40
  7. 2017RGB-D-based Human Motion Recognition with Deep Learning: A Surveycited by 37
  8. 2019Making the Invisible Visible: Action Recognition Through Walls and Occlusionscited by 25
  9. 2018Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networkscited by 19
  10. 2021A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognitioncited by 6
  11. 2021Selective Feature Compression for Efficient Activity Recognition Inferencecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognitioncited by 4
  2. 2026DistillH-Mamba: A Hypergraph-Mamba-Based Knowledge Distillation Model for Efficient Impact Fall Detectioncited by 1
  3. 2026DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognitioncited by 0