# Joint Temporal Pooling for Improving Skeleton-based Action Recognition

arXiv: https://arxiv.org/abs/2408.09356 · HTML: https://mlsanity.com/paper/2408.09356/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 18 Aug 2024.

## Builds on (most cited first, 23 of 23)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN](https://mlsanity.com/paper/1803.04831/) (2018)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)
- [SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition](https://mlsanity.com/paper/1904.04289/) (2019)
- [VidTr: Video Transformer Without Convolutions](https://mlsanity.com/paper/2104.11746/) (2021)
- [Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation](https://mlsanity.com/paper/1804.06055/) (2018)
- [PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding](https://mlsanity.com/paper/1703.07475/) (2017)
- [Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2206.13028/) (2022)
- [MGSampler: An Explainable Sampling Strategy for Video Action Recognition](https://mlsanity.com/paper/2104.09952/) (2021)
- [Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning](https://mlsanity.com/paper/1805.02335/) (2018)
- [Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks](https://mlsanity.com/paper/1510.00562/) (2015)
- [RGB-D-based Human Motion Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/1711.08362/) (2017)
- [Making the Invisible Visible: Action Recognition Through Walls and Occlusions](https://mlsanity.com/paper/1909.09300/) (2019)
- [Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks](https://mlsanity.com/paper/1804.01194/) (2018)
- [A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2111.06995/) (2021)
- [Selective Feature Compression for Efficient Activity Recognition Inference](https://mlsanity.com/paper/2104.00179/) (2021)

## Built on by (most cited first, 3 of 3)

- [Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2505.23012/) (2025)
- [DistillH-Mamba: A Hypergraph-Mamba-Based Knowledge Distillation Model for Efficient Impact Fall Detection](https://mlsanity.com/paper/2607.03156/) (2026)
- [DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2609.35444/) (2026)

## 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.