# Skeleton-Based Online Action Prediction Using Scale Selection Network

arXiv: https://arxiv.org/abs/1902.03084 · HTML: https://mlsanity.com/paper/1902.03084/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2019.

## Built on by (most cited first, 20 of 20)

- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [Self-Regulated Learning for Egocentric Video Activity Anticipation](https://mlsanity.com/paper/2111.11631/) (2021)
- [IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition](https://mlsanity.com/paper/2207.12100/) (2022)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [Human Interaction Recognition Framework based on Interacting Body Part Attention](https://mlsanity.com/paper/2101.08967/) (2021)
- [Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition](https://mlsanity.com/paper/2110.13008/) (2021)
- [ERA: Expert Retrieval and Assembly for Early Action Prediction](https://mlsanity.com/paper/2207.09675/) (2022)
- [STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition](https://mlsanity.com/paper/2303.18177/) (2023)
- [A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2111.06995/) (2021)
- [Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns](https://mlsanity.com/paper/2205.14405/) (2022)
- [CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition](https://mlsanity.com/paper/2410.07153/) (2024)
- [Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs](https://mlsanity.com/paper/2207.12648/) (2022)
- [Triangular Character Animation Sampling with Motion, Emotion, and Relation](https://mlsanity.com/paper/2203.04930/) (2022)
- [Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution](https://mlsanity.com/paper/2407.21525/) (2024)
- [Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction](https://mlsanity.com/paper/2501.00317/) (2024)
- [An end-to-end multi-scale network for action prediction in videos](https://mlsanity.com/paper/2301.01216/) (2022)
- [Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition](https://mlsanity.com/paper/2307.11973/) (2023)
- [Accurate online action and gesture recognition system using detectors and Deep SPD Siamese Networks](https://mlsanity.com/paper/2511.05250/) (2025)
- [STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition](https://mlsanity.com/paper/2607.17342/) (2026)

## Abstract (arXiv)

Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis. Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step. An activation sharing scheme is also proposed to handle the overlapping computations among the adjacent time steps, which enables our framework to run more efficiently. Moreover, to enhance the performance of our framework for action prediction with the skeletal input data, a hierarchy of dilated tree convolutions are also designed to learn the multi-level structured semantic representations over the skeleton joints at each frame. Our proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of our method for skeleton-based online action prediction.