# Motion Prediction Using Temporal Inception Module

arXiv: https://arxiv.org/abs/2010.03006 · HTML: https://mlsanity.com/paper/2010.03006/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [Back to MLP: A Simple Baseline for Human Motion Prediction](https://mlsanity.com/paper/2207.01567/) (2022)
- [Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction](https://mlsanity.com/paper/2203.16051/) (2022)
- [Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors](https://mlsanity.com/paper/2302.04860/) (2023)
- [TrajeVAE: Controllable Human Motion Generation from Trajectories](https://mlsanity.com/paper/2104.00351/) (2021)
- [3D Pose Based Feedback for Physical Exercises](https://mlsanity.com/paper/2208.03257/) (2022)
- [Learning Multiscale Correlations for Human Motion Prediction](https://mlsanity.com/paper/2103.10674/) (2021)
- [Dyadic Human Motion Prediction](https://mlsanity.com/paper/2112.00396/) (2021)
- [Recent Advances in Deterministic Human Motion Prediction: A Review](https://mlsanity.com/paper/2312.06184/) (2023)
- [Temporal Continual Learning with Prior Compensation for Human Motion Prediction](https://mlsanity.com/paper/2507.04060/) (2025)
- [Development of Human Motion Prediction Strategy using Inception Residual Block](https://mlsanity.com/paper/2108.04001/) (2021)

## Abstract (arXiv)

Human motion prediction is a necessary component for many applications in robotics and autonomous driving. Recent methods propose using sequence-to-sequence deep learning models to tackle this problem. However, they do not focus on exploiting different temporal scales for different length inputs. We argue that the diverse temporal scales are important as they allow us to look at the past frames with different receptive fields, which can lead to better predictions. In this paper, we propose a Temporal Inception Module (TIM) to encode human motion. Making use of TIM, our framework produces input embeddings using convolutional layers, by using different kernel sizes for different input lengths. The experimental results on standard motion prediction benchmark datasets Human3.6M and CMU motion capture dataset show that our approach consistently outperforms the state of the art methods.