# Development of Human Motion Prediction Strategy using Inception Residual Block

arXiv: https://arxiv.org/abs/2108.04001 · HTML: https://mlsanity.com/paper/2108.04001/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 51 references that are in the map.
- First posted on arXiv 9 Aug 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles](https://mlsanity.com/paper/1604.07446/) (2016)
- [Learning Trajectory Dependencies for Human Motion Prediction](https://mlsanity.com/paper/1908.05436/) (2019)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction](https://mlsanity.com/paper/2003.08802/) (2020)
- [Convolutional Sequence to Sequence Model for Human Dynamics](https://mlsanity.com/paper/1805.00655/) (2018)
- [Deep representation learning for human motion prediction and classification](https://mlsanity.com/paper/1702.07486/) (2017)
- [Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks](https://mlsanity.com/paper/1704.06803/) (2017)
- [Memory Attention Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1804.08254/) (2018)
- [Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks](https://mlsanity.com/paper/1804.08313/) (2018)
- [Motion Prediction Using Temporal Inception Module](https://mlsanity.com/paper/2010.03006/) (2020)
- [A context-aware pedestrian trajectory prediction framework for automated vehicles](https://mlsanity.com/paper/2104.08123/) (2021)
- [Context-Aware Pedestrian Motion Prediction In Urban Intersections](https://mlsanity.com/paper/1806.09453/) (2018)
- [A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling](https://mlsanity.com/paper/1809.08875/) (2018)

## Abstract (arXiv)

Human Motion Prediction is a crucial task in computer vision and robotics. It has versatile application potentials such as in the area of human-robot interactions, human action tracking for airport security systems, autonomous car navigation, computer gaming to name a few. However, predicting human motion based on past actions is an extremely challenging task due to the difficulties in detecting spatial and temporal features correctly. To detect temporal features in human poses, we propose an Inception Residual Block(IRB), due to its inherent capability of processing multiple kernels to capture salient features. Here, we propose to use multiple 1-D Convolution Neural Network (CNN) with different kernel sizes and input sequence lengths and concatenate them to get proper embedding. As kernels strides over different receptive fields, they detect smaller and bigger salient features at multiple temporal scales. Our main contribution is to propose a residual connection between input and the output of the inception block to have a continuity between the previously observed pose and the next predicted pose. With this proposed architecture, it learns prior knowledge much better about human poses and we achieve much higher prediction accuracy as detailed in the paper. Subsequently, we further propose to feed the output of the inception residual block as an input to the Graph Convolution Neural Network (GCN) due to its better spatial feature learning capability. We perform a parametric analysis for better designing of our model and subsequently, we evaluate our approach on the Human 3.6M dataset and compare our short-term as well as long-term predictions with the state of the art papers, where our model outperforms most of the pose results, the detailed reasons of which have been elaborated in the paper.