mlsanityData to 14 Oct 2026

Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform

arXiv 2505.12631 ↗First posted 19 May 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The 3D human pose is vital for modern computer vision and computer graphics, and its prediction has drawn attention in recent years. 3D human pose prediction aims at forecasting a human's future motion from the previous sequence. Ignoring that the arbitrariness of human motion sequences has a firm origin in transition in both temporal and spatial axes limits the performance of state-of-the-art methods, leading them to struggle with making precise predictions on complex cases, e.g., arbitrarily posing or greeting. To alleviate this problem, a network called HaarMoDic is proposed in this paper, which utilizes the 2D Haar transform to project joints to higher resolution coordinates where the network can access spatial and temporal information simultaneously. An ablation study proves that the significant contributing module within the HaarModic Network is the Multi-Resolution Haar (MR-Haar) block. Instead of mining in one of two axes or extracting separately, the MR-Haar block projects whole motion sequences to a mixed-up coordinate in higher resolution with 2D Haar Transform, allowing the network to give scope to information from both axes in different resolutions. With the MR-Haar block, the HaarMoDic network can make predictions referring to a broader range of information. Experimental results demonstrate that HaarMoDic surpasses state-of-the-art methods in every testing interval on the Human3.6M dataset in the Mean Per Joint Position Error (MPJPE) metric.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 33 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

18 of 33 references.

References · 18

  1. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  3. 2017On human motion prediction using recurrent neural networkscited by 338
  4. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  5. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  6. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 165
  7. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  8. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  9. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
  10. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  11. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  12. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 100
6 more
  1. 2017Deep representation learning for human motion prediction and classificationcited by 98
  2. 2021Multi-Person Extreme Motion Predictioncited by 75
  3. 2022Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Predictioncited by 66
  4. 2018Action-Agnostic Human Pose Forecastingcited by 56
  5. 2019Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Predictioncited by 50
  6. 2022P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Drivingcited by 1

Built on by

Not cited yet.