Enhancing Human Motion Prediction via Multi-range Decoupling Decoding with Gating-adjusting Aggregation

• URL: http://arxiv.org/abs/2503.23381v1
• Date: Sun, 30 Mar 2025 10:10:31 GMT
• Title: Enhancing Human Motion Prediction via Multi-range Decoupling Decoding with Gating-adjusting Aggregation
• Authors: Jiexin Wang, Wenwen Qiang, Zhao Yang, Bing Su,
• Abstract summary: Expressive representation of pose sequences is crucial for accurate motion modeling in human motion prediction.<n>Recent deep learning-based methods tend to overlook the varying relevance and dependencies between historical information and future moments.<n>We propose a novel approach called multi-range decoupling decoding with gating-adjusting aggregation.
• Score: 19.11704999742834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Expressive representation of pose sequences is crucial for accurate motion modeling in human motion prediction (HMP). While recent deep learning-based methods have shown promise in learning motion representations, these methods tend to overlook the varying relevance and dependencies between historical information and future moments, with a stronger correlation for short-term predictions and weaker for distant future predictions. This limits the learning of motion representation and then hampers prediction performance. In this paper, we propose a novel approach called multi-range decoupling decoding with gating-adjusting aggregation ($MD2GA$), which leverages the temporal correlations to refine motion representation learning. This approach employs a two-stage strategy for HMP. In the first stage, a multi-range decoupling decoding adeptly adjusts feature learning by decoding the shared features into distinct future lengths, where different decoders offer diverse insights into motion patterns. In the second stage, a gating-adjusting aggregation dynamically combines the diverse insights guided by input motion data. Extensive experiments demonstrate that the proposed method can be easily integrated into other motion prediction methods and enhance their prediction performance.

Related papers

• MDMP: Multi-modal Diffusion for supervised Motion Predictions with uncertainty [7.402769693163035]
  This paper introduces a Multi-modal Diffusion model for Motion Prediction (MDMP) It integrates skeletal data and textual descriptions of actions to generate refined long-term motion predictions with quantifiable uncertainty. Our model consistently outperforms existing generative techniques in accurately predicting long-term motions.
  arXiv  Detail & Related papers  (2024-10-04T18:49:00Z)
• AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving [59.94343412438211]
  We introduce the GPT style next token motion prediction into motion prediction. Different from language data which is composed of homogeneous units -words, the elements in the driving scene could have complex spatial-temporal and semantic relations. We propose to adopt three factorized attention modules with different neighbors for information aggregation and different position encoding styles to capture their relations.
  arXiv  Detail & Related papers  (2024-03-20T06:22:37Z)
• CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion [6.862357145175449]
  We propose CoMusion, a single-stage, end-to-end diffusion-based HMP framework. CoMusion is inspired from the insight that a smooth future pose prediction performance improves spatial prediction performance. Our method, facilitated by the Transformer-GCN module design and a proposed variance scheduler, predicts accurate, realistic, and consistent motions.
  arXiv  Detail & Related papers  (2023-05-21T19:31:56Z)
• Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark [49.58762201363483]
  We introduce RatPose, a bio-robot motion prediction dataset constructed by considering the influence factors of individuals and environments. We propose a Dual-stream Motion-Scenario Decoupling framework that effectively separates scenario-oriented and motion-oriented features. We demonstrate significant performance improvements of the proposed textitDMSD framework on different difficulty-level tasks.
  arXiv  Detail & Related papers  (2023-05-17T14:14:31Z)
• Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction [81.94175022575966]
  We introduce the task of action-driven human motion prediction. It aims to predict multiple plausible future motions given a sequence of action labels and a short motion history.
  arXiv  Detail & Related papers  (2022-05-31T08:38:07Z)
• Hybrid Predictive Coding: Inferring, Fast and Slow [62.997667081978825]
  We propose a hybrid predictive coding network that combines both iterative and amortized inference in a principled manner. We demonstrate that our model is inherently sensitive to its uncertainty and adaptively balances balances to obtain accurate beliefs using minimum computational expense.
  arXiv  Detail & Related papers  (2022-04-05T12:52:45Z)
• Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction [63.62263239934777]
  We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. We propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction. Our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency.
  arXiv  Detail & Related papers  (2021-12-30T10:45:22Z)
• Dyadic Human Motion Prediction [119.3376964777803]
  We introduce a motion prediction framework that explicitly reasons about the interactions of two observed subjects. Specifically, we achieve this by introducing a pairwise attention mechanism that models the mutual dependencies in the motion history of the two subjects. This allows us to preserve the long-term motion dynamics in a more realistic way and more robustly predict unusual and fast-paced movements.
  arXiv  Detail & Related papers  (2021-12-01T10:30:40Z)
• RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting [34.54878390622877]
  We propose a generic motion forecasting framework with dynamic key information selection and ranking based on a hybrid attention mechanism. The framework is instantiated to handle multi-agent trajectory prediction and human motion forecasting tasks. We validate the framework on both synthetic simulations and motion forecasting benchmarks in different domains.
  arXiv  Detail & Related papers  (2021-08-03T06:30:30Z)
• Learning Multiscale Correlations for Human Motion Prediction [10.335804615372629]
  We propose a novel multiscale graph convolution network (MGCN) to capture the correlations among human body components. We evaluate our approach on two standard benchmark datasets for human motion prediction.
  arXiv  Detail & Related papers  (2021-03-19T07:58:16Z)
• SDMTL: Semi-Decoupled Multi-grained Trajectory Learning for 3D human motion prediction [5.581663772616127]
  We propose a novel end-to-end network, Semi-Decoupled Multi-grained Trajectory Learning network, to predict future human motion. Specifically, we capture the temporal dynamics of motion trajectory at multi-granularity, including fine granularity and coarse. We learn multi-grained trajectory information using BSMEs hierarchically and further capture the information of temporal evolutional directions at each granularity.
  arXiv  Detail & Related papers  (2020-10-11T01:29:21Z)
• Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition [16.22360992454675]
  Action recognition via 3D skeleton data is an emerging important topic in these years. In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL. Our approach typically improves existing hand-crafted methods by 10-50% top-1 accuracy.
  arXiv  Detail & Related papers  (2020-08-01T06:37:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.