Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction

• URL: http://arxiv.org/abs/2308.16801v1
• Date: Thu, 31 Aug 2023 15:23:33 GMT
• Title: Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction
• Authors: Mohsen Zand, Ali Etemad, Michael Greenspan
• Abstract summary: A new method is proposed for human motion prediction by learning temporal and spatial dependencies. Our proposed method is able to effectively model the sequence information for motion prediction and outperform other techniques to set a new state-of-the-art.
• Score: 23.212848643552395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A new method is proposed for human motion prediction by learning temporal and spatial dependencies. Recently, multiscale graphs have been developed to model the human body at higher abstraction levels, resulting in more stable motion prediction. Current methods however predetermine scale levels and combine spatially proximal joints to generate coarser scales based on human priors, even though movement patterns in different motion sequences vary and do not fully comply with a fixed graph of spatially connected joints. Another problem with graph convolutional methods is mode collapse, in which predicted poses converge around a mean pose with no discernible movements, particularly in long-term predictions. To tackle these issues, we propose ResChunk, an end-to-end network which explores dynamically correlated body components based on the pairwise relationships between all joints in individual sequences. ResChunk is trained to learn the residuals between target sequence chunks in an autoregressive manner to enforce the temporal connectivities between consecutive chunks. It is hence a sequence-to-sequence prediction network which considers dynamic spatio-temporal features of sequences at multiple levels. Our experiments on two challenging benchmark datasets, CMU Mocap and Human3.6M, demonstrate that our proposed method is able to effectively model the sequence information for motion prediction and outperform other techniques to set a new state-of-the-art. Our code is available at https://github.com/MohsenZand/ResChunk.

Related papers

• Multi-Graph Convolution Network for Pose Forecasting [0.8057006406834467]
  We propose a novel approach called the multi-graph convolution network (MGCN) for 3D human pose forecasting. MGCN simultaneously captures spatial and temporal information by introducing an augmented graph for pose sequences. In our evaluation, MGCN outperforms the state-of-the-art in pose prediction.
  arXiv  Detail & Related papers  (2023-04-11T03:59:43Z)
• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors [21.915057426589744]
  We propose a simple yet effective approach that disentangles randomly sampled codes with a deterministic learnable component named anchors to promote sample precision and diversity. In principle, our spatial-temporal anchor-based sampling (STARS) can be applied to different motion predictors.
  arXiv  Detail & Related papers  (2023-02-09T18:58:07Z)
• Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting [50.901984244738806]
  We show how to model the evolutionary and multi-scale interactions of time series. In particular, we first provide a hierarchical graph structure cooperated with the dilated convolution to capture the scale-specific correlations. A unified neural network is provided to integrate the components above to get the final prediction.
  arXiv  Detail & Related papers  (2022-06-28T08:11:12Z)
• Motion Prediction via Joint Dependency Modeling in Phase Space [40.54430409142653]
  We introduce a novel convolutional neural model to leverage explicit prior knowledge of motion anatomy. We then propose a global optimization module that learns the implicit relationships between individual joint features. Our method is evaluated on large-scale 3D human motion benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-07T08:30:01Z)
• 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)
• Generating Smooth Pose Sequences for Diverse Human Motion Prediction [90.45823619796674]
  We introduce a unified deep generative network for both diverse and controllable motion prediction. Our experiments on two standard benchmark datasets, Human3.6M and HumanEva-I, demonstrate that our approach outperforms the state-of-the-art baselines in terms of both sample diversity and accuracy.
  arXiv  Detail & Related papers  (2021-08-19T00:58:00Z)
• MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction [34.565986275769745]
  We propose a novel Multi-Scale Residual Graph Convolution Network (MSR-GCN) for human pose prediction task. Our proposed approach is evaluated on two standard benchmark datasets, i.e., the Human3.6M dataset and the CMU Mocap dataset.
  arXiv  Detail & Related papers  (2021-08-16T15:26:23Z)
• Multi-level Motion Attention for Human Motion Prediction [132.29963836262394]
  We study the use of different types of attention, computed at joint, body part, and full pose levels. Our experiments on Human3.6M, AMASS and 3DPW validate the benefits of our approach for both periodical and non-periodical actions.
  arXiv  Detail & Related papers  (2021-06-17T08:08:11Z)
• Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking [98.91894395941766]
  We propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame. Specifically, we derive this prediction of dynamics through a graph neural network(GNN) that explicitly accounts for both spatial-temporal and visual information. Experiments on PoseTrack 2017 and PoseTrack 2018 datasets demonstrate that the proposed method achieves results superior to the state of the art on both human pose estimation and tracking tasks.
  arXiv  Detail & Related papers  (2021-06-07T16:36:50Z)
• 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)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

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.