Multi-level Motion Attention for Human Motion Prediction
- URL: http://arxiv.org/abs/2106.09300v1
- Date: Thu, 17 Jun 2021 08:08:11 GMT
- Title: Multi-level Motion Attention for Human Motion Prediction
- Authors: Wei Mao, Miaomiao Liu, Mathieu Salzmann, Hongdong Li
- Abstract summary: 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.
- Score: 132.29963836262394
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Human motion prediction aims to forecast future human poses given a
historical motion. Whether based on recurrent or feed-forward neural networks,
existing learning based methods fail to model the observation that human motion
tends to repeat itself, even for complex sports actions and cooking activities.
Here, we introduce an attention based feed-forward network that explicitly
leverages this observation. In particular, instead of modeling frame-wise
attention via pose similarity, we propose to extract motion attention to
capture the similarity between the current motion context and the historical
motion sub-sequences. In this context, we study the use of different types of
attention, computed at joint, body part, and full pose levels. Aggregating the
relevant past motions and processing the result with a graph convolutional
network allows us to effectively exploit motion patterns from the long-term
history to predict the future poses. Our experiments on Human3.6M, AMASS and
3DPW validate the benefits of our approach for both periodical and
non-periodical actions. Thanks to our attention model, it yields
state-of-the-art results on all three datasets. Our code is available at
https://github.com/wei-mao-2019/HisRepItself.
Related papers
- Past Movements-Guided Motion Representation Learning for Human Motion Prediction [0.0]
We propose a self-supervised learning framework designed to enhance motion representation.
The framework consists of two stages: first, the network is pretrained through the self-reconstruction of past sequences, and the guided reconstruction of future sequences based on past movements.
Our method reduces the average prediction errors by 8.8% across Human3.6, 3DPW, and AMASS datasets.
arXiv Detail & Related papers (2024-08-04T17:00:37Z) - 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) - 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) - 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) - 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) - Multi-Person Extreme Motion Prediction with Cross-Interaction Attention [44.35977105396732]
Human motion prediction aims to forecast future human poses given a sequence of past 3D skeletons.
We assume that the input of our system are two sequences of past skeletons for two interacting persons.
We devise a novel cross interaction attention mechanism that learns to predict cross dependencies between self poses and the poses of the other person.
arXiv Detail & Related papers (2021-05-18T20:52:05Z) - 3D Human motion anticipation and classification [8.069283749930594]
We propose a novel sequence-to-sequence model for human motion prediction and feature learning.
Our model learns to predict multiple future sequences of human poses from the same input sequence.
We show that it takes less than half the number of epochs to train an activity recognition network by using the feature learned from the discriminator.
arXiv Detail & Related papers (2020-12-31T00:19:39Z) - History Repeats Itself: Human Motion Prediction via Motion Attention [81.94175022575966]
We introduce an attention-based feed-forward network that explicitly leverages the observation that human motion tends to repeat itself.
In particular, we propose to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences.
Our experiments on Human3.6M, AMASS and 3DPW evidence the benefits of our approach for both periodical and non-periodical actions.
arXiv Detail & Related papers (2020-07-23T02:12:27Z)
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.