Adversarial Refinement Network for Human Motion Prediction
- URL: http://arxiv.org/abs/2011.11221v2
- Date: Tue, 24 Nov 2020 02:16:10 GMT
- Title: Adversarial Refinement Network for Human Motion Prediction
- Authors: Xianjin Chao, Yanrui Bin, Wenqing Chu, Xuan Cao, Yanhao Ge, Chengjie
Wang, Jilin Li, Feiyue Huang, Howard Leung
- Abstract summary: Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend.
We propose an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation.
- Score: 61.50462663314644
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Human motion prediction aims to predict future 3D skeletal sequences by
giving a limited human motion as inputs. Two popular methods, recurrent neural
networks and feed-forward deep networks, are able to predict rough motion
trend, but motion details such as limb movement may be lost. To predict more
accurate future human motion, we propose an Adversarial Refinement Network
(ARNet) following a simple yet effective coarse-to-fine mechanism with novel
adversarial error augmentation. Specifically, we take both the historical
motion sequences and coarse prediction as input of our cascaded refinement
network to predict refined human motion and strengthen the refinement network
with adversarial error augmentation. During training, we deliberately introduce
the error distribution by learning through the adversarial mechanism among
different subjects. In testing, our cascaded refinement network alleviates the
prediction error from the coarse predictor resulting in a finer prediction
robustly. This adversarial error augmentation provides rich error cases as
input to our refinement network, leading to better generalization performance
on the testing dataset. We conduct extensive experiments on three standard
benchmark datasets and show that our proposed ARNet outperforms other
state-of-the-art methods, especially on challenging aperiodic actions in both
short-term and long-term predictions.
Related papers
- AdvMT: Adversarial Motion Transformer for Long-term Human Motion
Prediction [2.837740438355204]
We present the Adversarial Motion Transformer (AdvMT), a novel model that integrates a transformer-based motion encoder and a temporal continuity discriminator.
With adversarial training, our method effectively reduces the unwanted artifacts in predictions, thereby ensuring the learning of more realistic and fluid human motions.
arXiv Detail & Related papers (2024-01-10T09:15:50Z) - GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction [15.731398013255179]
We propose a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction.
A two-stage tree sampling algorithm is presented, which leverages common features to reduce the inference time and improve accuracy for multi-modal prediction.
Experimental results demonstrate that our proposed framework achieves comparable state-of-the-art performance with real-time inference speed in public datasets.
arXiv Detail & Related papers (2023-11-25T03:55:06Z) - Physics-constrained Attack against Convolution-based Human Motion
Prediction [10.57307572170918]
We propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints.
Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example.
arXiv Detail & Related papers (2023-06-21T03:01:45Z) - 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) - DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback [23.687223152464988]
We propose DeFeeNet, a simple yet effective network that can be added on existing one-off prediction models.
We show that our proposed network improves consecutive human motion prediction performance regardless of the basic model.
arXiv Detail & Related papers (2023-04-10T10:18:23Z) - 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) - Probabilistic Human Motion Prediction via A Bayesian Neural Network [71.16277790708529]
We propose a probabilistic model for human motion prediction in this paper.
Our model could generate several future motions when given an observed motion sequence.
We extensively validate our approach on a large scale benchmark dataset Human3.6m.
arXiv Detail & Related papers (2021-07-14T09:05:33Z) - Interpretable Social Anchors for Human Trajectory Forecasting in Crowds [84.20437268671733]
We propose a neural network-based system to predict human trajectory in crowds.
We learn interpretable rule-based intents, and then utilise the expressibility of neural networks to model scene-specific residual.
Our architecture is tested on the interaction-centric benchmark TrajNet++.
arXiv Detail & Related papers (2021-05-07T09:22:34Z) - Social NCE: Contrastive Learning of Socially-aware Motion
Representations [87.82126838588279]
Experimental results show that the proposed method dramatically reduces the collision rates of recent trajectory forecasting, behavioral cloning and reinforcement learning algorithms.
Our method makes few assumptions about neural architecture designs, and hence can be used as a generic way to promote the robustness of neural motion models.
arXiv Detail & Related papers (2020-12-21T22:25:06Z) - Reciprocal Learning Networks for Human Trajectory Prediction [31.390399065230017]
We develop a new approach, called reciprocal learning, for human trajectory prediction.
We borrow the concept of adversarial attacks of deep neural networks, which iteratively modifies the input of the network to match the given or forced network output.
Our new method outperforms the state-of-the-art methods for human trajectory prediction.
arXiv Detail & Related papers (2020-04-09T02:50:29Z)
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.