DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback
- URL: http://arxiv.org/abs/2304.04496v2
- Date: Fri, 14 Apr 2023 12:28:40 GMT
- Title: DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback
- Authors: Xiaoning Sun, Huaijiang Sun, Bin Li, Dong Wei, Weiqing Li, Jianfeng Lu
- Abstract summary: 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.
- Score: 23.687223152464988
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Let us rethink the real-world scenarios that require human motion prediction
techniques, such as human-robot collaboration. Current works simplify the task
of predicting human motions into a one-off process of forecasting a short
future sequence (usually no longer than 1 second) based on a historical
observed one. However, such simplification may fail to meet practical needs due
to the neglect of the fact that motion prediction in real applications is not
an isolated ``observe then predict'' unit, but a consecutive process composed
of many rounds of such unit, semi-overlapped along the entire sequence. As time
goes on, the predicted part of previous round has its corresponding ground
truth observable in the new round, but their deviation in-between is neither
exploited nor able to be captured by existing isolated learning fashion. In
this paper, we propose DeFeeNet, a simple yet effective network that can be
added on existing one-off prediction models to realize deviation perception and
feedback when applied to consecutive motion prediction task. At each prediction
round, the deviation generated by previous unit is first encoded by our
DeFeeNet, and then incorporated into the existing predictor to enable a
deviation-aware prediction manner, which, for the first time, allows for
information transmit across adjacent prediction units. We design two versions
of DeFeeNet as MLP-based and GRU-based, respectively. On Human3.6M and more
complicated BABEL, experimental results indicate that our proposed network
improves consecutive human motion prediction performance regardless of the
basic model.
Related papers
- Sparse Prototype Network for Explainable Pedestrian Behavior Prediction [60.80524827122901]
We present Sparse Prototype Network (SPN), an explainable method designed to simultaneously predict a pedestrian's future action, trajectory, and pose.
Regularized by mono-semanticity and clustering constraints, the prototypes learn consistent and human-understandable features.
arXiv Detail & Related papers (2024-10-16T03:33:40Z) - Performative Time-Series Forecasting [71.18553214204978]
We formalize performative time-series forecasting (PeTS) from a machine-learning perspective.
We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts.
We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks.
arXiv Detail & Related papers (2023-10-09T18:34:29Z) - Learning Snippet-to-Motion Progression for Skeleton-based Human Motion
Prediction [14.988322340164391]
Existing Graph Convolutional Networks to achieve human motion prediction largely adopt a one-step scheme.
We observe that human motions have transitional patterns and can be split into snippets representative of each transition.
We propose a snippet-to-motion multi-stage framework that breaks motion prediction into sub-tasks easier to accomplish.
arXiv Detail & Related papers (2023-07-26T07:36:38Z) - Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge
for Human Motion Prediction [26.25110973770013]
Previous works on human motion prediction follow the pattern of building a mapping relation between the sequence observed and the one to be predicted.
We present a new prediction pattern, which introduces previously overlooked human poses, to implement the prediction task.
These poses exist after the predicted sequence, and form the privileged sequence.
arXiv Detail & Related papers (2022-08-02T08:13:43Z) - Uncertainty estimation of pedestrian future trajectory using Bayesian
approximation [137.00426219455116]
Under dynamic traffic scenarios, planning based on deterministic predictions is not trustworthy.
The authors propose to quantify uncertainty during forecasting using approximation which deterministic approaches fail to capture.
The effect of dropout weights and long-term prediction on future state uncertainty has been studied.
arXiv Detail & Related papers (2022-05-04T04:23:38Z) - Semantic Prediction: Which One Should Come First, Recognition or
Prediction? [21.466783934830925]
One of the primary downstream tasks is interpreting the scene's semantic composition and using it for decision-making.
There are two main ways to achieve the same outcome, given a pre-trained video prediction and pre-trained semantic extraction model.
We investigate these configurations using the Local Frequency Domain Transformer Network (LFDTN) as the video prediction model and U-Net as the semantic extraction model on synthetic and real datasets.
arXiv Detail & Related papers (2021-10-06T15:01:05Z) - Learning to Predict Trustworthiness with Steep Slope Loss [69.40817968905495]
We study the problem of predicting trustworthiness on real-world large-scale datasets.
We observe that the trustworthiness predictors trained with prior-art loss functions are prone to view both correct predictions and incorrect predictions to be trustworthy.
We propose a novel steep slope loss to separate the features w.r.t. correct predictions from the ones w.r.t. incorrect predictions by two slide-like curves that oppose each other.
arXiv Detail & Related papers (2021-09-30T19:19:09Z) - Adversarial Refinement Network for Human Motion Prediction [61.50462663314644]
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.
arXiv Detail & Related papers (2020-11-23T05:42:20Z) - TPNet: Trajectory Proposal Network for Motion Prediction [81.28716372763128]
Trajectory Proposal Network (TPNet) is a novel two-stage motion prediction framework.
TPNet first generates a candidate set of future trajectories as hypothesis proposals, then makes the final predictions by classifying and refining the proposals.
Experiments on four large-scale trajectory prediction datasets, show that TPNet achieves the state-of-the-art results both quantitatively and qualitatively.
arXiv Detail & Related papers (2020-04-26T00:01:49Z) - 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.