• Corpus ID: 233481953

OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation

@article{Feng2021ORNetPR,
  title={OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation},
  author={Qianyu Feng and Linchao Zhu and Bang Zhang and Pan Pan and Yi Yang},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.00397}
}
Contemporary data-driven methods are typically fed with full supervision on large-scale datasets which limits their applicability. However, in the actual systems with limitations such as measurement error and data acquisition problems, people usually obtain incomplete data. Although data completion has attracted wide attention, the underlying data pattern and relativity are still underdeveloped. Currently, the family of latent variable models allows learning deep latent variables over observed… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 36 REFERENCES

Position-aware Graph Neural Networks

Position-aware Graph Neural Networks (P-GNNs) are proposed, a new class of GNNs for computing position-aware node embeddings that are inductive, scalable, and can incorporate node feature information.

Deep Learning Face Attributes in the Wild

A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.

Gaussian Processes for Regression

This paper investigates the use of Gaussian process priors over functions, which permit the predictive Bayesian analysis for fixed values of hyperparameters to be carried out exactly using matrix operations.

Conditional Neural Processes

Conditional Neural Processes are inspired by the flexibility of stochastic processes such as GPs, but are structured as neural networks and trained via gradient descent, yet scale to complex functions and large datasets.

Sparse On-Line Gaussian Processes

An approach for sparse representations of gaussian process (GP) models (which are Bayesian types of kernel machines) in order to overcome their limitations for large data sets is developed based on a combination of a Bayesian on-line algorithm and a sequential construction of a relevant subsample of data that fully specifies the prediction of the GP model.

Finding Structure in Time

A proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory and suggests a method for representing lexical categories and the type/token distinction is developed.

Long short-termmemory

  • Neural computation 9,
  • 1997

Action2Motion: Conditioned Generation of 3D Human Motions

This paper aims to generate plausible human motion sequences in 3D given a prescribed action type, and proposes a temporal Variational Auto-Encoder (VAE) that encourages a diverse sampling of the motion space.

Polarization Human Shape and Pose Dataset

This work attempts to investigate the new question of whether the geometric cues from polarization camera could be leveraged in estimating detailed human body shapes, and curation of Polarization Human Shape and Pose Dataset (PHSPD), the home-grown polarization image dataset of various human shapes and poses.

Stochastic modelling and analysis of degradation for highly reliable products

In this paper, degradation models are classified into three classes, that is, stochastic process models, general path models, and other models beyond these two classes.