paper-with-me

Papers

Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion

2021-11-24 · Anthony Bourached, Robert Gray, Xiaodong Guan, Ryan-Rhys Griffiths, Ashwani Jha, Parashkev Nachev

Models of human motion commonly focus either on trajectory prediction or action classification but rarely both. The marked heterogeneity and intricate compositionality of human motion render each task vulnerable to the data degradation and distributional shift common to real-world scenarios. A sufficiently expressive generative model of action could in theory enable data conditioning and distributional resilience within a unified framework applicable to both tasks. Here we propose a novel architecture based on hierarchical variational autoencoders and deep graph convolutional neural networks for generating a holistic model of action over multiple time-scales. We show this Hierarchical Graph-convolutional Variational Autoencoder (HG-VAE) to be capable of generating coherent actions, detecting out-of-distribution data, and imputing missing data by gradient ascent on the model's posterior. Trained and evaluated on H3.6M and the largest collection of open source human motion data, AMASS, we show HG-VAE can facilitate downstream discriminative learning better than baseline models.

📄 PDF Abstract BibTeX arXiv:2111.12602

Code (1)

bouracha/generative_imputation 공식 구현 pytorch

Tasks

Action ClassificationTrajectory Prediction

Similar Papers 제목 키워드 기반

Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics

2020-05-06 · ACL 2020 6 · Guy Emerson

Functional Distributional Semantics provides a linguistically interpretable framework for distributional semantics, by representing the meaning of a word as a function (a binary classifier), instead of a vector. However,…

Language ModelingLanguage ModellingSemantic CompositionSemantic Similarity+2

Semi-supervised Parsing with a Variational Autoencoding Parser

2020-07-01 · WS 2020 7 · Xiao Zhang, Dan Goldwasser

We propose an end-to-end variational autoencoding parsing (VAP) model for semi-supervised graph-based projective dependency parsing. It encodes the input using continuous latent variables in a sequential manner by deep n…

Dependency Parsing

Variational Autoencoding Molecular Graphs with Denoising Diffusion Probabilistic Model

2023-07-02 · Daiki Koge, Naoaki Ono, Shigehiko Kanaya

In data-driven drug discovery, designing molecular descriptors is a very important task. Deep generative models such as variational autoencoders (VAEs) offer a potential solution by designing descriptors as probabilistic…

DenoisingDrug DiscoveryMolecular Property PredictionProperty Prediction+1

CoVAE: Consistency Training of Variational Autoencoders

2025-07-12 · Gianluigi Silvestri, Luca Ambrogioni arxiv

Current state-of-the-art generative approaches frequently rely on a two-stage training procedure, where an autoencoder (often a VAE) first performs dimensionality reduction, followed by training a generative model on the…

Dimensionality Reduction

WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling

2018-03-04 · ICLR 2018 1 · Hao Zhang, Bo Chen, Dandan Guo, Mingyuan Zhou

To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep late…