paper-with-me

Papers

Conditional Temporal Variational AutoEncoder for Action Video Prediction

2021-08-12 · Xiaogang Xu, Yi Wang, LiWei Wang, Bei Yu, Jiaya Jia

To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video. This paper proposes an Action Conditional Temporal Variational AutoEncoder (ACT-VAE) to improve motion prediction accuracy and capture movement diversity. ACT-VAE predicts pose sequences for an action clips from a single input image. It is implemented as a deep generative model that maintains temporal coherence according to the action category with a novel temporal modeling on latent space. Further, ACT-VAE is a general action sequence prediction framework. When connected with a plug-and-play Pose-to-Image (P2I) network, ACT-VAE can synthesize image sequences. Extensive experiments bear out our approach can predict accurate pose and synthesize realistic image sequences, surpassing state-of-the-art approaches. Compared to existing methods, ACT-VAE improves model accuracy and preserves diversity.

📄 PDF Abstract BibTeX arXiv:2108.05658

Code (0)

등록된 구현이 없습니다.

Tasks

Diversitymotion predictionPredictionVideo Prediction

Similar Papers 제목 키워드 기반

S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction

2023-07-13 · Mohammad Adiban, Kalin Stefanov, Sabato Marco Siniscalchi, Giampiero Salvi

We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemp…

PredictionVideo Prediction

Probabilistic Video Generation using Holistic Attribute Control

2018-03-21 · ECCV 2018 9 · Jiawei He, Andreas Lehrmann, Joseph Marino, Greg Mori 외

Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), …

AttributeFuture predictionVideo Generation

Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior

2018-09-01 · ECCV 2018 9 · Sijia Cai, WangMeng Zuo, Larry S. Davis, Lei Zhang

Video summarization is a challenging under-constrained problem because the underlying summary of a single video strongly depends on users' subjective understandings. Data-driven approaches, such as deep neural networks, …

DecoderSaliency PredictionSupervised Video SummarizationVideo Summarization

HierCVAE: Hierarchical Attention-Driven Conditional Variational Autoencoders for Multi-Scale Temporal Modeling

2025-08-26 · Yao Wu arxiv

Temporal modeling in complex systems requires capturing dependencies across multiple time scales while managing inherent uncertainties. We propose HierCVAE, a novel architecture that integrates hierarchical attention mec…

Learning Conditional Variational Autoencoders with Missing Covariates

2022-03-02 · Siddharth Ramchandran, Gleb Tikhonov, Otto Lönnroth, Pekka Tiikkainen 외

Conditional variational autoencoders (CVAEs) are versatile deep generative models that extend the standard VAE framework by conditioning the generative model with auxiliary covariates. The original CVAE model assumes tha…

Missing ValuesVariational Inference