Pose Guided Global and Local GAN for Appearance Preserving Human Video Prediction

Tang, Jilin; Hu, Haoji; Zhou, Qiang; Shan, Hangguan; Tian, Chuan; Quek, Tony Q. S.

doi:10.1109/icip.2019.8803792

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, in the keypoint coordinate space, the seminal model of Minderer et al [89] qualitatively outperformed SVG [161], SAVP [159] and EPVA [53], yet pixel-wise metrics reported similar results. In the human pose space, and by regressing future frames from human pose predictions, Tang et al [160] outperformed SAVP [159],…”

Section: Results On the High-level Prediction Spacementioning

confidence: 99%

“…To enable multiple predictions, they have used additional inputs ensuring trajectory and behavior variability at a human pose level. To better preserve the visual appearance in the predictions than [54], [132], [159], Tang et al [160] firstly predict human poses using a LSTMbased model to then synthesize pose-conditioned future frames using a combination of different networks: a global GAN modeling the time-invariant background alongside a coarse human pose, a local GAN refining the coarsepredicted human pose, and a 3D-AE to ensure temporal consistency across frames.…”

Section: Other High-level Spacesmentioning

confidence: 99%

See 1 more Smart Citation

A Review on Deep Learning Techniques for Video Prediction

Oprea

Martinez-Gonzalez

García-García

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

177

View full text Add to dashboard Cite

The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising research direction. Defined as a self-supervised learning task, video prediction represents a suitable framework for representation learning, as it demonstrated potential capabilities for extracting meaningful representations of the underlying patterns in natural videos. Motivated by the increasing interest in this task, we provide a review on the deep learning methods for prediction in video sequences. We firstly define the video prediction fundamentals, as well as mandatory background concepts and the most used datasets. Next, we carefully analyze existing video prediction models organized according to a proposed taxonomy, highlighting their contributions and their significance in the field. The summary of the datasets and methods is accompanied with experimental results that facilitate the assessment of the state of the art on a quantitative basis. The paper is summarized by drawing some general conclusions, identifying open research challenges and by pointing out future research directions.

show abstract

Section: Results On the High-level Prediction Spacementioning

confidence: 99%

Section: Other High-level Spacesmentioning

confidence: 99%