Pose2Pose

Willett, Nora S.; Shin, Hijung Valentina; Jin, Zeyu; Li, Wilmot; Finkelstein, Adam

doi:10.1145/3377325.3377505

Cited by 25 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…V. APPLICATIONS HPE has been used in a variety of applications such as action analysis [1], HCI [2], gaming [3], sport analysis [4], [5], motion capture [6], computer-generated imagery [7], [8]. Accurate joint points are semantically informative and can be utilized in computer vision tasks like action recognition, and human tracking [99].…”

Section: Multimodal Learning In 3d Hpementioning

confidence: 99%

“…HPE-based performance-driven animations accomplish character motions by transferring motions from a human performer to an animated character, which is prevalent in the film and game industries conveniently and economically. For 2D animation applications, Willett et al [8] proposed a novel method to jointly yield 2D animation and 2D character creation by leveraging human pose. In addition, the HPE technique is helpful in augmented reality.…”

Section: Character Animationmentioning

confidence: 99%

“…• Top-down MPPE [52] + Motion Transfer [115] • Bottom-up MPPE [40] + Motion Transfer [8] Animation by HPE-based motion transferring from human performer to animated character Sports Analysis…”

Section: D Hpe Action Analysismentioning

confidence: 99%

“…Human Pose Estimation (HPE) refers to estimating the positions of human joints and their associations in images or videos, which is a popular research topic in computer vision. It has been widely applied to various applications, such as action analysis [1], HCI [2], gaming [3], sport analysis [4], [5], motion capture [6], computer-generated imagery [7], [8]. Although HPE has been studied for decades, it is still an open and challenging task since the two main aspects of the wide diversity of the human body (such as various human poses, various clothing, environment or illumination conditions) and reconstruction ambiguity caused by occlusions (particularly the crowd) [9], [10].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Vision-Based Human Pose Estimation via Deep Learning: A Survey

Lan

et al. 2023

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

Human Pose Estimation (HPE) has attracted a significant amount of attention from the computer vision community in the past decades. Moreover, HPE has been applied to various domains such as human-computer interaction, sports analysis, and human tracking via images and videos. Recently, deep learning-based approaches have shown state-of-the-art performance in HPE-based applications. Although deep learning-based approaches have achieved remarkable performance in HPE, a comprehensive review of deep learning-based HPE methods remains lacking in the literature. In this paper, we provide an up-to-date and in-depth overview of the deep learning approaches in vision-based HPE. We summarize these methods of 2D and 3D HPE, and their applications, discuss the challenges and the research trends through bibliometrics and provide insightful recommendations for future research. This article provides a meaningful overview as introductory material for beginners to deep learning-based HPE, as well as supplementary material for advanced researchers.

show abstract

Section: Multimodal Learning In 3d Hpementioning

confidence: 99%

Section: Character Animationmentioning

confidence: 99%

Section: D Hpe Action Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Vision-Based Human Pose Estimation via Deep Learning: A Survey

Lan

et al. 2023

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

show abstract

“…Most studies use pose-estimation algorithms to generate motion for 2D or 3D human characters, 24,37 while a few focus on extracting the pose of animated characters. Khungurn and Chou 38 used pose estimation on Anime and Manga characters, and work focuses on face detection in Manga.…”

Section: Data Availability Statementmentioning

confidence: 99%

Personality expression in cartoon animal characters using Sasang typology

Mailee,

Sonlu,

Güdükbay

2023

Computer Animation & Virtual

View full text Add to dashboard Cite

The movement style is an adequate descriptor of different personalities. While many studies investigate the relationship between apparent personality and high‐level motion qualities in humans, similar research for animal characters still needs to be done. The variety in animals' skeletal configurations and texture complicates their pose estimation process. Our affect analysis framework includes a workflow for pose extraction in animal characters and a parameterization of the high‐level animal motion descriptors inspired by Laban movement analysis. Using a data set of quadruped walk cycles, we prove the display of typologies in cartoon animal characters, reporting the point‐biserial correlation between our motion parameters and the Sasang categories that reflect different personalities.

show abstract

Deep learning-based for human segmentation and tracking, 3D human pose estimation and action recognition on monocular video of MADS dataset

Le¹

2022

Multimed Tools Appl

View full text Add to dashboard Cite

Pose2Pose

Cited by 25 publications

References 27 publications

Vision-Based Human Pose Estimation via Deep Learning: A Survey

Vision-Based Human Pose Estimation via Deep Learning: A Survey

Personality expression in cartoon animal characters using Sasang typology

Deep learning-based for human segmentation and tracking, 3D human pose estimation and action recognition on monocular video of MADS dataset

Contact Info

Product

Resources

About