Occlusion-Aware Networks for 3D Human Pose Estimation in Video

Cheng, Yu; Yang, Bo; Wang, Bo; Yan, Wending; Tan, Robby T.

doi:10.1109/iccv.2019.00081

Cited by 198 publications

(146 citation statements)

References 39 publications

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…3 and MPI-3DHP (Tab. 4) but, interestingly, semi-supervised approaches [17,16] are the most successful on the HumanEva dataset (Tab. 5).…”

Section: Discussionmentioning

confidence: 99%

“…Large high-quality 3D human pose estimation datasets are crucial for the success of deep learning models. The precise 3D annotations of human body joints serve as a direct supervision for models to learn how to detect the joints and resolve 2D-to-3D elevation ambiguities [30,59,17,42,25,16]. However, acquiring 3D data in the real world is challenging and is done in specially designed studios [31] and indoor environments, using wearable IMU sensors [70].…”

Section: Datasetsmentioning

confidence: 99%

“…Occlusion problem is tackled in the occlussion-aware-network approach [16]. The model generates 2D confidence heatmaps to detect the unreliable, occluded joints.…”

Section: Deep Learningmentioning

confidence: 99%

See 2 more Smart Citations

A Review of 3D Human Pose Estimation from 2D Images

Bartol¹,

Bojanic²,

Petković³

et al. 2020

Proceedings of 3DBODY.TECH 2020 - 11th International Conference and Exhibition on 3D Body Scanning and Processing Technologies,

View full text Add to dashboard Cite

Human pose estimation task takes images as input and extracts a set of locations representing the predefined body joints and the sparse connections between the joints, called the body parts. A pose can be estimated from single or multiple frames, in a single (monocular) or multi-view (stereo) setup and for a single person or multiple people in the scene. In this work, we provide an overview of the classic and deep learning-based 3D pose estimation approaches. We also point out relevant evaluation metrics, pose parametrizations, body models, and 3D human pose datasets. Finally, we review stateof-the-art pose estimation results, briefly discuss open problems, and propose possible future research directions.

show abstract

“…3 and MPI-3DHP (Tab. 4) but, interestingly, semi-supervised approaches [17,16] are the most successful on the HumanEva dataset (Tab. 5).…”

Section: Discussionmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

A Review of 3D Human Pose Estimation from 2D Images

Bartol¹,

Bojanic²,

Petković³

et al. 2020

Proceedings of 3DBODY.TECH 2020 - 11th International Conference and Exhibition on 3D Body Scanning and Processing Technologies,

View full text Add to dashboard Cite

show abstract

“…As previously illustrated, multi-person human pose estimation (Cheng, Yang, Wang, Yan, & Tan, 2019;Y. He, Yan, Fragkiadaki, & Yu, 2020;Iskakov, Burkov, Lempitsky, & Malkov, 2019;Lassner et al, 2017;Pavlakos et al, 2019;Pavlakos, Zhou, Derpanis, & Daniilidis, 2017;Pavllo, Feichtenhofer, Grangier, & Auli, 2019) is a central part of vision-based analysis of football video.…”

Section: Appendix a Additional Work Related To Statistical Learning In Footballmentioning

confidence: 99%

Game Plan: What AI can do for Football, and What Football can do for AI

Tuyls

Omidshafiei²,

Müller³

et al. 2021

jair

View full text Add to dashboard Cite

The rapid progress in artificial intelligence (AI) and machine learning has opened unprecedented analytics possibilities in various team and individual sports, including baseball, basketball, and tennis. More recently, AI techniques have been applied to football, due to a huge increase in data collection by professional teams, increased computational power, and advances in machine learning, with the goal of better addressing new scientific challenges involved in the analysis of both individual players’ and coordinated teams’ behaviors. The research challenges associated with predictive and prescriptive football analytics require new developments and progress at the intersection of statistical learning, game theory, and computer vision. In this paper, we provide an overarching perspective highlighting how the combination of these fields, in particular, forms a unique microcosm for AI research, while offering mutual benefits for professional teams, spectators, and broadcasters in the years to come. We illustrate that this duality makes football analytics a game changer of tremendous value, in terms of not only changing the game of football itself, but also in terms of what this domain can mean for the field of AI. We review the state-of-the-art and exemplify the types of analysis enabled by combining the aforementioned fields, including illustrative examples of counterfactual analysis using predictive models, and the combination of game-theoretic analysis of penalty kicks with statistical learning of player attributes. We conclude by highlighting envisioned downstream impacts, including possibilities for extensions to other sports (real and virtual).

show abstract

“…It was trained in a weakly supervised manner without 2D to 3D correspondences and camera parameters. Cheng et al [134] proposed a method to handle occlusion by filtering out unreliable estimates of occluded keypoints when training their 2D and 3D temporal convolutional networks.…”

Section: Human Pose Estimationmentioning

confidence: 99%

VR content creation and exploration with deep learning: A survey

Wang

Lyu

et al. 2020

Comp. Visual Media

View full text Add to dashboard Cite

Virtual reality (VR) offers an artificial, computer generated simulation of a real life environment. It originated in the 1960s and has evolved to provide increasing immersion, interactivity, imagination, and intelligence. Because deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion, they can build very powerful models which leverage large quantities of visual media data. Intelligence of VR methods and applications has been significantly boosted by the recent developments in deep learning techniques. VR content creation and exploration relates to image and video analysis, synthesis and editing, so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed, designed specifically to handle panoramic images and video and virtual 3D scenes. This article surveys recent research that uses such deep learning methods for VR content creation and exploration. It considers the problems involved, and discusses possible future directions in this active and emerging research area. Keywords virtual reality; deep learning; neural networks; 360 • image and video virtual content

show abstract

Occlusion-Aware Networks for 3D Human Pose Estimation in Video

Cited by 198 publications

References 39 publications

A Review of 3D Human Pose Estimation from 2D Images

A Review of 3D Human Pose Estimation from 2D Images

Game Plan: What AI can do for Football, and What Football can do for AI

VR content creation and exploration with deep learning: A survey

Contact Info

Product

Resources

About