Sign language recognition: A deep survey

R Rastgoo, K Kiani, S Escalera - Expert Systems with Applications, 2021 - Elsevier
Sign language, as a different form of the communication language, is important to large
groups of people in society. There are different signs in each sign language with variability …

Recovering 3d human mesh from monocular images: A survey

Y Tian, H Zhang, Y Liu, L Wang - IEEE transactions on pattern …, 2023 - ieeexplore.ieee.org
Estimating human pose and shape from monocular images is a long-standing problem in
computer vision. Since the release of statistical body models, 3D human mesh recovery has …

Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives

K Grauman, A Westbury, L Torresani… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract We present Ego-Exo4D a diverse large-scale multimodal multiview video dataset
and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric …

Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis

J Luiten, G Kopanas, B Leibe, D Ramanan - arxiv preprint arxiv …, 2023 - arxiv.org
We present a method that simultaneously addresses the tasks of dynamic scene novel-view
synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We …

Fake it till you make it: face analysis in the wild using synthetic data alone

E Wood, T Baltrušaitis, C Hewitt… - Proceedings of the …, 2021 - openaccess.thecvf.com
We demonstrate that it is possible to perform face-related computer vision in the wild using
synthetic data alone. The community has long enjoyed the benefits of synthesizing training …

Mediapipe hands: On-device real-time hand tracking

F Zhang, V Bazarevsky, A Vakunov… - arxiv preprint arxiv …, 2020 - arxiv.org
We present a real-time on-device hand tracking pipeline that predicts hand skeleton from
single RGB camera for AR/VR applications. The pipeline consists of two models: 1) a palm …

Probabilistic regression for visual tracking

M Danelljan, LV Gool, R Timofte - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Visual tracking is fundamentally the problem of regressing the state of the target in each
video frame. While significant progress has been achieved, trackers are still prone to failures …

Frankmocap: A monocular 3d whole-body pose estimation system via regression and integration

Y Rong, T Shiratori, H Joo - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Most existing monocular 3D pose estimation approaches only focus on a single body part,
neglecting the fact that the essential nuance of human motion is conveyed through a concert …

Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis

J Luiten, G Kopanas, B Leibe… - … Conference on 3D …, 2024 - ieeexplore.ieee.org
We present a method that simultaneously addresses the tasks of dynamic scene novel-view
synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We …

Learning to reconstruct 3D human pose and shape via model-fitting in the loop

N Kolotouros, G Pavlakos, MJ Black… - Proceedings of the …, 2019 - openaccess.thecvf.com
Abstract Model-based human pose estimation is currently approached through two different
paradigms. Optimization-based methods fit a parametric body model to 2D observations in …