Quantitative behavioral measurements are important for answering questions across scientific disciplines—from neuroscience to ecology. State-of-the-art deep-learning methods …
W Li, Z Wang, B Yin, Q Peng, Y Du, T Xiao, G Yu… - arXiv preprint arXiv …, 2019 - arxiv.org
Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their …
G Moon, JY Chang, KM Lee - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Multi-person pose estimation from a 2D image is an essential technique for human behavior understanding. In this paper, we propose a human pose refinement network that estimates a …
Estimating 3D human pose from a single image is a challenging task. This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing an …
Multi-scale context module and single-stage encoder-decoder structure are commonly employed for semantic segmentation. The multi-scale context module refers to the …
Recent years have witnessed an unprecedented growing of sport videos, as different types of sports activities can be widely-observed (ie, from professional athletics to personal …
We present the first single-network approach for 2D whole-body pose estimation, which entails simultaneous localization of body, face, hands, and feet keypoints. Due to the bottom …
Z Zhang, J Tang, G Wu - arXiv preprint arXiv:1911.10346, 2019 - arxiv.org
Recent research on human pose estimation has achieved significant improvement. However, most existing methods tend to pursue higher scores using complex architecture or …
W Tang, Y Wu - Proceedings of the IEEE/CVF conference …, 2019 - openaccess.thecvf.com
Human pose estimation (HPE) is inherently a homogeneous multi-task learning problem, with the localization of each body part as a different task. Recent HPE approaches …