Harvesting Multiple Views for Marker-Less 3D Human Pose Annotations
Citations
593 citations
546 citations
Cites background from "Harvesting Multiple Views for Marke..."
..., [12, 31, 4, 11]), it is interesting to note that the representation of 3D human pose in a discretized 3D space has also been previously adopted in multi-view settings [7, 15, 23], where it was used to accommodate predictions from different viewpoints....
[...]
218 citations
216 citations
Cites background or methods from "Harvesting Multiple Views for Marke..."
...6M Protocol 1 Protocol 2 Year Method Use extra 3D data MPJPE ↓ Normalized MPJPE ↓ PMPJPE ↓ 2017 [197] No 56....
[...]
...A group of methods [197] [198] [199] [200] [201] used body models to tackle the association problem by optimizing model parameters to match the model projection with the 2D pose....
[...]
213 citations
References
123,388 citations
3,865 citations
"Harvesting Multiple Views for Marke..." refers background or methods in this paper
...Given a set of images captured with a calibrated multi-view setup, a generic ConvNet for 2D human pose [27] pro-...
[...]
...ConvNets have had a tremendous impact on the task of 2D human pose estimation [40, 41, 27]....
[...]
...For the generic 2D pose ConvNet, we use a publicly available model [27], which is trained on the MPII human pose dataset [2]....
[...]
...[27] built upon previous work to identify the best practices for human pose prediction and propose an hourglass module consisting of ResNet components [19], and iterative processing to achieve state-of-the-art performance on standard benchmarks [2, 36]....
[...]
...Here, we adopt the state-of-theart stacked hourglass design [27]....
[...]
2,687 citations
2,612 citations
"Harvesting Multiple Views for Marke..." refers background or methods in this paper
...ConvNets have had a tremendous impact on the task of 2D human pose estimation [40, 41, 27]....
[...]
...The initial work of Toshev and Szegedy [40] regressed directly the x, y coordinates of the joints using a cascade of ConvNets....
[...]
2,514 citations
"Harvesting Multiple Views for Marke..." refers background or methods in this paper
...The marginal distribution of the discrete variables is efficiently computed by the sum-product algorithm [15]....
[...]
...Multi-view 3D human pose: Several approaches [6, 1, 9, 22, 4, 5] have extended the pictorial structures model [16, 15] to reason about 3D human pose taken from multiple (calibrated) viewpoints....
[...]
...The heatmaps in each view are backprojected to a common discretized 3D space, functioning as unary potentials of a 3D pictorial structure [16, 15], while a tree graph models the pairwise relations between joints....
[...]