Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Citations
[...]
14,299 citations
Cites background or methods from "Realtime Multi-Person 2D Pose Estim..."
...9 points higher than the COCO 2016 keypoint detection winner [4] that uses a multi-stage processing pipeline (see caption of Table 4)....
[...]
...CMUPose+++ [4] is the 2016 competition winner that uses multi-scale testing, post-processing with CPM [33], and filtering with an object detector, adding a cumulative ∼5 points (clarified in personal communication)....
[...]
...APkp AP 50 AP kp 75 AP kp M AP kp L CMU-Pose+++ [4] 61....
[...]
..., modeling structures [4]) will be complementary to our simple approach, but it is beyond the scope of this paper....
[...]
[...]
11,343 citations
Cites background or methods from "Realtime Multi-Person 2D Pose Estim..."
...9 points higher than the COCO 2016 keypoint detection winner [6] that uses a multi-stage processing pipeline (see caption of Table 4)....
[...]
...CMU-Pose+++ [6] is the 2016 competition winner that uses multi-scale testing, post-processing with CPM [44], and filtering with an object detector, adding a cumulative ∼5 points (clarified in personal communication)....
[...]
...APkp AP 50 AP kp 75 AP kp M AP kp L CMU-Pose+++ [6] 61....
[...]
..., modeling structures [6]) will be complementary to our simple approach....
[...]
3,097 citations
2,979 citations
Cites background from "Realtime Multi-Person 2D Pose Estim..."
...This paper is interested in single-person pose estimation, which is the basis of other related problems, such as multiperson pose estimation [6, 26, 32, 38, 46, 55, 40, 45, 17, 69],...
[...]
2,681 citations
References
123,388 citations
55,235 citations
"Realtime Multi-Person 2D Pose Estim..." refers methods in this paper
...The image is analyzed by a CNN (initialized by the first 10 layers of VGG-19 [53] and fine-tuned), generating a set of feature maps F that is input to the first stage....
[...]
...During training, we initialize the 10 layers from the VGG-19 [32]....
[...]
49,914 citations
30,462 citations
"Realtime Multi-Person 2D Pose Estim..." refers background or methods in this paper
...knees, hips, shoulders, elbows, wrists, necks, torsos, and head tops, while COCO [67] also includes some facial keypoints....
[...]
...The MSCOCO evaluation defines the object keypoint similarity (OKS) and uses the mean average precision (AP) over 10 OKS thresholds as main competition metric [1]....
[...]
...dataset [66], which consists of 3844 training and 1758 testing groups of multiple interacting individuals in highly articulated poses with 14 body parts; (2) COCO keypoint challenge dataset [67], which requires simultaneously detecting people and localizing 17 keypoints (body parts) in each person (including 12 human body parts and 5 facial keypoints); (3) our foot dataset, which is a subset of 15K annotations out of the COCO keypoint dataset....
[...]
...Existing human pose datasets ([66], [67]) contain limited body part types....
[...]
...We report results on the inaugural MSCOCO 2016 challenge where our approach sets the state-of-the-art, and in the MPII multiperson benchmark, where we significantly exceed the previous state-of-the-art result....
[...]
28,888 citations
"Realtime Multi-Person 2D Pose Estim..." refers methods in this paper
...The library also includes 3D keypoint pose detection, by performing 3D triangulation with non-linear Levenberg-Marquardt refinement [64] over the results of multiple synchronized camera views....
[...]