Share your thoughts, 1 month free Claude Pro on usSee more

Multi-Person Pose Estimation on MPII (full test)

92.2Head Joint Accuracy

GPN

Updated 1mo ago

Evaluation Results

Method
GPN 2017.05	92.2	89.7	82.1	74.4	78.6	76.4	69.3	80.4	-
Associative Embedding (Our method) 2016.11	92.1	89.3	78.9	69.8	76.2	71.6	64.7	77.5	-
Newell and Deng 2017.05	92.1	89.3	78.9	69.8	76.2	71.6	64.7	77.5	-
Newell & Deng 2016.12	92.1	89.3	78.9	69.8	76.2	71.6	64.7	77.5	-
Newell and Deng 2019.08	92.1	89.3	78.9	69.8	76.2	71.6	64.7	77.5	-
Fieraru et al. 2019.08	91.8	89.5	80.4	69.6	77.3	71.7	65.5	78	-
BU-full 2016.12	91.5	87.8	74.6	62.5	72.2	65.3	56.7	72.9	0.12
RMPE++ 2016.12	91.3	90.5	84	76.4	80.3	79.9	72.4	82.1	-
Part Affinity Fields 2016.11	91.2	87.6	77.7	66.8	75.4	68.9	61.7	75.6	-
Cao et al. 2016.11	91.2	87.6	77.7	66.8	75.4	68.9	61.7	75.6	-
Cao et al. 2017.05	91.2	87.6	77.7	66.8	75.4	68.9	61.7	75.6	-
Cao et al. 2016.12	91.2	87.6	77.7	66.8	75.4	68.9	61.7	75.6	-
Cao et al. 2019.08	91.2	87.6	77.7	66.8	75.4	68.9	61.7	75.6	-
Levinkov et al. 2016.11	89.8	85.2	71.8	59.6	71.1	63	53.5	70.6	-
Levinkov et al. 2017.05	89.8	85.2	71.8	59.6	71.1	63	53.5	70.6	-
Levinkov et al. 2016.12	89.8	85.2	71.8	59.6	71.1	63	53.5	70.6	-
Levinkov et al. 2019.08	89.8	85.2	71.8	59.6	71.1	63	53.5	70.6	-
SPM 2019.08	89.7	87.4	80.4	72.4	76.7	74.9	68.3	78.5	-
DeeperCut 2016.05	89.4	84.5	70.4	59.3	68.9	62.7	54.6	70	485
DeeperCut 2016.12	89.4	84.5	70.4	59.3	68.9	62.7	54.6	70	485
Insafutdinov et al. [45] 2016.11	89.4	84.5	70.4	59.3	68.9	62.7	54.6	70	-
Part Affinity Fields 2016.11	89	84.9	74.9	64.2	71	65.6	58.1	72.5	-
TD/BU+ SP 2016.12	88.8	87	75.9	64.9	74.2	68.8	60.5	74.3	0.005
Insafutdinov et al. [27] 2016.11	88.8	87	75.9	64.9	74.2	68.8	60.5	74.3	-
Insafutdinov et al. 2017.05	88.8	87	75.9	64.9	74.2	68.8	60.5	74.3	-
Insafutdinov et al. 2016.12	88.8	87	75.9	64.9	74.2	68.8	60.5	74.3	-
Insafutdinov et al. [15] 2019.08	88.8	87	75.9	64.9	74.2	68.8	60.5	74.3	-
Fang et al. 2016.11	88.4	86.5	78.6	70.4	74.4	73	65.8	76.7	-
Fang et al. 2017.05	88.4	86.5	78.6	70.4	74.4	73	65.8	76.7	-
RMPE 2016.12	88.4	86.5	78.6	70.4	74.4	73	65.8	76.7	-
Fang et al. 2019.08	88.4	86.5	78.6	70.4	74.4	73	65.8	76.7	-
DeeperCut 2016.05	79.1	72.2	59.7	50	56	51	44.6	59.4	485
DeeperCut 2016.12	79.1	72.2	59.7	50	56	51	44.6	59.4	485
DeeperCut 2016.11	78.4	72.5	60.2	51	57.2	52	45.4	59.5	-
Insafutdinov et al. [28] 2016.11	78.4	72.5	60.2	51	57.2	52	45.4	59.5	-
Insafutdinov et al. 2017.05	78.4	72.5	60.2	51	57.2	52	45.4	59.5	-
DeeperCut 2016.12	78.4	72.5	60.2	51	57.2	52	45.4	59.5	-
Insafutdinov et al. [16] 2019.08	78.4	72.5	60.2	51	57.2	52	45.4	59.5	-
Faster R-CNN + unary 2016.05	75.1	73.6	62.7	51	61.1	52.6	42.2	59.7	1
DeeperCut 2016.05	73.7	65.4	54.9	45.2	52.3	47.8	40.7	54.7	2,785
Faster R-CNN + unary 2016.05	64.9	62.9	53.4	44.1	50.7	43.1	35.2	51	1
Iqbal et al. 2016.11	58.4	53.9	44.5	35	42.2	36.7	31.1	43.1	-
Iqbal&Gall 2016.12	58.4	53.9	44.5	35	42.2	36.7	31.1	43.1	10
Iqbal & Gall 2016.11	58.4	53.9	44.5	35	42.2	36.7	31.1	43.1	-
Iqbal and Gall 2017.05	58.4	53.9	44.5	35	42.2	36.7	31.1	43.1	-
Iqbal & Gall 2016.12	58.4	53.9	44.5	35	42.2	36.7	31.1	43.1	-
Iqbal and Gall 2019.08	58.4	53.9	44.5	35	42.2	36.7	31.1	43.1	-