Stacked Hourglass Networks for Human Pose Estimation

Stacked Hourglass Networks for Human Pose Estimation. Newell, A., Yang, K., & Deng, J. arXiv:1603.06937 [cs], July, 2016. arXiv: 1603.06937

Paper abstract bibtex

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a ﬁnal set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

@article{newell_stacked_2016,
	title = {Stacked {Hourglass} {Networks} for {Human} {Pose} {Estimation}},
	url = {http://arxiv.org/abs/1603.06937},
	abstract = {This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a ﬁnal set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.},
	language = {en},
	urldate = {2022-01-19},
	journal = {arXiv:1603.06937 [cs]},
	author = {Newell, Alejandro and Yang, Kaiyu and Deng, Jia},
	month = jul,
	year = {2016},
	note = {arXiv: 1603.06937},
	keywords = {/unread, Computer Science - Computer Vision and Pattern Recognition, ⛔ No DOI found},
}

Downloads: 0

{"_id":"iHNhnYcMuuDnNQT87","bibbaseid":"newell-yang-deng-stackedhourglassnetworksforhumanposeestimation-2016","downloads":0,"creationDate":"2017-04-24T18:33:15.086Z","title":"Stacked Hourglass Networks for Human Pose Estimation","author_short":["Newell, A.","Yang, K.","Deng, J."],"year":2016,"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","bibdata":{"bibtype":"article","type":"article","title":"Stacked Hourglass Networks for Human Pose Estimation","url":"http://arxiv.org/abs/1603.06937","abstract":"This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a ﬁnal set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.","language":"en","urldate":"2022-01-19","journal":"arXiv:1603.06937 [cs]","author":[{"propositions":[],"lastnames":["Newell"],"firstnames":["Alejandro"],"suffixes":[]},{"propositions":[],"lastnames":["Yang"],"firstnames":["Kaiyu"],"suffixes":[]},{"propositions":[],"lastnames":["Deng"],"firstnames":["Jia"],"suffixes":[]}],"month":"July","year":"2016","note":"arXiv: 1603.06937","keywords":"/unread, Computer Science - Computer Vision and Pattern Recognition, ⛔ No DOI found","bibtex":"@article{newell_stacked_2016,\n\ttitle = {Stacked {Hourglass} {Networks} for {Human} {Pose} {Estimation}},\n\turl = {http://arxiv.org/abs/1603.06937},\n\tabstract = {This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a ﬁnal set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.},\n\tlanguage = {en},\n\turldate = {2022-01-19},\n\tjournal = {arXiv:1603.06937 [cs]},\n\tauthor = {Newell, Alejandro and Yang, Kaiyu and Deng, Jia},\n\tmonth = jul,\n\tyear = {2016},\n\tnote = {arXiv: 1603.06937},\n\tkeywords = {/unread, Computer Science - Computer Vision and Pattern Recognition, ⛔ No DOI found},\n}\n\n","author_short":["Newell, A.","Yang, K.","Deng, J."],"key":"newell_stacked_2016","id":"newell_stacked_2016","bibbaseid":"newell-yang-deng-stackedhourglassnetworksforhumanposeestimation-2016","role":"author","urls":{"Paper":"http://arxiv.org/abs/1603.06937"},"keyword":["/unread","Computer Science - Computer Vision and Pattern Recognition","⛔ No DOI found"],"metadata":{"authorlinks":{}},"html":""},"search_terms":["stacked","hourglass","networks","human","pose","estimation","newell","yang","deng"],"keywords":["/unread","computer science - computer vision and pattern recognition","⛔ no doi found"],"authorIDs":[],"dataSources":["9cexBw6hrwgyZphZZ","aXmRAq63YsH7a3ufx","CmHEoydhafhbkXXt5"]}