Personalizing human video pose estimation
<p>We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person’s appearance to improve pose estimation in long videos</p> <br/> <p>We make the following contributions: (i) we show that given a few high-precision pose annotat...
| Asıl Yazarlar: | , , , , |
|---|---|
| Materyal Türü: | Conference item |
| Baskı/Yayın Bilgisi: |
Institute of Electrical and Electronics Engineers
2016
|
| _version_ | 1826257262465777664 |
|---|---|
| author | Charles, J Pfister, T Maggee, D Hogg, D Zisserman, A |
| author_facet | Charles, J Pfister, T Maggee, D Hogg, D Zisserman, A |
| author_sort | Charles, J |
| collection | OXFORD |
| description | <p>We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person’s appearance to improve pose estimation in long videos</p> <br/> <p>We make the following contributions: (i) we show that given a few high-precision pose annotations, e.g. from a generic ConvNet pose estimator, additional annotations can be generated throughout the video using a combination of image-based matching for temporally distant frames, and dense optical flow for temporally local frames; (ii) we develop an occlusion aware self-evaluation model that is able to automatically select the high-quality and reject the erroneous additional annotations; and (iii) we demonstrate that these high-quality annotations can be used to fine-tune a ConvNet pose estimator and thereby personalize it to lock on to key discriminative features of the person’s appearance. The outcome is a substantial improvement in the pose estimates for the target video using the personalized ConvNet compared to the original generic ConvNet.</p> <br/> <p>Our method outperforms the state of the art (including top ConvNet methods) by a large margin on three standard benchmarks, as well as on a new challenging YouTube video dataset. Furthermore, we show that training from the automatically generated annotations can be used to improve the performance of a generic ConvNet on other benchmarks.</p> |
| first_indexed | 2024-03-06T18:15:23Z |
| format | Conference item |
| id | oxford-uuid:046eef2e-1918-4bb7-ac4e-3bda9ee7f90e |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:15:23Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:046eef2e-1918-4bb7-ac4e-3bda9ee7f90e2022-03-26T08:51:48ZPersonalizing human video pose estimationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:046eef2e-1918-4bb7-ac4e-3bda9ee7f90eSymplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2016Charles, JPfister, TMaggee, DHogg, DZisserman, A<p>We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person’s appearance to improve pose estimation in long videos</p> <br/> <p>We make the following contributions: (i) we show that given a few high-precision pose annotations, e.g. from a generic ConvNet pose estimator, additional annotations can be generated throughout the video using a combination of image-based matching for temporally distant frames, and dense optical flow for temporally local frames; (ii) we develop an occlusion aware self-evaluation model that is able to automatically select the high-quality and reject the erroneous additional annotations; and (iii) we demonstrate that these high-quality annotations can be used to fine-tune a ConvNet pose estimator and thereby personalize it to lock on to key discriminative features of the person’s appearance. The outcome is a substantial improvement in the pose estimates for the target video using the personalized ConvNet compared to the original generic ConvNet.</p> <br/> <p>Our method outperforms the state of the art (including top ConvNet methods) by a large margin on three standard benchmarks, as well as on a new challenging YouTube video dataset. Furthermore, we show that training from the automatically generated annotations can be used to improve the performance of a generic ConvNet on other benchmarks.</p> |
| spellingShingle | Charles, J Pfister, T Maggee, D Hogg, D Zisserman, A Personalizing human video pose estimation |
| title | Personalizing human video pose estimation |
| title_full | Personalizing human video pose estimation |
| title_fullStr | Personalizing human video pose estimation |
| title_full_unstemmed | Personalizing human video pose estimation |
| title_short | Personalizing human video pose estimation |
| title_sort | personalizing human video pose estimation |
| work_keys_str_mv | AT charlesj personalizinghumanvideoposeestimation AT pfistert personalizinghumanvideoposeestimation AT maggeed personalizinghumanvideoposeestimation AT hoggd personalizinghumanvideoposeestimation AT zissermana personalizinghumanvideoposeestimation |