Deep convolutional neural networks for efficient pose estimation in gesture videos
Our objective is to efficiently and accurately estimate the upper body pose of humans in gesture videos. To this end, we build on the recent successful applications of deep convolutional neural networks (ConvNets). Our novelties are: (i) our method is the first to our knowledge to use ConvNets for e...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2015
|
| _version_ | 1817931522255093760 |
|---|---|
| author | Pfister, T Simonyan, K Charles, J Zisserman, A |
| author_facet | Pfister, T Simonyan, K Charles, J Zisserman, A |
| author_sort | Pfister, T |
| collection | OXFORD |
| description | Our objective is to efficiently and accurately estimate the upper body pose of humans in gesture videos. To this end, we build on the recent successful applications of deep convolutional neural networks (ConvNets). Our novelties are: (i) our method is the first to our knowledge to use ConvNets for estimating human pose in videos; (ii) a new network that exploits temporal information from multiple frames, leading to better performance; (iii) showing that pre-segmenting the foreground of the video improves performance; and (iv) demonstrating that even without foreground segmentations, the network learns to abstract away from the background and can estimate the pose even in the presence of a complex, varying background. |
| first_indexed | 2024-12-09T03:23:21Z |
| format | Conference item |
| id | oxford-uuid:05ebcea8-1ba4-49a0-82fb-f37cfb75c6e3 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:23:21Z |
| publishDate | 2015 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:05ebcea8-1ba4-49a0-82fb-f37cfb75c6e32024-11-26T13:28:30ZDeep convolutional neural networks for efficient pose estimation in gesture videosConference itemhttp://purl.org/coar/resource_type/c_5794uuid:05ebcea8-1ba4-49a0-82fb-f37cfb75c6e3EnglishSymplectic ElementsSpringer2015Pfister, TSimonyan, KCharles, JZisserman, AOur objective is to efficiently and accurately estimate the upper body pose of humans in gesture videos. To this end, we build on the recent successful applications of deep convolutional neural networks (ConvNets). Our novelties are: (i) our method is the first to our knowledge to use ConvNets for estimating human pose in videos; (ii) a new network that exploits temporal information from multiple frames, leading to better performance; (iii) showing that pre-segmenting the foreground of the video improves performance; and (iv) demonstrating that even without foreground segmentations, the network learns to abstract away from the background and can estimate the pose even in the presence of a complex, varying background. |
| spellingShingle | Pfister, T Simonyan, K Charles, J Zisserman, A Deep convolutional neural networks for efficient pose estimation in gesture videos |
| title | Deep convolutional neural networks for efficient pose estimation in gesture videos |
| title_full | Deep convolutional neural networks for efficient pose estimation in gesture videos |
| title_fullStr | Deep convolutional neural networks for efficient pose estimation in gesture videos |
| title_full_unstemmed | Deep convolutional neural networks for efficient pose estimation in gesture videos |
| title_short | Deep convolutional neural networks for efficient pose estimation in gesture videos |
| title_sort | deep convolutional neural networks for efficient pose estimation in gesture videos |
| work_keys_str_mv | AT pfistert deepconvolutionalneuralnetworksforefficientposeestimationingesturevideos AT simonyank deepconvolutionalneuralnetworksforefficientposeestimationingesturevideos AT charlesj deepconvolutionalneuralnetworksforefficientposeestimationingesturevideos AT zissermana deepconvolutionalneuralnetworksforefficientposeestimationingesturevideos |