Fully-convolutional Siamese networks for object tracking
The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object’s appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they c...
| Główni autorzy: | , , , , |
|---|---|
| Format: | Conference item |
| Język: | English |
| Wydane: |
Springer Verlag
2016
|
| _version_ | 1826298075083177984 |
|---|---|
| author | Bertinetto, L Valmadre, J Henriques, JF Vedaldi, A Torr, PHS |
| author_facet | Bertinetto, L Valmadre, J Henriques, JF Vedaldi, A Torr, PHS |
| author_sort | Bertinetto, L |
| collection | OXFORD |
| description | The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object’s appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they can learn. Recently, several attempts have been made to exploit the expressive power of deep convolutional networks. However, when the object to track is not known beforehand, it is necessary to perform Stochastic Gradient Descent online to adapt the weights of the network, severely compromising the speed of the system. In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks. |
| first_indexed | 2024-03-07T04:41:17Z |
| format | Conference item |
| id | oxford-uuid:d1bd82ef-ec46-4714-b78a-7dc66e9cdc8e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T04:41:17Z |
| publishDate | 2016 |
| publisher | Springer Verlag |
| record_format | dspace |
| spelling | oxford-uuid:d1bd82ef-ec46-4714-b78a-7dc66e9cdc8e2022-03-27T07:59:02ZFully-convolutional Siamese networks for object trackingConference itemhttp://purl.org/coar/resource_type/c_5794uuid:d1bd82ef-ec46-4714-b78a-7dc66e9cdc8eEnglishSymplectic Elements at OxfordSpringer Verlag2016Bertinetto, LValmadre, JHenriques, JFVedaldi, ATorr, PHSThe problem of arbitrary object tracking has traditionally been tackled by learning a model of the object’s appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they can learn. Recently, several attempts have been made to exploit the expressive power of deep convolutional networks. However, when the object to track is not known beforehand, it is necessary to perform Stochastic Gradient Descent online to adapt the weights of the network, severely compromising the speed of the system. In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks. |
| spellingShingle | Bertinetto, L Valmadre, J Henriques, JF Vedaldi, A Torr, PHS Fully-convolutional Siamese networks for object tracking |
| title | Fully-convolutional Siamese networks for object tracking |
| title_full | Fully-convolutional Siamese networks for object tracking |
| title_fullStr | Fully-convolutional Siamese networks for object tracking |
| title_full_unstemmed | Fully-convolutional Siamese networks for object tracking |
| title_short | Fully-convolutional Siamese networks for object tracking |
| title_sort | fully convolutional siamese networks for object tracking |
| work_keys_str_mv | AT bertinettol fullyconvolutionalsiamesenetworksforobjecttracking AT valmadrej fullyconvolutionalsiamesenetworksforobjecttracking AT henriquesjf fullyconvolutionalsiamesenetworksforobjecttracking AT vedaldia fullyconvolutionalsiamesenetworksforobjecttracking AT torrphs fullyconvolutionalsiamesenetworksforobjecttracking |