Object tracking via online metric learning
By considering visual tracking as a similarity matching problem, we propose a self-supervised tracking method that incorporates adaptive metric learning and semi-supervised learning into the framework of object tracking. For object representation, the spatial-pyramid structure is applied by fusing b...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/101770 http://hdl.handle.net/10220/12979 |
| _version_ | 1826127778709241856 |
|---|---|
| author | Cong, Yang Yuan, Junsong Tang, Yandong |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Cong, Yang Yuan, Junsong Tang, Yandong |
| author_sort | Cong, Yang |
| collection | NTU |
| description | By considering visual tracking as a similarity matching problem, we propose a self-supervised tracking method that incorporates adaptive metric learning and semi-supervised learning into the framework of object tracking. For object representation, the spatial-pyramid structure is applied by fusing both the shape and texture cues as descriptors. A metric learner is adaptively trained online to best distinguish the foreground object and background, and a new bi-linear graph is defined accordingly to propagate the label of each sample. Then high-confident samples are collected to self-update the model to handle large-scale issue. Experiments on the benchmark dataset and comparisons with the state-of-the-art methods validate the advantages of our algorithm. |
| first_indexed | 2024-10-01T07:14:25Z |
| format | Conference Paper |
| id | ntu-10356/101770 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:14:25Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/1017702020-03-07T13:24:50Z Object tracking via online metric learning Cong, Yang Yuan, Junsong Tang, Yandong School of Electrical and Electronic Engineering IEEE International Conference on Image Processing (19th : 2012 : Orlando, Florida, US) DRNTU::Engineering::Electrical and electronic engineering By considering visual tracking as a similarity matching problem, we propose a self-supervised tracking method that incorporates adaptive metric learning and semi-supervised learning into the framework of object tracking. For object representation, the spatial-pyramid structure is applied by fusing both the shape and texture cues as descriptors. A metric learner is adaptively trained online to best distinguish the foreground object and background, and a new bi-linear graph is defined accordingly to propagate the label of each sample. Then high-confident samples are collected to self-update the model to handle large-scale issue. Experiments on the benchmark dataset and comparisons with the state-of-the-art methods validate the advantages of our algorithm. 2013-08-05T03:21:07Z 2019-12-06T20:44:21Z 2013-08-05T03:21:07Z 2019-12-06T20:44:21Z 2012 2012 Conference Paper https://hdl.handle.net/10356/101770 http://hdl.handle.net/10220/12979 10.1109/ICIP.2012.6466884 en |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Cong, Yang Yuan, Junsong Tang, Yandong Object tracking via online metric learning |
| title | Object tracking via online metric learning |
| title_full | Object tracking via online metric learning |
| title_fullStr | Object tracking via online metric learning |
| title_full_unstemmed | Object tracking via online metric learning |
| title_short | Object tracking via online metric learning |
| title_sort | object tracking via online metric learning |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/101770 http://hdl.handle.net/10220/12979 |
| work_keys_str_mv | AT congyang objecttrackingviaonlinemetriclearning AT yuanjunsong objecttrackingviaonlinemetriclearning AT tangyandong objecttrackingviaonlinemetriclearning |