Action search by example using randomized visual vocabularies
Because actions can be small video objects, it is a challenging problem to search for similar actions in crowded and dynamic scenes when a single query example is provided. We propose a fast action search method that can efficiently locate similar actions spatiotemporally. Both the query action and...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/100686 http://hdl.handle.net/10220/17968 |
| _version_ | 1826126632654471168 |
|---|---|
| author | Yuan, Junsong Liu, Zicheng Yu, Gang |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Yuan, Junsong Liu, Zicheng Yu, Gang |
| author_sort | Yuan, Junsong |
| collection | NTU |
| description | Because actions can be small video objects, it is a challenging problem to search for similar actions in crowded and dynamic scenes when a single query example is provided. We propose a fast action search method that can efficiently locate similar actions spatiotemporally. Both the query action and the video datasets are characterized by spatio-temporal interest points. Instead of using a unified visual vocabulary to index all interest points in the database, we propose randomized visual vocabularies to enable fast and robust interest point matching. To accelerate action localization, we have developed a coarse-to-fine video subvolume search scheme, which is several orders of magnitude faster than the existing spatio-temporal branch and bound search. Our experiments on cross-dataset action search show promising results when compared with the state of the arts. Additional experiments on a 5-h versatile video dataset validate the efficiency of our method, where an action search can be finished in just 37.6 s on a regular desktop machine. |
| first_indexed | 2024-10-01T06:55:31Z |
| format | Journal Article |
| id | ntu-10356/100686 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:55:31Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/1006862020-03-07T14:00:31Z Action search by example using randomized visual vocabularies Yuan, Junsong Liu, Zicheng Yu, Gang School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Because actions can be small video objects, it is a challenging problem to search for similar actions in crowded and dynamic scenes when a single query example is provided. We propose a fast action search method that can efficiently locate similar actions spatiotemporally. Both the query action and the video datasets are characterized by spatio-temporal interest points. Instead of using a unified visual vocabulary to index all interest points in the database, we propose randomized visual vocabularies to enable fast and robust interest point matching. To accelerate action localization, we have developed a coarse-to-fine video subvolume search scheme, which is several orders of magnitude faster than the existing spatio-temporal branch and bound search. Our experiments on cross-dataset action search show promising results when compared with the state of the arts. Additional experiments on a 5-h versatile video dataset validate the efficiency of our method, where an action search can be finished in just 37.6 s on a regular desktop machine. Accepted version 2013-12-02T07:24:59Z 2019-12-06T20:26:38Z 2013-12-02T07:24:59Z 2019-12-06T20:26:38Z 2013 2013 Journal Article Yu, G., Yuan, J., & Liu, Z. (2013). Action Search by Example using Randomized Visual Vocabularies. IEEE Transactions on Image Processing, 22(1), 377-390. 1057-7149 https://hdl.handle.net/10356/100686 http://hdl.handle.net/10220/17968 10.1109/TIP.2012.2216273 en IEEE transactions on image processing © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/TIP.2012.2216273]. 15 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Yuan, Junsong Liu, Zicheng Yu, Gang Action search by example using randomized visual vocabularies |
| title | Action search by example using randomized visual vocabularies |
| title_full | Action search by example using randomized visual vocabularies |
| title_fullStr | Action search by example using randomized visual vocabularies |
| title_full_unstemmed | Action search by example using randomized visual vocabularies |
| title_short | Action search by example using randomized visual vocabularies |
| title_sort | action search by example using randomized visual vocabularies |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/100686 http://hdl.handle.net/10220/17968 |
| work_keys_str_mv | AT yuanjunsong actionsearchbyexampleusingrandomizedvisualvocabularies AT liuzicheng actionsearchbyexampleusingrandomizedvisualvocabularies AT yugang actionsearchbyexampleusingrandomizedvisualvocabularies |