Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge
In this work, we present a new framework, video segmentation by detection (VSD), for tackling the problem of unsupervised video multi-object segmentation. Our model employs an object detector for automatic target discovery and a set of single-object trackers for the simultaneous tracking of all targ...
| প্রধান লেখক: | , , , , |
|---|---|
| বিন্যাস: | Conference item |
| প্রকাশিত: |
DAVIS: Densely Annotated VIdeo Segmentation
2019
|
| _version_ | 1826264976033054720 |
|---|---|
| author | Yang, Z Wang, Q Bai, S Hu, W Torr, P |
| author_facet | Yang, Z Wang, Q Bai, S Hu, W Torr, P |
| author_sort | Yang, Z |
| collection | OXFORD |
| description | In this work, we present a new framework, video segmentation by detection (VSD), for tackling the problem of unsupervised video multi-object segmentation. Our model employs an object detector for automatic target discovery and a set of single-object trackers for the simultaneous tracking of all targets. While addressing the object re-identification problem, we observe that many of the objects of interest in the dataset are humans or human centric such as bicycles. As such, following a design philosophy that special purpose algorithms will always be better than general purpose ones, we explore whether we can leverage the rich existing research efforts on re-identifying humans to improve the results or exploit the spatial relations of human-centric objects to humans. The proposed method achieves the highest J -Mean of 0.535 and an overall second place in the unsupervised track of the 2019 DAVIS Challenge. |
| first_indexed | 2024-03-06T20:16:25Z |
| format | Conference item |
| id | oxford-uuid:2c4aea29-c1b8-4ae2-8fe9-88c95bcb242c |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:16:25Z |
| publishDate | 2019 |
| publisher | DAVIS: Densely Annotated VIdeo Segmentation |
| record_format | dspace |
| spelling | oxford-uuid:2c4aea29-c1b8-4ae2-8fe9-88c95bcb242c2022-03-26T12:36:08ZVideo segmentation by detection for the 2019 Unsupervised DAVIS ChallengeConference itemhttp://purl.org/coar/resource_type/c_5794uuid:2c4aea29-c1b8-4ae2-8fe9-88c95bcb242cSymplectic Elements at OxfordDAVIS: Densely Annotated VIdeo Segmentation2019Yang, ZWang, QBai, SHu, WTorr, PIn this work, we present a new framework, video segmentation by detection (VSD), for tackling the problem of unsupervised video multi-object segmentation. Our model employs an object detector for automatic target discovery and a set of single-object trackers for the simultaneous tracking of all targets. While addressing the object re-identification problem, we observe that many of the objects of interest in the dataset are humans or human centric such as bicycles. As such, following a design philosophy that special purpose algorithms will always be better than general purpose ones, we explore whether we can leverage the rich existing research efforts on re-identifying humans to improve the results or exploit the spatial relations of human-centric objects to humans. The proposed method achieves the highest J -Mean of 0.535 and an overall second place in the unsupervised track of the 2019 DAVIS Challenge. |
| spellingShingle | Yang, Z Wang, Q Bai, S Hu, W Torr, P Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge |
| title | Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge |
| title_full | Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge |
| title_fullStr | Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge |
| title_full_unstemmed | Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge |
| title_short | Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge |
| title_sort | video segmentation by detection for the 2019 unsupervised davis challenge |
| work_keys_str_mv | AT yangz videosegmentationbydetectionforthe2019unsuperviseddavischallenge AT wangq videosegmentationbydetectionforthe2019unsuperviseddavischallenge AT bais videosegmentationbydetectionforthe2019unsuperviseddavischallenge AT huw videosegmentationbydetectionforthe2019unsuperviseddavischallenge AT torrp videosegmentationbydetectionforthe2019unsuperviseddavischallenge |