Vector ordering and regression learning‐based ranking for dynamic summarisation of user videos
Dynamic video summarisation (video skimming) is a process of generating a shorter video (video skim) as a summary of a given video, which helps in its easier and quicker comprehension. In this study, an efficient dynamic summarisation approach for user videos is proposed using vector ordering for ra...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-12-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-ipr.2020.0234 |
| _version_ | 1811340895005442048 |
|---|---|
| author | Vivekraj V K Debashis Sen Balasubramanian Raman |
| author_facet | Vivekraj V K Debashis Sen Balasubramanian Raman |
| author_sort | Vivekraj V K |
| collection | DOAJ |
| description | Dynamic video summarisation (video skimming) is a process of generating a shorter video (video skim) as a summary of a given video, which helps in its easier and quicker comprehension. In this study, an efficient dynamic summarisation approach for user videos is proposed using vector ordering for ranking video units (frames/shots). User videos are casually shot unscripted videos, where skimming involves the selection of its interesting part(s) ignoring many uninteresting ones. The concept of R‐ordering of vectors is employed to find a representative frame, which is used to perform relative ranking of the video frames. It is theoretically shown that significance is given to each element of a frame's feature vector while computing the importance scores that lead to the frame ranks used for skimming. Furthermore, the allocation of different weights to the features involved is also achieved using linear and Gaussian process regressions. Through extensive experiments considering several standard datasets with human‐labelled ground truth, the proposed approach is demonstrated to be efficient and to perform better than the relevant state‐of‐the‐art. |
| first_indexed | 2024-04-13T18:48:41Z |
| format | Article |
| id | doaj.art-fd3ecb8a235a4978a9f21e0ae955c942 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-13T18:48:41Z |
| publishDate | 2020-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-fd3ecb8a235a4978a9f21e0ae955c9422022-12-22T02:34:31ZengWileyIET Image Processing1751-96591751-96672020-12-0114153941395610.1049/iet-ipr.2020.0234Vector ordering and regression learning‐based ranking for dynamic summarisation of user videosVivekraj V K0Debashis Sen1Balasubramanian Raman2Department of Computer Science and EngineeringIndian Institute of Technology RoorkeeRoorkeeIndiaDepartment of Electronics and Electrical Communications EngineeringIndian Institute of Technology KharagpurKharagpurIndiaDepartment of Computer Science and EngineeringIndian Institute of Technology RoorkeeRoorkeeIndiaDynamic video summarisation (video skimming) is a process of generating a shorter video (video skim) as a summary of a given video, which helps in its easier and quicker comprehension. In this study, an efficient dynamic summarisation approach for user videos is proposed using vector ordering for ranking video units (frames/shots). User videos are casually shot unscripted videos, where skimming involves the selection of its interesting part(s) ignoring many uninteresting ones. The concept of R‐ordering of vectors is employed to find a representative frame, which is used to perform relative ranking of the video frames. It is theoretically shown that significance is given to each element of a frame's feature vector while computing the importance scores that lead to the frame ranks used for skimming. Furthermore, the allocation of different weights to the features involved is also achieved using linear and Gaussian process regressions. Through extensive experiments considering several standard datasets with human‐labelled ground truth, the proposed approach is demonstrated to be efficient and to perform better than the relevant state‐of‐the‐art.https://doi.org/10.1049/iet-ipr.2020.0234vector orderinguser videosdynamic video summarisationvideo skimmingshorter videovideo skim |
| spellingShingle | Vivekraj V K Debashis Sen Balasubramanian Raman Vector ordering and regression learning‐based ranking for dynamic summarisation of user videos IET Image Processing vector ordering user videos dynamic video summarisation video skimming shorter video video skim |
| title | Vector ordering and regression learning‐based ranking for dynamic summarisation of user videos |
| title_full | Vector ordering and regression learning‐based ranking for dynamic summarisation of user videos |
| title_fullStr | Vector ordering and regression learning‐based ranking for dynamic summarisation of user videos |
| title_full_unstemmed | Vector ordering and regression learning‐based ranking for dynamic summarisation of user videos |
| title_short | Vector ordering and regression learning‐based ranking for dynamic summarisation of user videos |
| title_sort | vector ordering and regression learning based ranking for dynamic summarisation of user videos |
| topic | vector ordering user videos dynamic video summarisation video skimming shorter video video skim |
| url | https://doi.org/10.1049/iet-ipr.2020.0234 |
| work_keys_str_mv | AT vivekrajvk vectororderingandregressionlearningbasedrankingfordynamicsummarisationofuservideos AT debashissen vectororderingandregressionlearningbasedrankingfordynamicsummarisationofuservideos AT balasubramanianraman vectororderingandregressionlearningbasedrankingfordynamicsummarisationofuservideos |