Temporal semantic compression for video browsing
We present a video browsing approach, termed Temporal Semantic Compression (TSC) that uses automated measures of interest to support today's foraging behaviours. Conventional browsers 'compress' a video stream using simple 2x or 8x fast-forward. TSC browsers dynamically filter video b...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
ACM Press
2008
|
| Online Access: | http://hdl.handle.net/20.500.11937/13482 |
| _version_ | 1848748359368572928 |
|---|---|
| author | Adams, Brett Greenhill, Stewart Venkatesh, Svetha |
| author2 | J. Bradshaw |
| author_facet | J. Bradshaw Adams, Brett Greenhill, Stewart Venkatesh, Svetha |
| author_sort | Adams, Brett |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | We present a video browsing approach, termed Temporal Semantic Compression (TSC) that uses automated measures of interest to support today's foraging behaviours. Conventional browsers 'compress' a video stream using simple 2x or 8x fast-forward. TSC browsers dynamically filter video based on a single user gesture to leave out more or less of the boring bits. We demonstrate a browser with an example interest measure, derived from an automated estimate of movie tempo, to forage in terms of narrative structures such as crises, climaxes, and action sequence book-ends. Media understanding algorithms facilitate browsing, and interactivity enables the human-in-the-loop to cope when those algorithms fail to cross the semantic gap. |
| first_indexed | 2025-11-14T07:03:47Z |
| format | Conference Paper |
| id | curtin-20.500.11937-13482 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:03:47Z |
| publishDate | 2008 |
| publisher | ACM Press |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-134822022-11-21T06:47:04Z Temporal semantic compression for video browsing Adams, Brett Greenhill, Stewart Venkatesh, Svetha J. Bradshaw H. Lieberman S. Staab We present a video browsing approach, termed Temporal Semantic Compression (TSC) that uses automated measures of interest to support today's foraging behaviours. Conventional browsers 'compress' a video stream using simple 2x or 8x fast-forward. TSC browsers dynamically filter video based on a single user gesture to leave out more or less of the boring bits. We demonstrate a browser with an example interest measure, derived from an automated estimate of movie tempo, to forage in terms of narrative structures such as crises, climaxes, and action sequence book-ends. Media understanding algorithms facilitate browsing, and interactivity enables the human-in-the-loop to cope when those algorithms fail to cross the semantic gap. 2008 Conference Paper http://hdl.handle.net/20.500.11937/13482 10.1145/1378773.1378813 ACM Press restricted |
| spellingShingle | Adams, Brett Greenhill, Stewart Venkatesh, Svetha Temporal semantic compression for video browsing |
| title | Temporal semantic compression for video browsing |
| title_full | Temporal semantic compression for video browsing |
| title_fullStr | Temporal semantic compression for video browsing |
| title_full_unstemmed | Temporal semantic compression for video browsing |
| title_short | Temporal semantic compression for video browsing |
| title_sort | temporal semantic compression for video browsing |
| url | http://hdl.handle.net/20.500.11937/13482 |