Abstract
We address the problem of temporally aligning semantically similar videos, for example two videos of cars on different tracks. We present an alignment method that establishes frame-to-frame correspondences such that the two cars are seen from a similar viewpoint (e.g. facing right), while also being temporally smooth and visually pleasing. Unlike previous works, we do not assume that the videos show the same scripted sequence of events. We compare against three alternative methods, including the popular DTW algorithm, on a new dataset of realistic videos collected from the internet. We perform a comprehensive evaluation using a novel protocol that includes both quantitative measures and a user study on visual pleasingness.
| Original language | English |
|---|---|
| Title of host publication | The 13th Asian Conference on Computer Vision (ACCV 2016) |
| Publisher | Springer, Cham |
| Pages | 273-288 |
| Number of pages | 16 |
| ISBN (Electronic) | 978-3-319-54190-7 |
| ISBN (Print) | 978-3-319-54189-1 |
| Publication status | Published - 12 Mar 2017 |
| Event | 13th Asian Conference on Computer Vision - Taipei, Taiwan, Province of China Duration: 20 Nov 2016 → 24 Nov 2016 http://www.accv2016.org/ |
Publication series
| Name | Lecture Notes in Computer Science |
|---|---|
| Publisher | Springer, Cham |
| Volume | 10114 |
| ISSN (Print) | 0302-9743 |
Conference
| Conference | 13th Asian Conference on Computer Vision |
|---|---|
| Abbreviated title | ACCV'16 |
| Country/Territory | Taiwan, Province of China |
| City | Taipei |
| Period | 20/11/16 → 24/11/16 |
| Internet address |