Summarizing Unconstrained Videos Using Salient Montages
We present a novel method to summarize unconstrained videos using salient montages (i.e., a "melange" of frames in the video as shown in Fig. 1, by finding "montageable moments" and identifying the salient people and actions to depict in each montage. Our method aims at addressin...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 39(2017), 11 vom: 01. Nov., Seite 2256-2269
|
|---|
| 1. Verfasser: |
Sun, Min
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Farhadi, Ali,
Taskar, Ben,
Seitz, Steve |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2017
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.
Cameras
Detectors
Electronic mail
Feature extraction
Tracking
Videos
YouTube |
|---|