Multi-Moments in Time : Learning and Interpreting Models for Multi-Action Video Understanding
Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds. However, most large-scale datasets built to train models for action recognition in video only provide a single label per video. Consequently, models can be incorrectly...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 12 vom: 09. Dez., Seite 9434-9445
|
|---|
| 1. Verfasser: |
Monfort, Mathew
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Pan, Bowen,
Ramakrishnan, Kandan,
Andonian, Alex,
McNamara, Barry A,
Lascelles, Alex,
Fan, Quanfu,
Gutfreund, Dan,
Feris, Rogerio Schmidt,
Oliva, Aude |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|