Integrating Language and Vision to Generate Natural Language Descriptions of Videos in the Wild
5774Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Factor Graph
Method |
usedFor |
Video Description
Task |
|
N-Gram Language Model
Method |
comparesWith |
Video Description
Task |
|
Text Corpus
Material |
provides |
Factor Graph
Method |
|
Visual Recognition System
Material |
usedFor |
Activity Recognition
Task |
|
Visual Recognition System
Material |
usedFor |
Entity Recognition
Task |
|
YouTube Videos
Material |
testedOn |
Video Description
Task |