Visual Semantic Role Labeling for Video Understanding.
Arka SadhuTanmay GuptaMark YatskarRam NevatiaAniruddha KembhaviPublished in: CoRR (2021)
Keyphrases
- semantic role labeling
- dependency parsing
- syntactic parsing
- relation extraction
- video data
- predicate argument
- semantic roles
- tree kernels
- video sequences
- visual features
- video frames
- word sense disambiguation
- visual information
- named entity recognition
- syntactic and semantic dependency parsing
- prepositional phrase
- conditional random fields
- low level