Visual Semantic Role Labeling for Video Understanding.
Arka SadhuTanmay GuptaMark YatskarRam NevatiaAniruddha KembhaviPublished in: CVPR (2021)
Keyphrases
- semantic role labeling
- dependency parsing
- predicate argument
- syntactic parsing
- relation extraction
- semantic roles
- video sequences
- word sense disambiguation
- visual information
- video data
- video frames
- tree kernels
- visual features
- named entity recognition
- metadata
- key frames
- knowledge representation
- dependency parser
- hidden markov models
- syntactic dependencies
- prepositional phrase
- syntactic and semantic dependency parsing