Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling.
Yu ZhaoHao FeiYixin CaoBobo LiMeishan ZhangJianguo WeiMin ZhangTat-Seng ChuaPublished in: CoRR (2023)
Keyphrases
- semantic role labeling
- spatio temporal
- video sequences
- moving objects
- space time
- dynamic textures
- image sequences
- dependency parsing
- syntactic parsing
- relation extraction
- video data
- semantic roles
- predicate argument
- word sense disambiguation
- video frames
- structured data
- tree kernels
- prepositional phrase
- syntactic and semantic dependency parsing
- named entity recognition
- semantic relations
- parse tree
- question answering