FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing.
Zhuang LiYuyang ChaiTerry Yue ZhuoLizhen QuGholamreza HaffariFei LiDonghong JiQuan Hung TranPublished in: ACL (Findings) (2023)
Keyphrases
- natural language
- d scene
- graph grammars
- three dimensional
- positional information
- video sequences
- computer vision
- scene classification
- scene analysis
- graph representation
- single image
- random walk
- input image
- natural language processing
- real scenes
- spanning tree
- multiple images
- real world
- web pages
- keywords
- weighted graph
- bipartite graph
- graph theory
- graph model
- dynamic scenes
- scene understanding
- graph matching
- object recognition
- directed graph
- graph theoretic
- image sequences
- connected components
- moving objects