EASG-Bench is a 1,807-question egocentric video QA benchmark built from action scene graphs, and current video-LLMs score far below language-only models on temporal ordering questions.
Egoplan- bench: Benchmarking egocentric embodied planning with multimodal large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
support 1representative citing papers
citing papers explorer
-
EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
EASG-Bench is a 1,807-question egocentric video QA benchmark built from action scene graphs, and current video-LLMs score far below language-only models on temporal ordering questions.