Sign in
ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos.
Zhou Yu
Lixiang Zheng
Zhou Zhao
Fei Wu
Jianping Fan
Kui Ren
Jun Yu
Published in:
CoRR (2023)
Keyphrases
</>
fine grained
coarse grained
real world
access control
video frames
video content
massively parallel
video sequences
tightly coupled
knowledge base
knowledge representation
metadata
high level
user behavior
user generated