DIVE, an iterative question-decomposition system with intent estimation and object-centric video summarization, achieves 81.44% on CVRR-ES.
Llama-vid: An image is worth 2 tokens in large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DIVE: Deep-search Iterative Video Exploration A Technical Report for the CVRR Challenge at CVPR 2025
DIVE, an iterative question-decomposition system with intent estimation and object-centric video summarization, achieves 81.44% on CVRR-ES.