LLaVA-MR combines dense frame sampling, frame-difference key-frame selection, and variance-based token compression to improve generative MLLM video moment retrieval, reporting small SOTA gains over Mr. BLIP on three benchmarks.
Video action transformer network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
LLaVA-MR combines dense frame sampling, frame-difference key-frame selection, and variance-based token compression to improve generative MLLM video moment retrieval, reporting small SOTA gains over Mr. BLIP on three benchmarks.