B-VLLM selects question-relevant frames and spatial tokens before feeding a video to a vision LLM, improving video QA accuracy under a fixed token budget.
Dif- fusiondet: Diffusion model for object detection
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens
B-VLLM selects question-relevant frames and spatial tokens before feeding a video to a vision LLM, improving video QA accuracy under a fixed token budget.