ResNetVLLM claims state-of-the-art zero-shot video QA by training a non-pretrained ResNet jointly with a LLaVA-based LLM on instruction data, without releasing code or statistical details.
Instructblip: Towards general-purpose vision- language models with instruction tuning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Task
ResNetVLLM claims state-of-the-art zero-shot video QA by training a non-pretrained ResNet jointly with a LLaVA-based LLM on instruction data, without releasing code or statistical details.