A single-image pipeline generates adversarial 3D pose variations that degrade vision-language model accuracy by up to 80%, and a new benchmark, MM3DTBench, quantifies this vulnerability.
Nocaps: Novel object caption- ing at scale
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
-
AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
A single-image pipeline generates adversarial 3D pose variations that degrade vision-language model accuracy by up to 80%, and a new benchmark, MM3DTBench, quantifies this vulnerability.