A new 170K-image, 5M-QA traffic surveillance benchmark improves LMM test scores by 27-83% after fine-tuning, but the gains are measured on the same pipeline that created the data.
Title resolution pending
1 Pith paper cite this work, alongside 241 external citations. Polarity classification is still indexing.
1
Pith paper citing it
241
external citations · OpenAlex
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance
A new 170K-image, 5M-QA traffic surveillance benchmark improves LMM test scores by 27-83% after fine-tuning, but the gains are measured on the same pipeline that created the data.