The paper proposes MLLM-SUL, an image-based multimodal language model that jointly generates driving-scene captions and localizes risk objects, reporting state-of-the-art scores on DRAMA-ROLISP and an extended DRAMA-SRIS dataset.
Traffic sign interpretation via natural language description,
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
background 1representative citing papers
citing papers explorer
-
MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios
The paper proposes MLLM-SUL, an image-based multimodal language model that jointly generates driving-scene captions and localizes risk objects, reporting state-of-the-art scores on DRAMA-ROLISP and an extended DRAMA-SRIS dataset.