RoadTones: Tone Controllable Text Generation from Road Event Videos
For developers of video-language models in communication-critical applications (e.g., autonomous driving alerts), this work addresses the underexplored problem of tone control, but the contributions are incremental as they extend existing video captioning with tonal annotations and a CoT mechanism.
The paper introduces RoadTones, a dataset-model-evaluation suite for tone-controllable road video captioning, enabling control over expression style beyond factual accuracy. The RoadTones-51K dataset and RoadTones-VL-CoT model achieve joint factual consistency and tone adherence, validated via user study.
Existing video-language models can generate factual descriptions of road events but lack control over how these events are expressed: their tone, urgency, or style. This limits deployment in communication-critical settings where the effectiveness of a message depends on both content and presentation, not just factual accuracy. To mitigate this, we introduce a comprehensive dataset-model-evaluation suite for tone-controllable road video captioning. Our human-validated data generation pipeline expands road-video corpora with diverse tonal annotations and multi-tone captions, yielding the RoadTones-51K dataset. We propose RoadTones-VL-CoT, a controllable video-to-text model that also generates tone-conditioned Chain-of-Thought intermediate drafts for interpretability. We also introduce RoadTones-Eval, a new evaluation suite that jointly measures factual consistency and tone adherence. In addition, we conducted a user study whose results validate caption quality, tone control, and factual consistency. Together, these contributions lay the foundation for context-sensitive tone-controllable video captioning.