A new multi-frame visual storytelling dataset with explicit entity grounding, plus a fine-tuned Qwen2.5-VL baseline that reduces measured hallucinations by 12.3%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation
A new multi-frame visual storytelling dataset with explicit entity grounding, plus a fine-tuned Qwen2.5-VL baseline that reduces measured hallucinations by 12.3%.