MLLM-VADStory: Domain Knowledge-Driven Multimodal LLMs for Video Ad Storyline Insights
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911371209211904 |
|---|---|
| author | Yang, Jasmine Zhang, Poppy Hill, Shawndra |
| author_facet | Yang, Jasmine Zhang, Poppy Hill, Shawndra |
| contents | We propose MLLM-VADStory, a novel domain knowledge-guided multimodal large language models (MLLM) framework to systematically quantify and generate insights for video ad storyline understanding at scale. The framework is centered on the core idea that ad narratives are structured by functional intent, with each scene unit performing a distinct communicative function, delivering product and brand-oriented information within seconds. MLLM-VADStory segments ads into functional units, classifies each unit's functionality using a novel advertising-specific functional role taxonomy, and then aggregates functional sequences across ads to recover data-driven storyline structures. Applying the framework to 50k social media video ads across four industry subverticals, we find that story-based creatives improve video retention, and we recommend top-performing story arcs to guide advertisers in creative design. Our framework demonstrates the value of using domain knowledge to guide MLLMs in generating scalable insights for video ad storylines, making it a versatile tool for understanding video creatives in general. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07850 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MLLM-VADStory: Domain Knowledge-Driven Multimodal LLMs for Video Ad Storyline Insights Yang, Jasmine Zhang, Poppy Hill, Shawndra Multimedia Computer Vision and Pattern Recognition We propose MLLM-VADStory, a novel domain knowledge-guided multimodal large language models (MLLM) framework to systematically quantify and generate insights for video ad storyline understanding at scale. The framework is centered on the core idea that ad narratives are structured by functional intent, with each scene unit performing a distinct communicative function, delivering product and brand-oriented information within seconds. MLLM-VADStory segments ads into functional units, classifies each unit's functionality using a novel advertising-specific functional role taxonomy, and then aggregates functional sequences across ads to recover data-driven storyline structures. Applying the framework to 50k social media video ads across four industry subverticals, we find that story-based creatives improve video retention, and we recommend top-performing story arcs to guide advertisers in creative design. Our framework demonstrates the value of using domain knowledge to guide MLLMs in generating scalable insights for video ad storylines, making it a versatile tool for understanding video creatives in general. |
| title | MLLM-VADStory: Domain Knowledge-Driven Multimodal LLMs for Video Ad Storyline Insights |
| topic | Multimedia Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.07850 |