| title | AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation |
|---|---|
| authors | Zhifei Yang, Zhao Jiang, Keyang Lu, Honghe Zhu, Zheng Zhang, Jingjing Lv, Changping Peng, Ching Law, Zhen Xiao |
| date | 2026-10-07 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.10047 |
| affiliation | Peking University |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Product-centric advertisement video generation aims to create promotional videos that preserve fine-grained product identity while presenting selling points through coherent multi-shot narratives. However, this emerging task remains underexplored due to the lack of large-scale advertisement-specific datasets and comprehensive evaluation frameworks. To address this gap, we introduce AdSpark, a large-scale dataset and benchmark for product-centric advertisement video generation, based on data from a major e-commerce platform. AdSpark-300K contains approximately 300K reference image--prompt--video triplets, comprising a real-world subset and a synthetic subset. Each sample provides structured advertisement annotations, including product identity annotations, selling-point descriptions, creative plans, and aligned audio scripts, enabling models to learn product preservation and advertisement-oriented visual storytelling. We further propose AdSpark-Bench, a diagnostic benchmark that evaluates generated advertisements across six dimensions, including visual quality, product fidelity, instruction adherence, temporal coherence, audio alignment, and advertisement effectiveness. Based on AdSpark-Bench, we evaluate representative models, revealing key challenges in product preservation, multi-shot storytelling, and selling-point visualization. Experiments with AdSpark-300K-finetuned models further validate the effectiveness of our dataset. AdSpark provides a unified dataset and benchmark for future research, and we will release the dataset upon acceptance. |
cite
@misc{yang2026adspark,
title={AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation},
author={Zhifei Yang and Zhao Jiang and Keyang Lu and Honghe Zhu and Zheng Zhang and Jingjing Lv and Changping Peng and Ching Law and Zhen Xiao},
year={2026},
eprint={2610.10047},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.10047}
}