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 \textbf{AdSpark}, a large-scale dataset and benchmark for product-centric advertisement video generation, based on data from a major e-commerce platform. \textit{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 \textit{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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yang, Z., Jiang, Z., Lu, K., Zhu, H., Zhang, Z., Lv, J., Peng, C., Law, C., & Xiao, Z. (2026). AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation. https://omanscience.com/en/articles/adspark-a-large-scale-dataset-and-benchmark-for-product-centric-advertisement-video-generation
MLA 9
Yang, Zhifei, et al. "AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation." https://omanscience.com/en/articles/adspark-a-large-scale-dataset-and-benchmark-for-product-centric-advertisement-video-generation.
Chicago (author–date)
Yang, Zhifei, Zhao Jiang, Keyang Lu, Honghe Zhu, Zheng Zhang, Jingjing Lv, Changping Peng, Ching Law, and Zhen Xiao. 2026. "AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation." https://omanscience.com/en/articles/adspark-a-large-scale-dataset-and-benchmark-for-product-centric-advertisement-video-generation.
Harvard
Yang, Z., Jiang, Z., Lu, K., Zhu, H., Zhang, Z., Lv, J., Peng, C., Law, C. and Xiao, Z. (2026) 'AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation', Available at: https://omanscience.com/en/articles/adspark-a-large-scale-dataset-and-benchmark-for-product-centric-advertisement-video-generation.
Vancouver
Yang Z, Jiang Z, Lu K, Zhu H, Zhang Z, Lv J, et al. AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation. https://omanscience.com/en/articles/adspark-a-large-scale-dataset-and-benchmark-for-product-centric-advertisement-video-generation
IEEE
Z. Yang, Z. Jiang, K. Lu, H. Zhu, Z. Zhang, J. Lv, C. Peng, C. Law, and Z. Xiao, "AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation," https://omanscience.com/en/articles/adspark-a-large-scale-dataset-and-benchmark-for-product-centric-advertisement-video-generation.