# AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation

arXiv: https://arxiv.org/abs/2610.10047 · HTML: https://mlsanity.com/paper/2610.10047/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 33 of its 57 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 30 of 33)

- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation](https://mlsanity.com/paper/2305.10874/) (2023)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation](https://mlsanity.com/paper/2505.04512/) (2025)
- [OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation](https://mlsanity.com/paper/2412.00115/) (2024)
- [Understanding SSIM](https://mlsanity.com/paper/2006.13846/) (2020)
- [SkyReels-A2: Compose Anything in Video Diffusion Transformers](https://mlsanity.com/paper/2504.02436/) (2025)
- [Multi-subject Open-set Personalization in Video Generation](https://mlsanity.com/paper/2501.06187/) (2025)
- [Kling-Omni Technical Report](https://mlsanity.com/paper/2512.16776/) (2025)
- [Towards A Better Metric for Text-to-Video Generation](https://mlsanity.com/paper/2401.07781/) (2024)
- [VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2411.13503/) (2024)
- [CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models](https://mlsanity.com/paper/2508.11484/) (2025)
- [VINO: A Unified Visual Generator with Interleaved OmniModal Context](https://mlsanity.com/paper/2601.02358/) (2026)
- [MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement](https://mlsanity.com/paper/2505.23742/) (2025)
- [SkyReels-V3 Technique Report](https://mlsanity.com/paper/2601.17323/) (2026)
- [Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model](https://mlsanity.com/paper/2510.18573/) (2025)
- [Bernini: Latent Semantic Planning for Video Diffusion](https://mlsanity.com/paper/2605.22344/) (2026)
- [RefAlign: Representation Alignment for Reference-to-Video Generation](https://mlsanity.com/paper/2603.25743/) (2026)
- [MV-S2V: Multi-View Subject-Consistent Video Generation](https://mlsanity.com/paper/2601.17756/) (2026)
- [MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation](https://mlsanity.com/paper/2604.23789/) (2026)

## Abstract (arXiv)

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. textitAdSpark-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 textitAdSpark-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.