AdSpark: 300K e-commerce triplets and benchmark for product-centric ad video generation
Zhifei Yang · hf · 2026-10-08
AdSpark is a large-scale dataset and benchmark for product-centric advertisement video generation, built from a major e-commerce platform. AdSpark-300K provides 300K reference image-prompt-video triplets (real and synthetic) with structured annotations: product identity, selling points, creative plans, and aligned audio scripts. AdSpark-Bench evaluates generations across six dimensions including product fidelity, instruction adherence, and advertisement effectiveness. Evaluations reveal key challenges in product preservation, multi-shot storytelling, and selling-point visualization; the dataset will be released upon acceptance.
More from Multimodal
- AI-generated feature 'A Woman Asleep' enters major film festival's main competition — lmoroney · 2026-10-08
- vLLM-Omni technical report: a unified serving runtime for omni-modal generation — vllm_project · 2026-10-08
- Alaskan Raven Couple 'Conversing' Video Goes Viral on X — ZeroStateReflex · 2026-10-08
- Band Builds Audio-Reactive WebGL + Local SD 1.5 Pipeline for Live Improv Music Video — XploitXploit · 2026-10-08
- Claude turns OpenAI's 198-page Erdős conjecture proof into a 2-minute narrated 3D animation — imjustnewatai · 2026-10-08
- AI Short Film About Relationships Made With ComfyUI Agent Driver and Multi-Model Pipeline — TheHollywoodGeek · 2026-10-08