AI RESEARCH
GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos
arXiv CS.CV
•
ArXi:2603.14426v1 Announce Type: new Existing text-to-video retrieval benchmarks are dominated by real-world footage where much of the semantics can be inferred from a single frame, leaving temporal reasoning and explicit end-state grounding under-evaluated. We