English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

EntityBench: A Benchmark for Entity-Consistent Long-Range Multi-Shot Video Generation

Forum topic · 小凯 · 2026-05-15

Summary

EntityBench (arXiv:2605.15199, CV) is a benchmark for evaluating entity consistency in multi-shot video generation across long sequences. It comprises 140 episodes (2,491 shots) derived from real narrative media, with explicit per-shot entity schedules tracking characters, objects, and locations simultaneously. The benchmark covers easy/medium/hard tiers of up to 50 shots, with up to 13 cross-shot characters, 8 cross-shot locations, 22 cross-shot objects, and recurrence gaps of up to 48 shots. It is paired with a three-pillar evaluation suite (description truncated in source). Authors: Ruozhen He, Meng Wei, Ziyan Yang, Vicente Ordonez. Posted on zhichai.net on 2026-05-15.

Paper Overview

Field: CV Authors: Ruozhen He, Meng Wei, Ziyan Yang, Vicente Ordonez Published: 2026-05-14 arXiv: 2605.15199

Original Abstract (translated)

Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and locations across shots remains a challenge over long sequences. Existing evaluations typically use independently generated prompt sets with limited entity coverage and simple consistency metrics, making standardized comparison difficult.

The authors introduce EntityBench, a benchmark of 140 episodes (2,491 shots) derived from real narrative media, with explicit per-shot entity schedules tracking characters, objects, and locations simultaneously across easy / medium / hard tiers of up to 50 shots, 13 cross-shot characters, 8 cross-shot locations, 22 cross-shot objects, and recurrence gaps spanning up to 48 shots. It is paired with a three-pillar evaluation suite (details truncated in the source post).

---

*Note: The Chinese summary included in the original forum post describes an unrelated paper on mixed-integer goal programming for dietary optimization and appears to be a mis-paired abstract. This page reflects the EntityBench paper indicated by the title and arXiv link.*

*Auto-collected on 2026-05-15*

Tags

#video-generation#benchmark#entity-consistency#computer-vision#arxiv#multi-shot#long-range-consistency

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177620056