CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning
Singh, Darshan, Nagrani, Arsha, Manikantan, Kawshik, Singh, Harman, Tewari, Dinesh, Weyand, Tobias, Schmid, Cordelia, Angelova, Anelia 等 9 位作者
原文摘要
Recent advancements in video models have shown tremendous progress, particularly in long video understanding. However, current benchmarks predominantly feature western-centric data and English as the dominant language, introducing significant biases in evaluation. To address this, we introduce CURVE, a challenging benchmark for multicultural and multilingual video reasoning. CURVE comprises high-quality, entirely human-generated annotations from diverse, region-specific cultural videos across 18 global locales. Unlike prior work that relies on automatic translations, CURVE provides complex questions, answers, and multi-step reasoning steps, all crafted in native languages. Making progress on CURVE requires a deeply situated understanding of visual cultural context. Furthermore, we leverage CURVE's reasoning traces to construct evidence-based graphs and propose a novel iterative strategy using these graphs to identify fine-grained errors in reasoning. Our evaluations reveal that SoTA Video-LLMs struggle significantly, performing substantially below human-level accuracy, with errors primarily stemming from the visual perception of cultural elements. We will release CURVE to foster the development of more equitable and capable multimodal foundation models.
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表