When retrieving a person from a video archive by voice and face, should the system be multimodal or not? In real-world broadcast archives, unlike curated benchmarks, a target may be heard but unseen, seen but unheard, or both. Fusing scores from an absent modality injects noise, degrading precision below the best unimodal system. We propose a query-adaptive framework that detects active modalities via cross-modal score consistency: when both modalities are active, files retrieved by one also score highly on the other; this agreement breaks down when a modality is absent. Classifiers driven by these cross-modal features achieve 89% detection accuracy. On the BBC Rewind corpus (with over 12,000 broadcast videos) the adaptive system attains 94.2% P@1, outperforming speaker-only (82.9%), face-only (93.4%), and fixed fusion (90.0%), recovering 64% of the gap to an oracle with ground-truth modality labels (96.6%).

翻译：当通过语音和面部从视频档案中检索人物时，系统应采用多模态还是单一模态？在实际广播档案中，与精心策划的基准测试不同，目标人物可能只闻其声不见其人，或只见其人未闻其声，或两者兼有。融合缺失模态的分数会引入噪声，导致检索精度低于最优单一模态系统。我们提出一种查询自适应框架，通过跨模态分数一致性检测主动模态：当两种模态均活跃时，通过一种模态检索到的文件在另一种模态上也获得高分；当某一模态缺失时，这种一致性被破坏。基于这些跨模态特征训练的检测器实现了89%的检测准确率。在BBC Rewind语料库（包含超过12,000个广播视频）上，自适应系统达到了94.2%的P@1，优于仅依赖说话人（82.9%）、仅依赖面部（93.4%）和固定融合（90.0%）方法，将系统与具备真实模态标签的基准系统（96.6%）之间的差距缩小了64%。