解决视频检索中查询模糊带来的不确定性问题
Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval
- 分层证据学习框架，融合多粒度跨模态信息
- 在多个数据集上超越现有最佳方法，提升显著
- 适合关注视频检索与不确定性建模的研究者
部分相关视频检索旨在用描述部分内容的简短文本查询，召回完整未剪辑视频。由于查询简短而视频内容丰富，检索过程天然存在不确定性。模糊查询常导致视频间语义歧义，且视频中稀疏的时间监督难以提供充分匹配证据。为此，我们提出 Holmes，一种分层证据学习框架，通过聚合多粒度跨模态证据来显式量化和建模不确定性。在视频间层面，相似度得分被解释为证据支持，并用狄利克雷分布建模；基于三重原则，实现细粒度查询识别，进而引导查询自适应校准学习。在视频内层面，通过灵活最优传输与自适应尘箱构建软查询-片段对齐，积累更密集证据，缓解时间监督稀疏性，抑制虚假局部响应。大量实验表明，Holmes 显著优于当前最优方法。代码已开源：https://github.com/lijun2005/ICML26-Holmes。
原文摘要 · Abstract (English)
Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries and rich video content inevitably introduces uncertainty into the retrieval process. In this setting, vague queries often induce semantic ambiguity across videos, a challenge that is further exacerbated by the sparse temporal supervision within videos, which fails to provide sufficient matching evidence. To address this, we propose Holmes, a hierarchical evidential learning framework that aggregates multi-granular cross-modal evidence to quantify and model uncertainty explicitly. At the inter-video level, similarity scores are interpreted as evidential support and modeled via a Dirichlet distribution. Based on the proposed three-fold principle, we perform fine-grained query identification, which then guides query-adaptive calibrated learning. At the intra-video level, to accumulate denser evidence, we formulate a soft query-clip alignment via flexible optimal transport with an adaptive dustbin, which alleviates sparse temporal supervision while suppressing spurious local responses. Extensive experiments demonstrate that Holmes outperforms state-of-the-art methods. Code is released at https://github.com/lijun2005/ICML26-Holmes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。