发表机构
School of Electronic and Electrical Engineering, Kyungpook National University（庆北国立大学电子与电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究文本到视频检索问题，提出分布对齐桥（DAB）框架，将其视为分布对齐任务，通过高斯分布建模考虑不确定性，用受扩散启发的桥和分布感知对比损失优化，在多基准测试中显著优于现有基线并提供校准排名。
AI 中文摘要
本文提出了分布对齐桥（DAB）框架，将文本到视频检索重新定义为分布对齐任务，而非传统确定性点匹配。通过将文本和视频嵌入建模为高斯分布，DAB明确考虑了模态特定的不确定性。利用确定性、受扩散启发的桥，通过截断细化过程迭代细化文本分布至目标视频分布。引入基于库尔贝克-莱布勒散度的分布感知对比损失优化跨模态相似性。在多个基准测试中，DAB显著优于现有基线，提供校准的不确定性感知排名。
英文摘要
This paper proposes the Distribution-Alignment Bridge (DAB), a framework that reconceptualizes text-to-video retrieval as a distribution alignment task rather than traditional deterministic point matching. By modeling both text and video embeddings as Gaussian distributions defined by mean and variance, DAB explicitly accounts for modality-specific uncertainty. We employ a deterministic, diffusion-inspired bridge to iteratively refine text distributions toward their target video distributions through a truncated refinement process. This approach unifies probabilistic embedding and distributional transformation into a cohesive, end-to-end trainable system. To optimize cross-modal similarity, we introduce a distribution-aware contrastive loss based on Kullback-Leibler divergence. Extensive evaluations on MSR-VTT, MSVD, and VATEX benchmarks confirm that DAB significantly outperforms existing probabilistic and diffusion-based baselines, while providing calibrated uncertainty-aware ranking through bridge-induced distributional margins.
CommentsECCV 2026
