RANKVIDEO：基于推理重排序的文本到视频检索方法

摘要

重排序是现代检索系统的关键组成部分，通常将高效的一阶段检索器与更具表现力的模型结合以优化结果。尽管大型推理模型在文本重排序领域取得快速进展，但基于推理的视频检索重排序研究仍显不足。为此，我们提出RANKVIDEO——一种基于推理的视频重排序模型，其通过显式分析查询-视频对的视频内容来评估相关性。该模型采用两阶段课程训练：首先进行基于感知的监督微调，随后结合点对点、成对和教师置信度蒸馏目标进行重排序训练，并辅以构建推理密集型查询-视频对的数据合成流程。在大型MultiVENT 2.0基准测试上的实验表明，RANKVIDEO在双阶段框架内持续提升检索性能，nDCG@10指标平均提升31%，优于纯文本和视觉语言重排序方案，同时具备更高效率。

English

Reranking is a critical component of modern retrieval systems, which typically pair an efficient first-stage retriever with a more expressive model to refine results. While large reasoning models have driven rapid progress in text-centric reranking, reasoning-based reranking for video retrieval remains underexplored. To address this gap, we introduce RANKVIDEO, a reasoning-based reranker for video retrieval that explicitly reasons over query-video pairs using video content to assess relevance. RANKVIDEO is trained using a two-stage curriculum consisting of perception-grounded supervised fine-tuning followed by reranking training that combines pointwise, pairwise, and teacher confidence distillation objectives, and is supported by a data synthesis pipeline for constructing reasoning-intensive query-video pairs. Experiments on the large-scale MultiVENT 2.0 benchmark demonstrate that RANKVIDEO consistently improves retrieval performance within a two-stage framework, yielding an average improvement of 31% on nDCG@10 and outperforming text-only and vision-language reranking alternatives, while more efficient.

RANKVIDEO：基于推理重排序的文本到视频检索方法

RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval

摘要

Support