RANKVIDEO：面向文本-视频检索的推理重排方法

摘要

重排序是现代检索系统的关键组成部分，通常通过将高效初阶检索器与更具表现力的模型相结合来优化结果。尽管大型推理模型已推动文本重排序技术快速发展，但基于推理的视频检索重排序研究仍处于探索不足的状态。为解决这一空白，我们提出RANKVIDEO——一种基于推理的视频检索重排序器，能够显式地对查询-视频对进行推理，利用视频内容评估相关性。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，随后结合点式、对式排序目标及教师置信度蒸馏目标进行重排序训练，并辅以专门构建推理密集型查询-视频对的数据合成流程。在大规模MultiVENT 2.0基准测试上的实验表明，RANKVIDEO在双阶段检索框架中持续提升检索性能，nDCG@10指标平均提升31%，在保持更高效率的同时优于纯文本及视觉-语言重排序方案。

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：面向文本-视频检索的推理重排方法

RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval

摘要

Support