双路检索+逐对视觉重排，提升视频搜索准确率
Dual-Route Top-K Retrieval with 1v1 VLM Reranking for the CoVR-R
- 分两路检索：文本增强与视觉嵌入结合，生成候选集
- 最终在隐藏测试集上达到95.28% R@1，99.66% R@50
- 适合需要高精度视频检索的应用场景
我们提出一种用于CoVR-R挑战的双路Top-K检索与1v1 VLM重排方法。该方法将组合视频检索拆解为两个关联问题：获取足够全面的前K个候选集，并安全判断是否有新候选可替代当前最优结果。首先通过VLM槽选择器改进推理/文本种子，不依赖DFN视觉检索；随后引入基于接触图嵌入的DFN-H/DFN-L视觉路径。两路结果合并为前10候选集，再由VLM最终重排器执行保守的1v1比较。在隐藏测试集上，系统取得95.28% R@1、97.47% R@5、98.48% R@10和99.66% R@50的成绩。核心启示是，CoVR-R更受益于召回与选择的解耦，而非广泛文本重排或直接多候选VLM分类。
原文摘要 · Abstract (English)
We describe \emph{Dual-Route Top-K Retrieval with 1v1 VLM Reranking} for the CoVR-R challenge. The method treats composed video retrieval as two coupled problems: finding a sufficiently complete top-k candidate set, and then safely deciding whether any candidate should replace a strong current top-1. We first improve the reasoning/text seed with a VLM slot selector over existing candidates, without introducing DFN visual retrieval. We then add a visual route from contact-sheet embeddings using DFN-H/DFN-L. The routes are merged into a top-10 candidate set, after which a VLM final reranker performs conservative 1v1 comparisons between the current top-1 and each challenger. On the hidden test split, the final system reaches 95.28 R@1, 97.47 R@5, 98.48 R@10, and 99.66 R@50. The main lesson is that CoVR-R benefits more from recall-selection decoupling than from broad text reranking or direct multi-candidate VLM classification.
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。