সংরক্ষণ করুন:
গ্রন্থ-পঞ্জীর বিবরন
প্রধান লেখক: Skow, Tyler, Martin, Alexander, Van Durme, Benjamin, Chellappa, Rama, Kriz, Reno
বিন্যাস: Preprint
প্রকাশিত: 2026
বিষয়গুলি:
অনলাইন ব্যবহার করুন:https://arxiv.org/abs/2602.02444
ট্যাগগুলো: ট্যাগ যুক্ত করুন
কোনো ট্যাগ নেই, প্রথমজন হিসাবে ট্যাগ করুন!
সূচিপত্রের সারণি:
  • 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.