paper-with-me

Papers

Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval

2026-05-30 · Ali Alavi arxiv

Composed Video Retrieval (CoVR) seeks the target video that results from applying a free-form textual modification to a reference video. We address the \emph{Reason-Aware} CoVR (CoVR-R) challenge at the CVPR~2026 VidLLMs workshop, where retrieval is strictly zero-shot. We present \textbf{R3-CoVR} (\emph{Reason, Retrieve, Re-rank}), a training-free pipeline built entirely from frozen foundation models. A multimodal large language model (Qwen3-VL-8B) reasons about the \emph{after-effects} an edit implies -- state transitions, action phases, scene, camera and tempo -- and verbalises a concise post-edit description; a contrastive video--text encoder (SigLIP-2) embeds this description and the gallery for first-stage retrieval; finally a constraint-aware re-ranking stage uses the same multimodal model as a judge that scores each shortlisted candidate against the intended edited result. On the challenge test set, R3-CoVR attains \textbf{91.9\% R@1} and \textbf{98.2\% R@10}. Two findings drive these results: (i)~matching the description length to the contrastive encoder's text window lifts \Rk{1} from $67.5$ to $72.7$; and (ii)~the constraint-aware re-ranker, which reorders only the shortlist, lifts \Rk{1} from $72.7$ to $91.9$ -- the single largest gain. We analyse the re-ranker's behaviour, the retrieve/re-rank blend, and the shortlist depth, and we release a clean three-layer implementation.

📄 PDF Abstract BibTeX arXiv:2606.00910

Code (0)

등록된 구현이 없습니다.

Tasks

Video Retrieval

Similar Papers 제목 키워드 기반

Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers

2025-11-03 · Mohamed Eltahir, Ali Habibullah, Lama Ayash, Tanveer Hussain 외 arxiv

In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fusion techniques are training-free, they r…

Video Retrieval

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking

2025-06-11 · Wuwei Zhang, Fangcong Yin, Howard Yen, Danqi Chen 외

Recent work has identified retrieval heads (Wu et al., 2025b), a subset of attention heads responsible for retrieving salient information in long-context language models (LMs), as measured by their copy-paste behavior in…

Re-RankingRetrieval

GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning

2026-01-13 · Jiajin Liu, Yuanfu Sun, Dongzhe Fan, Qiaoyu Tan arxiv

Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, pr…

Node ClassificationLink PredictionGraph Learning

Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval

2025-08-29 · Yuxiang Liu, Tian Wang, Gourab Kundu, Tianyu Cao 외 arxiv

Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve r…

Logical Reasoning

A Comparative Study of Specialized LLMs as Dense Retrievers

2025-07-05 · Hengran Zhang, Keping Bi, Jiafeng Guo arxiv

While large language models (LLMs) are increasingly deployed as dense retrievers, the impact of their domain-specific specialization on retrieval effectiveness remains underexplored. This investigation systematically exa…

Mathematical ReasoningText Retrieval