Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Video RetrievalSimilar Papers 제목 키워드 기반
Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers
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 RetrievalQuery-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
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-RankingRetrievalGraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning
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 LearningExploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval
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 ReasoningA Comparative Study of Specialized LLMs as Dense Retrievers
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