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

• URL: http://arxiv.org/abs/2606.00910v1
• Date: Sat, 30 May 2026 22:21:42 GMT
• Title: Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval
• Abstract summary: Composed Video Retrieval (CoVR) seeks the target video that results from applying a free-form textual modification to a reference video.<n>We present textbfR3-CoVR (emphReason, Retrieve, Re-rank), a training-free pipeline built entirely from frozen foundation models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Reason-Then-Retrieve for CoVR-R with Structured Edit Prompts and Dense-Sparse Fusion [13.20120200276798]
  We build a zero-shot reason-then-retrieve pipeline around Qwen3.5-27B.<n>For each gallery video, the model generates a retrieval-oriented structured description and a dense embedding.<n>On validation, the current best submission reaches 80.81 at R@1, 94.86 at R@5, 97.11 at R@10, and 98.59 at R@50.
  arXiv  Detail & Related papers  (2026-06-01T16:21:01Z)
• R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking [73.0537447183962]
  We present a zero-shot composed video retrieval pipeline built around Reasoning-guided Recalling and Reranking.<n>The model generates a reasoning trace that describes the expected target video after applying the edit.<n>Experiments have demonstrated the effectiveness of our method in addressing this challenge.
  arXiv  Detail & Related papers  (2026-05-31T09:20:53Z)
• CoVR-R:Reason-Aware Composed Video Retrieval [25.765681895305736]
  Composed Video Retrieval (CoVR) aims to find a target video given a reference video and a textual modification.<n>Prior work assumes the modification text fully specifies the visual changes, overlooking after-effects and implicit consequences.<n>We introduce a reasoning-first, zero-shot approach that leverages large multimodal models to infer causal and temporal consequences implied by the edit.
  arXiv  Detail & Related papers  (2026-03-20T17:59:25Z)
• PREGEN: Uncovering Latent Thoughts in Composed Video Retrieval [9.493866391853723]
  Composed Video Retrieval (CoVR) aims to retrieve a video based on a query video and a modifying text.<n>Current CoVR methods fail to fully exploit modern Vision-Language Models (VLMs)<n>We introduce PREGEN, an efficient and powerful CoVR framework that overcomes these limitations.
  arXiv  Detail & Related papers  (2026-01-20T09:57:04Z)
• Stable Video Infinity: Infinite-Length Video Generation with Error Recycling [76.91310169118408]
  We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines.<n> SVI incorporates Error-Recycling Fine-Tuning, a new type of efficient training that recycles the Diffusion Transformer's self-generated errors into supervisory prompts.<n>We evaluate SVI on three benchmarks, including consistent, creative, and conditional settings, thoroughly verifying its versatility and state-of-the-art role.
  arXiv  Detail & Related papers  (2025-10-10T09:45:46Z)
• From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos [48.666667545084835]
  Composed Video Retrieval (CoVR) retrieves a target video given a query video and a modification text describing the intended change.<n>We introduce TF-CoVR, the first large-scale benchmark dedicated to temporally fine-grained CoVR.<n> TF-CoVR focuses on gymnastics and diving and provides 180K triplets drawn from FineGym and FineDiving.
  arXiv  Detail & Related papers  (2025-06-05T17:31:17Z)
• EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval [52.375143786641196]
  EgoCVR is an evaluation benchmark for fine-grained Composed Video Retrieval. EgoCVR consists of 2,295 queries that specifically focus on high-quality temporal video understanding.
  arXiv  Detail & Related papers  (2024-07-23T17:19:23Z)
• Composed Video Retrieval via Enriched Context and Discriminative Embeddings [118.66322242183249]
  Composed video retrieval (CoVR) is a challenging problem in computer vision. We introduce a novel CoVR framework that leverages detailed language descriptions to explicitly encode query-specific contextual information. Our approach achieves gains as high as around 7% in terms of recall@K=1 score.
  arXiv  Detail & Related papers  (2024-03-25T17:59:03Z)
• CoVR-2: Automatic Data Construction for Composed Video Retrieval [59.854331104466254]
  Composed Image Retrieval (CoIR) has recently gained popularity as a task that considers both text and image queries together. We propose a scalable automatic dataset creation methodology that generates triplets given video-caption pairs. We also expand the scope of the task to include composed video retrieval (CoVR)
  arXiv  Detail & Related papers  (2023-08-28T17:55:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.