ReCoVR: Closing the Loop in Interactive Composed Video Retrieval

• URL: http://arxiv.org/abs/2605.09836v1
• Date: Mon, 11 May 2026 00:38:24 GMT
• Title: ReCoVR: Closing the Loop in Interactive Composed Video Retrieval
• Abstract summary: Composed video retrieval (CoVR) searches for target videos using a reference video and a modification text.<n>We first formalize interactive composed video retrieval, a multi-turn extension of CoVR, where users progressively refine their search intent.<n>We propose ReCoVR (Reflexive Composed Video Retrieval), a dual-pathway architecture built on reflexive perception.
• Score: 26.019146002897724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Composed video retrieval (CoVR) searches for target videos using a reference video and a modification text, but existing methods are restricted to a single interaction round and cannot support the progressive nature of real-world visual search. To bridge this gap, we first formalize interactive composed video retrieval, a multi-turn extension of CoVR, where users progressively refine their search intent through natural-language feedback across turns. Adapting existing interactive retrieval methods to this setting reveals two structural weaknesses: reliance on a single retrieval channel and an open-loop retrieval design that consumes user feedback but does not diagnose whether its own retrieval trajectory is drifting or stagnating. To address these limitations, we propose ReCoVR (Reflexive Composed Video Retrieval), a dual-pathway architecture built on reflexive perception, where the system treats its retrieval history as diagnostic evidence alongside user feedback. Specifically, an Intent Pathway routes heterogeneous feedback to complementary retrieval channels, while a Reflection Pathway performs trajectory-level reflection to monitor result evolution and correct retrieval errors across turns. Experiments on multiple benchmarks show that ReCoVR consistently outperforms interactive baselines, notably achieving 74.30% R@1 after just one interactive round on the WebVid-CoVR-Test dataset.

Related papers

• 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)
• ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval [19.132505747414]
  This research aims to solve the challenge of video retrieval from massive datasets, caused by ambiguous user queries.<n>The root cause is the "Intent-Query Gap", where users' intent cannot be captured by a simple text query.<n>We propose the ADEPT framework: a training-free agent that pioneers an entropy-driven decision engine.
  arXiv  Detail & Related papers  (2026-05-07T14:00:16Z)
• Interactive Multi-Turn Retrieval for Health Videos [8.02912741133541]
  We introduce interactive multi-turn semantic retrieval for health videos and construct MHVRC, a Multi-Turn Health Video Retrieval Corpus.<n>We propose DATR, a Dialogue-Aware Two-Stage Retrieval framework.<n>Experiments on MHVRC show consistent gains over strong text-video retrieval baselines.
  arXiv  Detail & Related papers  (2026-05-02T12:12:07Z)
• ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval [24.278296673415827]
  Composed Video Retrieval (CVR) has emerged as a novel paradigm in video retrieval.<n>Traditional composition methods tend to bias the composed feature toward the reference video.<n>ReTrack is the first CVR framework that improves multi-modal query understanding by calibrating directional bias in composed features.
  arXiv  Detail & Related papers  (2026-04-20T07:17:59Z)
• RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval [99.33724613432922]
  We introduce RANKVIDEO, a reasoning-based reranker for video retrieval.<n>RANKVIDEO explicitly reasons over query-video pairs using video content to assess relevance.<n> Experiments on the large-scale MultiVENT 2.0 benchmark demonstrate that RANKVIDEO consistently improves retrieval performance within a two-stage framework.
  arXiv  Detail & Related papers  (2026-02-02T18:40:37Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• 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)
• Simple Baselines for Interactive Video Retrieval with Questions and Answers [33.17722358007974]
  We propose several simple yet effective baselines for interactive video retrieval via question-answering. We employ a VideoQA model to simulate user interactions and show that this enables the productive study of the interactive retrieval task. Experiments on MSR-VTT, MSVD, and AVSD show that our framework using question-based interaction significantly improves the performance of text-based video retrieval systems.
  arXiv  Detail & Related papers  (2023-08-21T00:32:19Z)
• Video Corpus Moment Retrieval with Contrastive Learning [56.249924768243375]
  Video corpus moment retrieval (VCMR) is to retrieve a temporal moment that semantically corresponds to a given text query. We propose a Retrieval and Localization Network with Contrastive Learning (ReLoCLNet) for VCMR. Experimental results show that ReLoCLNet encodes text and video separately for efficiency, its retrieval accuracy is comparable with baselines adopting cross-modal interaction learning.
  arXiv  Detail & Related papers  (2021-05-13T12:54:39Z)

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.