ReCoVR introduces a reflexive dual-pathway architecture for interactive composed video retrieval that outperforms baselines by combining intent routing with trajectory-level reflection on retrieval history.
Covr-r: Reason-aware composed video retrieval
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Composed Video Retrieval (CoVR) aims to find a target video given a reference video and a textual modification. Prior work assumes the modification text fully specifies the visual changes, overlooking after-effects and implicit consequences (e.g., motion, state transitions, viewpoint or duration cues) that emerge from the edit. We argue that successful CoVR requires reasoning about these after-effects. We introduce a reasoning-first, zero-shot approach that leverages large multimodal models to (i) infer causal and temporal consequences implied by the edit, and (ii) align the resulting reasoned queries to candidate videos without task-specific finetuning. To evaluate reasoning in CoVR, we also propose CoVR-Reason, a benchmark that pairs each (reference, edit, target) triplet with structured internal reasoning traces and challenging distractors that require predicting after-effects rather than keyword matching. Experiments show that our zero-shot method outperforms strong retrieval baselines on recall at K and particularly excels on implicit-effect subsets. Our automatic and human analysis confirm higher step consistency and effect factuality in our retrieved results. Our findings show that incorporating reasoning into general-purpose multimodal models enables effective CoVR by explicitly accounting for causal and temporal after-effects. This reduces dependence on task-specific supervision, improves generalization to challenging implicit-effect cases, and enhances interpretability of retrieval outcomes. These results point toward a scalable and principled framework for explainable video search. The model, code, and benchmark are available at https://github.com/mbzuai-oryx/CoVR-R.
citation-role summary
background 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
R^3 is a zero-shot pipeline that generates reasoning traces to augment composed video queries, fuses scores via agreement-gated residual, and re-ranks candidates for the CoVR-R challenge.
Training-free composed video retrieval pipeline using DINOv3 for candidate selection and video-LLM reasoning achieves 48.78 Recall@1 and 51.48 Recall@5 on the CVPR 2026 challenge test set.
Dual-route top-k retrieval with 1v1 VLM reranking reaches 95.28 R@1 on CoVR-R hidden test by merging text and DFN visual routes then using conservative pairwise VLM comparisons.
EgoAdapt improves VQA on the HD-EPIC egocentric benchmark via category-conditioned routing, calibrated option scoring, and test-time consistency adaptation.
TempRet enhances a CLIP dual-encoder with temporal modeling and two-stage reranking to report 67.97% mAP and 82.92% nDCG on the EK-100 MIR benchmark.
citing papers explorer
-
ReCoVR: Closing the Loop in Interactive Composed Video Retrieval
ReCoVR introduces a reflexive dual-pathway architecture for interactive composed video retrieval that outperforms baselines by combining intent routing with trajectory-level reflection on retrieval history.
-
R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking
R^3 is a zero-shot pipeline that generates reasoning traces to augment composed video queries, fuses scores via agreement-gated residual, and re-ranks candidates for the CoVR-R challenge.
-
Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning
Training-free composed video retrieval pipeline using DINOv3 for candidate selection and video-LLM reasoning achieves 48.78 Recall@1 and 51.48 Recall@5 on the CVPR 2026 challenge test set.
-
Dual-Route Top-K Retrieval with 1v1 VLM Reranking for the CoVR-R
Dual-route top-k retrieval with 1v1 VLM reranking reaches 95.28 R@1 on CoVR-R hidden test by merging text and DFN visual routes then using conservative pairwise VLM comparisons.
-
EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge
EgoAdapt improves VQA on the HD-EPIC egocentric benchmark via category-conditioned routing, calibrated option scoring, and test-time consistency adaptation.
-
TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
TempRet enhances a CLIP dual-encoder with temporal modeling and two-stage reranking to report 67.97% mAP and 82.92% nDCG on the EK-100 MIR benchmark.