# Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval

arXiv: https://arxiv.org/abs/2609.10008 · HTML: https://mlsanity.com/paper/2609.10008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 52 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents](https://mlsanity.com/paper/2507.04590/) (2025)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [CoVR-2: Automatic Data Construction for Composed Video Retrieval](https://mlsanity.com/paper/2308.14746/) (2023)
- [ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval](https://mlsanity.com/paper/2604.17898/) (2026)
- [HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval](https://mlsanity.com/paper/2512.02792/) (2025)
- [Composed Video Retrieval via Enriched Context and Discriminative Embeddings](https://mlsanity.com/paper/2403.16997/) (2024)
- [Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval](https://mlsanity.com/paper/2505.19650/) (2025)
- [EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval](https://mlsanity.com/paper/2407.16658/) (2024)
- [CoLLM: A Large Language Model for Composed Image Retrieval](https://mlsanity.com/paper/2503.19910/) (2025)
- [Lost in Embeddings: Information Loss in Vision-Language Models](https://mlsanity.com/paper/2509.11986/) (2025)
- [CoVR-R:Reason-Aware Composed Video Retrieval](https://mlsanity.com/paper/2603.20190/) (2026)
- [Beyond Simple Edits: Composed Video Retrieval with Dense Modifications](https://mlsanity.com/paper/2508.14039/) (2025)
- [MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2505.19707/) (2025)
- [A Benchmark for Omni-Modal Reasoning in Long Videos](https://mlsanity.com/paper/2512.16978/) (2025)
- [R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking](https://mlsanity.com/paper/2606.01113/) (2026)
- [The Embedder's Dilemma: LLMs Are Better, but at What Cost?](https://mlsanity.com/paper/2608.12875/) (2026)
- [From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos](https://mlsanity.com/paper/2506.05274/) (2025)
- [VeRVE: Versatile Retrieval for Videos via Unified Embeddings](https://mlsanity.com/paper/2601.12193/) (2026)
- [CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content](https://mlsanity.com/paper/2601.22508/) (2026)
- [UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval](https://mlsanity.com/paper/2604.20318/) (2026)

## Abstract (arXiv)

Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gallery scale, this creates a fundamental tension: compact embeddings enable efficient, reusable search but can miss the transient actions, state changes, and subtle constraints that demand fine-grained video reasoning, whereas applying large multimodal models uniformly sacrifices scalability. To address these limitations, we propose that frozen foundation models should instead occupy complementary roles, with inference depth adapted to query difficulty. Based on this premise, we introduce methodname, a framework for training-free methodexpansion. Specifically, a composed-query embedding first searches reusable video-only gallery representations; uncertain queries undergo bounded reranking and candidate expansion; ambiguous edits trigger target-description generation; and only close leading candidates reach multimodal verification. To support these roles, frame selection, spatial resolution, and time cues are adapted to each stage. Across complete target-gallery evaluations, our method reaches state-of-the-art performance among training-free approaches, with 89.55 and 93.43 R@1 on Dense-WebVid-CoVR and CoVR-R, respectively (with more than +35% and +25% absolute margins to the closest counterpart). These results show that adaptively orchestrating foundation-model capabilities can combine scalable retrieval with fine-grained reasoning without task-specific training. The source code and all relevant guidelines are available on https://github.com/demidovd98/CoVRAGE.