Lune

CVPR2026Top-tier venue

Compositional Transformation Reasoning for Composed Video Retrieval

Sihong Huang, Jiaxin Wu, Dongmei Jiang, Yi Cai, Yaowei Wang, Xiaoyong Wei

Abstract

Composed Video Retrieval aims to retrieve a target video given a reference video and a textual modification describing the desired change. The core challenge lies in modeling compositional multimodal transformations, i.e., how entities, actions, and scenes evolve across video and language modalities in response to fine-grained textual edits. Existing methods address this issue by training on large-scale video-text-video triplets or by generating dense textual descriptions to capture subtle visual differences. However, these supervised approaches often rely on noisy web-scale data and dataset-specific correspondences, leading to overfitting and limited generalization in diverse or fine-grained scenarios, while also failing to effectively model compositional and temporal transformations. We propose Multiobjective Reasoning (MoRe), a zero-shot framework based on MLLMs for multi-objective candidate selection and finegrained transformation reasoning. Our method decomposes the compositional transformation into three complementary reasoning dimensions, i.e., entity, action, and scene, and performs pairwise candidate reasoning to explicitly capture semantic evolution over time. Furthermore, we introduce a recall-oriented multi-objective candidate selection module that identifies high-quality retrieval targets by jointly balancing visual, textual, and multimodal similarities before transformation reasoning. Experiments on EgoCVR and WebVid-CoVR demonstrate the effectiveness of our method over state-of-the-art approaches under the zero-shot setting, with R@1 improvements of +5.8 and +10.8, respectively.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation cites Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
  • BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation cites Learning Transferable Visual Models From Natural Language Supervision
  • Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval cites Learning Transferable Visual Models From Natural Language Supervision
  • MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on18

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 6,549 citations
  3. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language ModelsDeyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li et al.ICLR 2024 · 3,079 citations
  4. Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalMax Bain, Arsha Nagrani, Gül Varol, Andrew ZissermanICCV 2021 · 1,550 citations
  5. Ego4D: Around the World in 3, 000 Hours of Egocentric VideoKristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis et al.CVPR 2022 · 525 citations

Related papers

  1. Composed Video Retrieval via Enriched Context and Discriminative EmbeddingsOmkar Thawakar, Muzammal Naseer, Rao Muhammad Anwer, Salman H. Khan et al.CVPR 2024 · 10 citations
  2. Beyond Simple Edits: Composed Video Retrieval with Dense ModificationsOmkar Thawakar, Dmitry Demidov, Ritesh Thawkar, Rao Muhammad Anwer et al.ICCV 2025 · 2 citations
  3. CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image RetrievalZelong Sun, Dong Jing, Zhiwu LuICCV 2025 · 5 citations
  4. ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video RetrievalZixu Li, Yupeng Hu, Zhiwei Chen, Qinlei Huang et al.AAAI 2026 · 24 citations
  5. ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image RetrievalTianyu Yang, ChenWei He, Xiangzhao Hao, Tianyue Wang et al.CVPR 2026 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines