MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval

• URL: http://arxiv.org/abs/2603.17360v1
• Date: Wed, 18 Mar 2026 04:49:19 GMT
• Title: MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval
• Abstract summary: Composed Image Retrieval (CIR) aims to retrieve target images based on a reference image and modified texts.<n>We propose a novel Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning (MCoT-MVS) for CIR.
• Score: 23.52156477012636
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Composed Image Retrieval (CIR) aims to retrieve target images based on a reference image and modified texts. However, existing methods often struggle to extract the correct semantic cues from the reference image that best reflect the user's intent under textual modification prompts, resulting in interference from irrelevant visual noise. In this paper, we propose a novel Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning (MCoT-MVS) for CIR, integrating attention-aware multi-level vision features guided by reasoning cues from a multi-modal large language model (MLLM). Specifically, we leverage an MLLM to perform chain-of-thought reasoning on the multimodal composed input, generating the retained, removed, and target-inferred texts. These textual cues subsequently guide two reference visual attention selection modules to selectively extract discriminative patch-level and instance-level semantics from the reference image. Finally, to effectively fuse these multi-granular visual cues with the modified text and the imagined target description, we design a weighted hierarchical combination module to align the composed query with target images in a unified embedding space. Extensive experiments on two CIR benchmarks, namely CIRR and FashionIQ, demonstrate that our approach consistently outperforms existing methods and achieves new state-of-the-art performance. Code and trained models are publicly released.

Related papers

• LoMo: Local Modality Substitution for Deeper Vision-Language Fusion [10.837487434757882]
  Local Modality Substitution (LoMo) is a lightweight, architecture-agnostic data curation paradigm designed to provide supervision for cross-modal representational invariance between semantically equivalent text and image carriers.<n>LoMo significantly improves overall multimodal reasoning and yields deeper cross-modal fusion. Specifically, it delivers consistent gains across foundational models, improving over standard SFT by 2.67 points on LLaVA-Vision-1.5-8B and 2.82 points on Qwen3.5-9B.
  arXiv  Detail & Related papers  (2026-05-28T17:27:55Z)
• Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation [22.845591588026366]
  We propose a framework that provides explicit, structured supervision from high-level concepts to fine-grained appearances.<n>At the conceptual level, we introduce a VAE dropout training strategy that randomly omits reference VAE features.<n>At the appearance level, we integrate the VLM-derived correspondences into a correspondence-aware masked attention module.
  arXiv  Detail & Related papers  (2026-02-03T12:13:29Z)
• QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models [50.51641024244313]
  We investigate how current prompting methods perceive fine-grained visual details and process visual information when dealing with multiple images.<n>Inspired by the findings, we propose a new zero-shot prompting method, Question-Guided Chain-of-Captions (QG-CoC)<n>We evaluate our method on various open-source and closed-source MLLMs for multi-image and single-image benchmarks.
  arXiv  Detail & Related papers  (2025-11-05T05:49:48Z)
• Query-Kontext: An Unified Multimodal Model for Image Generation and Editing [53.765351127477224]
  Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I)<n>We introduce Query-Kontext, a novel approach that bridges the VLM and diffusion model via a multimodal kontext'' composed of semantic cues and coarse-grained image conditions encoded from multimodal inputs.<n> Experiments show that our approach matches strong unified baselines and even outperforms task-specific state-of-the-art methods in several cases.
  arXiv  Detail & Related papers  (2025-09-30T17:59:46Z)
• From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning [27.117102717184597]
  Multi-image Interleaved Reasoning aims to improve Multi-modal Large Language Models (MLLMs) ability to jointly comprehend and reason across multiple images and their associated textual contexts.<n>MIR requires joint reasoning over multiple images accompanied by interleaved textual contexts to accurately associate image regions with corresponding texts.<n>Our method significantly enhances models reasoning performance on MIR benchmarking and other established benchmarks.
  arXiv  Detail & Related papers  (2025-09-21T11:19:02Z)
• MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval [32.33545237942899]
  Composed Image Retrieval (CIR) is the task of retrieving a target image from a gallery using a reference image and a modification text.<n>We propose Chain-of-Thought with re-ranking (MCoT-RE) as a training-free zero-shot CIR framework.
  arXiv  Detail & Related papers  (2025-07-17T06:22:49Z)
• Visual Semantic Description Generation with MLLMs for Image-Text Matching [7.246705430021142]
  We propose a novel framework that bridges the modality gap by leveraging multimodal large language models (MLLMs) as visual semantics.<n>Our approach combines: (1) Instance-level alignment by fusing visual features with VSD to enhance the linguistic expressiveness of image representations, and (2) Prototype-level alignment through VSD clustering to ensure category-level consistency.
  arXiv  Detail & Related papers  (2025-07-11T13:38:01Z)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• OVMR: Open-Vocabulary Recognition with Multi-Modal References [96.21248144937627]
  Existing works have proposed different methods to embed category cues into the model, eg, through few-shot fine-tuning. This paper tackles open-vocabulary recognition from a different perspective by referring to multi-modal clues composed of textual descriptions and exemplar images. The proposed OVMR is a plug-and-play module, and works well with exemplar images randomly crawled from the Internet.
  arXiv  Detail & Related papers  (2024-06-07T06:45:28Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• Two-stage Visual Cues Enhancement Network for Referring Image Segmentation [89.49412325699537]
  Referring Image (RIS) aims at segmenting the target object from an image referred by one given natural language expression. In this paper, we tackle this problem by devising a Two-stage Visual cues enhancement Network (TV-Net) Through the two-stage enhancement, our proposed TV-Net enjoys better performances in learning fine-grained matching behaviors between the natural language expression and image.
  arXiv  Detail & Related papers  (2021-10-09T02:53:39Z)

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.