Papers Zero-Shot Composed Image Retrieval (ZS-CIR)
“Zero-Shot Composed Image Retrieval (ZS-CIR)” 태그가 달린 논문 36편 · 필터 해제
MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval
Existing Zero-Shot Composed Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens, which are concatenated with the modifying text and processed by frozen text enc…
Image RetrievalLarge Language ModelMultimodal Large Language ModelRetrieval+2Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval
Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a compositional query, consisting of a reference image and a modifying text-without relying on annotated training data. Existing approaches…
Contrastive LearningImage RetrievalMultimodal ReasoningRetrieval+1CoLLM: A Large Language Model for Composed Image Retrieval
Composed Image Retrieval (CIR) is a complex task that aims to retrieve images based on a multimodal query. Typical training data consists of triplets containing a reference image, a textual description of desired modific…
Image RetrievalLanguage ModelingLanguage ModellingLarge Language Model+3Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent across domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to modify a r…
AttributeImage RetrievalZero-Shot Composed Image Retrieval (ZS-CIR)ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning
With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the de…
Image RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)Data-Efficient Generalization for Zero-shot Composed Image Retrieval
Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve the target image based on a reference image and a text description without requiring in-distribution triplets for training. One prevalent approach follows the …
Image RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval
Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images by integrating information from a composed query (reference image and modification text) without training samples. Existing methods primarily com…
Image RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrieval
Zero-shot composed image retrieval (ZS-CIR) enables image search using a reference image and text prompt without requiring specialized text-image composition networks trained on large-scale paired data. However, current …
Image RetrievalRetrievalSemantic SimilaritySemantic Textual Similarity+1SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval
Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds applications in a variety of domains inc…
Image RetrievalRetrievalTripletZero-Shot Composed Image Retrieval (ZS-CIR)MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
Despite the rapidly growing demand for multimodal retrieval, progress in this field remains severely constrained by a lack of training data. In this paper, we introduce MegaPairs, a novel data synthesis method that lever…
Image RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Composed Image Retrieval (CIR) aims to retrieve target images that closely resemble a reference image while integrating user-specified textual modifications, thereby capturing user intent more precisely. Existing trainin…
Image RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)Composed Image Retrieval for Training-Free Domain Conversion
This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text. We show that a strong vision-language model pro…
Image RetrievalLanguage ModelingLanguage ModellingRetrieval+1Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
The Zero-shot Composed Image Retrieval (ZSCIR) requires retrieving images that match the query image and the relative captions. Current methods focus on projecting the query image into the text feature space, subsequentl…
Image RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)MoTaDual: Modality-Task Dual Alignment for Enhanced Zero-shot Composed Image Retrieval
Composed Image Retrieval (CIR) is a challenging vision-language task, utilizing bi-modal (image+text) queries to retrieve target images. Despite the impressive performance of supervised CIR, the dependence on costly, man…
Image RetrievalPrompt LearningRetrievalTriplet+1Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval
Zero-Shot Composed Image Retrieval (ZS-CIR) has attracted more attention in recent years, focusing on retrieving a specific image based on a query composed of a reference image and a relative text without training sample…
Image RetrievalImage to textRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval
Zero-Shot Composed Image Retrieval (ZS-CIR) supports diverse tasks with a broad range of visual content manipulation intentions that can be related to domain, scene, object, and attribute. A key challenge for ZS-CIR is t…
AttributeDenoisingImage RetrievalRetrieval+2Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
Composed image retrieval (CIR), which formulates the query as a combination of a reference image and modified text, has emerged as a new form of image search due to its enhanced ability to capture user intent. However, t…
Image CaptioningImage RetrievalRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
Zero-Shot Composed Image Retrieval (ZS-CIR) has garnered increasing interest in recent years, which aims to retrieve a target image based on a query composed of a reference image and a modification text without training …
Image RetrievalImage to textRetrievalZero-Shot Composed Image Retrieval (ZS-CIR)An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable image searches. The mainstream Zero-Shot (ZS) CIR methods bypass the need for expensi…
Contrastive LearningImage RetrievalRetrievalTriplet+1Composed Image Retrieval for Remote Sensing
This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descriptive power over unimodal queries, eith…
Composed Image Retrieval (CoIR)DescriptiveImage RetrievalLanguage Modeling+3