中文
相关论文

相关论文: MELT: Improve Composed Image Retrieval via the Mod…

200 篇论文

Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations. Existing CLIP-based methods face two core challenges: (1) union-based…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Yuqi Xiao , Yingying Zhu

We extend the task of composed image retrieval, where an input query consists of an image and short textual description of how to modify the image. Existing methods have only been applied to non-complex images within narrow domains, such as…

计算机视觉与模式识别 · 计算机科学 2021-08-10 Zheyuan Liu , Cristian Rodriguez-Opazo , Damien Teney , Stephen Gould

Composed Image Retrieval (CIR) uses a reference image plus a natural-language edit to retrieve images that apply the requested change while preserving other relevant visual content. Classic fusion pipelines typically rely on supervised…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Guoyizhe Wei , Yang Jiao , Nan Xi , Zhishen Huang , Jingjing Meng , Rama Chellappa , Yan Gao

As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality, and its key…

计算机视觉与模式识别 · 计算机科学 2023-01-18 Yan Zhang , Zhong Ji , Di Wang , Yanwei Pang , Xuelong Li

Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…

计算机视觉与模式识别 · 计算机科学 2025-10-10 Weihuang Lin , Yiwei Ma , Jiayi Ji , Xiaoshuai Sun , Rongrong Ji

Composed image retrieval (CIR) aims to retrieve a target image that depicts a reference image modified by a textual description. While recent vision-language models (VLMs) achieve promising CIR performance by embedding images and text into…

计算机视觉与模式识别 · 计算机科学 2026-04-13 François Gardères , Camille-Sovanneary Gauthier , Jean Ponce , Shizhe Chen

Composed Image Retrieval (CIR) allows users to search for images by combining a reference image with a text prompt that describes desired modifications. While vision-language models like CLIP have popularized this task by embedding multiple…

Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of annotating CIR triplet datasets, zero-shot (ZS) CIR has…

计算机视觉与模式识别 · 计算机科学 2025-04-28 Yabing Wang , Zhuotao Tian , Qingpei Guo , Zheng Qin , Sanping Zhou , Ming Yang , Le Wang

Existing single-image denoising algorithms often struggle to restore details when dealing with complex noisy images. The introduction of near-infrared (NIR) images offers new possibilities for RGB image denoising. However, due to the…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Yuchen Wang , Hongyuan Wang , Lizhi Wang , Xin Wang , Lin Zhu , Wanxuan Lu , Hua Huang

Composed Image Retrieval (CIR) involves retrieving a target image based on a composed query of an image paired with text that specifies modifications or changes to the visual reference. CIR is inherently an instruction-following task, as…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Wenliang Zhong , Weizhi An , Feng Jiang , Hehuan Ma , Yuzhi Guo , Junzhou Huang

Composed Image Retrieval (CIR) aims to retrieve target images from a gallery based on a reference image and modification text as a combined query. Recent approaches focus on balancing global information from two modalities and encode the…

计算机视觉与模式识别 · 计算机科学 2025-05-26 Yuxin Yang , Yinan Zhou , Yuxin Chen , Ziqi Zhang , Zongyang Ma , Chunfeng Yuan , Bing Li , Lin Song , Jun Gao , Peng Li , Weiming Hu

Image retrieval with hybrid-modality queries, also known as composing text and image for image retrieval (CTI-IR), is a retrieval task where the search intention is expressed in a more complex query format, involving both vision and text…

计算机视觉与模式识别 · 计算机科学 2022-04-26 Yida Zhao , Yuqing Song , Qin Jin

Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification. Current techniques rely on supervised learning for CIR models using labeled triplets of the reference image, text,…

计算机视觉与模式识别 · 计算机科学 2024-04-25 Young Kyun Jang , Donghyun Kim , Zihang Meng , Dat Huynh , Ser-Nam Lim

Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption that describes the difference between the two images. The high effort and cost required for labeling…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Alberto Baldrati , Lorenzo Agnolucci , Marco Bertini , Alberto Del Bimbo

As a challenging vision-language task, Zero-Shot Composed Image Retrieval (ZS-CIR) is designed to retrieve target images using bi-modal (image+text) queries. Typical ZS-CIR methods employ an inversion network to generate pseudo-word tokens…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Haiwen Li , Fei Su , Zhicheng Zhao

Semantic retrieval is crucial for modern applications yet remains underexplored in current research. Existing datasets are limited to single languages, single images, or singular retrieval conditions, often failing to fully exploit the…

Composed Image Retrieval (CIR) is a cross-modal task that aims to retrieve target images from large-scale databases using a reference image and a modification text. Most existing methods rely on a single model to perform feature fusion and…

图形学 · 计算机科学 2025-12-19 Yawei Cai , Jiapeng Mi , Nan Ji , Haotian Rong , Yawei Zhang , Zhangti Li , Wenbin Guo , Rensong Xie

Retrieval is being redefined by agentic AI, demanding multimodal reasoning beyond conventional similarity-based paradigms. Composed Image Retrieval (CIR) exemplifies this shift as each query combines a reference image with textual…

信息检索 · 计算机科学 2026-03-02 Zhongyu Yang , Wei Pang , Yingfang Yuan

Content Based Image Retrieval(CBIR) is one of the important subfield in the field of Information Retrieval. The goal of a CBIR algorithm is to retrieve semantically similar images in response to a query image submitted by the end user. CBIR…

信息检索 · 计算机科学 2014-09-03 Vikas Verma

Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Santhosh Kakarla , Gautama Shastry Bulusu Venkata