paper-with-me

Zero-Shot Composed Image Retrieval (ZS-CIR)

12개 벤치마크 · 논문 36편 · 이 태스크의 논문 보기 →

Benchmarks

CIRR

결과 94개

CIRCO

결과 86개

Fashion IQ

결과 82개

ImageNet-R

결과 40개

GeneCIS

결과 22개

ImageNet

결과 22개

MiniDomainNet

결과 12개

NICO++

결과 12개

PatternCom

결과 4개

FashionIQ

결과 2개

Most implemented

Papers

MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval

2025-05-26 · Rong-Cheng Tu, Zhao Jin, Jingyi Liao, Xiao Luo 외

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+2

Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval

2025-05-26 · Rong-Cheng Tu, Wenhao Sun, Hanzhe You, Yingjie Wang 외

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+1

CoLLM: A Large Language Model for Composed Image Retrieval

2025-03-25 · CVPR 2025 1 · Chuong Huynh, Jinyu Yang, Ashish Tawari, Mubarak Shah 외

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+3

Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval

2025-03-21 · CVPR 2025 1 · Yuanmin Tang, Jing Yu, Keke Gai, Jiamin Zhuang 외

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

2025-03-13 · Pengfei Luo, Jingbo Zhou, Tong Xu, Yuan Xia 외

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

2025-03-07 · Zining Chen, Zhicheng Zhao, Fei Su, Xiaoqin Zhang 외

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)

전체 36편 보기 →