paper-with-me

Image Retrieval

56개 벤치마크 · 논문 2,507편 · 이 태스크의 논문 보기 →

Benchmarks

ROxford (Hard)

결과 23개

ROxford (Medium)

결과 23개

RParis (Hard)

결과 23개

RParis (Medium)

결과 23개

Fashion IQ

결과 22개

CIRR

결과 19개

Flickr30K 1K test

결과 18개

SOP

결과 14개

Flickr30k-CN

결과 11개

Oxf5k

결과 11개

iNaturalist

결과 10개

COCO-CN

결과 9개

Flickr30k

결과 9개

MUGE Retrieval

결과 9개

Oxf105k

결과 9개

CARS196

결과 8개

CUB-200-2011

결과 8개

In-Shop

결과 7개

Par106k

결과 7개

Par6k

결과 7개

AmsterTime

결과 5개

ConQA Conceptual

결과 5개

ConQA Descriptive

결과 5개

PhotoChat

결과 5개

DeepPatent

결과 4개

24/7 Tokyo

결과 3개

Exact Street2Shop

결과 3개

LaSCo

결과 3개

MSCOCO

결과 3개

AIC-ICC

결과 2개

CBVS

결과 2개

INRIA Holidays

결과 2개

Oxford5k

결과 2개

Paris6k

결과 2개

WIT

결과 2개

street2shop - topwear

결과 2개

CIFAR-10

결과 1개

COFAR

결과 1개

DeepFashion

결과 1개

FETA Car-Manuals

결과 1개

FooDI-ML (Global)

결과 1개

FooDI-ML (Spain)

결과 1개

ICFG-PEDES

결과 1개

INSTRE

결과 1개

ImageCoDe

결과 1개

Localized Narratives

결과 1개

NUS-WIDE

결과 1개

PKU-Reid

결과 1개

RUC-CAS-WenLan

결과 1개

Most implemented

Papers

PailitaoGR: Latent Think-with-Images for Generative Image Retrieval

2026-08-27 · Xiaomeng Fan, Yueran Liu, Shengyu Zhou, Chenghan Fu 외 arxiv

Generative retrieval has demonstrated strong performance by directly generating product semantic identifiers (SIDs). Extending this paradigm to image search, however, is nontrivial because real-world query images contain…

Image Retrieval

Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching

2026-08-27 · Rong Shan, Tianyi Xu, Congmin Zheng, Wenteng Chen 외 hf

Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to capture the complexity of human search intent …

Image Retrieval

MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image Retrieval

2026-08-26 · Zihao Zhang, Dayan Wu, Xinze Liu, Hengjie Zhu 외 arxiv

Training-free zero-shot composed image retrieval finds a target image in a gallery from a reference image and a text edit without learning from task-specific image triplets. Existing methods typically describe the target…

Image Retrieval

EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking

2026-08-21 · Enjun Du, Siyi Liu, Zirong Chen, Xinyu Zuo 외 arxiv

Real-world image search queries are multimodal and compositional: ``find this shirt in pink'' specifies an entity to retain, an attribute to modify, and context to ignore. Yet existing re-rankers either compress such mul…

Image Retrieval

SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval

2026-08-19 · Zhenyao Cui, Siyuan Kan, Siyang Li, Ziwei Wang 외 arxiv

Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG), with potential for neural communication. However, cu…

Image Retrieval

Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval

2026-08-19 · Zhenyao Cui, Siyuan Kan, Dingkun Liu, Dongrui Wu arxiv

Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically …

Image Retrieval

전체 2,507편 보기 →