Papers with Code 아카이브
Composed Image Retrieval (CoIR)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 2
Composed Image Retrieval (CoIR) is the task involves retrieving images from a large database based on a query composed of multiple elements, such as text, images, and sketches. The goal is to develop algorithms that can understand and combine multiple sources of information to accurately retrieve images that match the query, extending the user’s expression ability.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval
CoLLM: A Large Language Model for Composed Image Retrieval
Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning
Data-Efficient Generalization for Zero-shot Composed Image Retrieval
CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval
PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrieval
SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Composed Image Retrieval for Training-Free Domain Conversion
Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
MoTaDual: Modality-Task Dual Alignment for Enhanced Zero-shot Composed Image Retrieval
Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval
Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval
Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
Composed Image Retrieval for Remote Sensing
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking
Language-only Efficient Training of Zero-shot Composed Image Retrieval
Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
Vision-by-Language for Training-Free Compositional Image Retrieval
Sentence-level Prompts Benefit Composed Image Retrieval
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
CoVR-2: Automatic Data Construction for Composed Video Retrieval
GeneCIS: A Benchmark for General Conditional Image Similarity
Zero-shot Composed Text-Image Retrieval
Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
Bi-directional Training for Composed Image Retrieval via Text Prompt Learning
Zero-Shot Composed Image Retrieval with Textual Inversion
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.