Papers with Code 아카이브

Cross-Modal Retrieval

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 5
평가표: 13
보존된 평가 기록: 111

Cross-Modal Retrieval (CMR) is a task of retrieving items across different modalities, such as image, text, video, and audio. The core challenge of CMR is the heterogeneity gap, which arises because data from different modalities have distinct representations, making direct comparison difficult. To address this, most CMR methods focus on learning a shared latent embedding space. In this space, concepts from different modalities are projected, allowing their similarity to be measured using a distance metric.

Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Cross-Modal Retrieval

논문

An analysis of vision-language models for fabric retrieval

Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval

Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval

Multimodal Medical Image Binding via Shared Text Embeddings

ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025

FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models

Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models

SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking

EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast

FOLIAGE: Towards Physical Intelligence World Models Via Unbounded Surface Evolution

DocMMIR: A Framework for Document Multi-modal Information Retrieval

TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP

GMM-Based Comprehensive Feature Extraction and Relative Distance Preservation For Few-Shot Cross-Modal Retrieval

SMOTExT: SMOTE meets Large Language Models

Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping

Towards Cross-modal Retrieval in Chinese Cultural Heritage Documents: Dataset and Solution

Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner

CellCLIP -- Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning

Descriptive Image-Text Matching with Graded Contextual Similarity

MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval

Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models

Compositional Image-Text Matching and Retrieval by Grounding Entities

Disentangling and Generating Modalities for Recommendation in Missing Modality Scenarios

The 1st EReL@MIR Workshop on Efficient Representation Learning for Multimodal Information Retrieval

Improving Sound Source Localization with Joint Slot Attention on Image and Audio

SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs

Instruction-augmented Multimodal Alignment for Image-Text and Element Matching

Dependency Structure Augmented Contextual Scoping Framework for Multimodal Aspect-Based Sentiment Analysis

PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage

Learning Sparse Disentangled Representations for Multimodal Exclusion Retrieval

FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs

LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text

Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes

PromptHash: Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval

Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology