Cross-Modal Information Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Cross-Modal Information Retrieval (CMIR) is the task of finding relevant items across different modalities. For example, given an image, find a text or vice versa. The main challenge in CMIR is known as the heterogeneity gap: since items from different modalities have different data types, the similarity between them cannot be measured directly. Therefore, the majority of CMIR methods published to date attempt to bridge this gap by learning a latent representation space, where the similarity between items from different modalities can be measured.
Source: 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.
Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models
Distilling Vision-Language Pretraining for Efficient Cross-Modal Retrieval
DEMO: A Statistical Perspective for Efficient Image-Text Matching
MVBIND: Self-Supervised Music Recommendation For Videos Via Embedding Space Binding
Global–Local Information Soft-Alignment for Cross-Modal Remote-Sensing Image–Text Retrieval
CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering
RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning
All in One Framework for Multimodal Re-identification in the Wild
COM3D: Leveraging Cross-View Correspondence and Cross-Modal Mining for 3D Retrieval
Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models
Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching
Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting
Anchor-aware Deep Metric Learning for Audio-visual Retrieval
Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding
Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning
Bridging Vision and Language Spaces with Assignment Prediction
Knowledge-enhanced Visual-Language Pretraining for Computational Pathology
SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues
Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models
Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining
VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition
A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels
NAC: Mitigating Noisy Correspondence in Cross-Modal Matching Via Neighbor Auxiliary Corrector
RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training
Improving Medical Multi-modal Contrastive Learning with Expert Annotations
REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence
Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
Large Language Models are In-Context Molecule Learners
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Tri-Modal Motion Retrieval by Learning a Joint Embedding Space
Image-Text Matching with Multi-View Attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.