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.
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
Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts
Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.