Image-text matching
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 8
Image-Text Matching is a subtask within Cross-Modal Retrieval (CMR) that involves establishing associations between images and corresponding textual descriptions. The goal is to retrieve an image given a textual query or, conversely, retrieve a textual description given an image query. This task is challenging due to the heterogeneity gap between image and text data representations. Image-text matching is used in applications such as content-based image search, visual question answering, and multimodal summarization.
Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer
GR-GAN: Gradual Refinement Text-to-image Generation
CCMB: A Large-scale Chinese Cross-modal Benchmark
Declaration-based Prompt Tuning for Visual Question Answering
Language Models Can See: Plugging Visual Controls in Text Generation
Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations
No Token Left Behind: Explainability-Aided Image Classification and Generation
ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO
DT2I: Dense Text-to-Image Generation from Region Descriptions
Two-stream Hierarchical Similarity Reasoning for Image-text Matching
Dual Embodied-Symbolic Concept Representations for Deep Learning
MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Unpaired Referring Expression Grounding via Bidirectional Cross-Modal Matching
Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation
Embedding Arithmetic of Multimodal Queries for Image Retrieval
DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching
MURAL: Multimodal, Multitask Retrieval Across Languages
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
Step-Wise Hierarchical Alignment Network for Image-Text Matching
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval
Towards Efficient Cross-Modal Visual Textual Retrieval using Transformer-Encoder Deep Features
More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching
VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching
Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching
UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training
Macroscopic Control of Text Generation for Image Captioning
Similarity Reasoning and Filtration for Image-Text Matching
VinVL: Revisiting Visual Representations in Vision-Language Models
Learning Dual Semantic Relations with Graph Attention for Image-Text Matching
MedICaT: A Dataset of Medical Images, Captions, and Textual References
Universal Weighting Metric Learning for Cross-Modal Matching
Contrastive Cross-Modal Pre-Training: A General Strategy for Small Sample Medical Imaging
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.