SOTAVerified

Image-text matching

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–188 of 188 papers

TitleStatusHype
UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training—0
Macroscopic Control of Text Generation for Image Captioning—0
Similarity Reasoning and Filtration for Image-Text MatchingCode1
VinVL: Revisiting Visual Representations in Vision-Language ModelsCode2
Learning Dual Semantic Relations with Graph Attention for Image-Text MatchingCode1
MedICaT: A Dataset of Medical Images, Captions, and Textual ReferencesCode1
Universal Weighting Metric Learning for Cross-Modal MatchingCode1
Contrastive Cross-Modal Pre-Training: A General Strategy for Small Sample Medical Imaging—0
Consensus-Aware Visual-Semantic Embedding for Image-Text MatchingCode1
A Novel Attention-based Aggregation Function to Combine Vision and Language—0
Deep Multimodal Neural Architecture SearchCode1
Transformer Reasoning Network for Image-Text Matching and RetrievalCode1
Oscar: Object-Semantics Aligned Pre-training for Vision-Language TasksCode2
Text-Guided Neural Image InpaintingCode1
Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal TransformersCode1
More Grounded Image Captioning by Distilling Image-Text Matching ModelCode1
Graph Structured Network for Image-Text MatchingCode1
InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining—0
Adaptive Offline Quintuplet Loss for Image-Text MatchingCode1
Expressing Objects just like Words: Recurrent Visual Embedding for Image-Text Matching—0
ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data—0
Learning fragment self-attention embeddings for image-text matchingCode0
UNITER: Learning UNiversal Image-TExt Representations—0
UNITER: UNiversal Image-TExt Representation LearningCode1
Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators—0
Visual Semantic Reasoning for Image-Text MatchingCode1
VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsCode1
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training—0
Matching Images and Text with Multi-modal Tensor Fusion and Re-rankingCode0
Knowledge Aware Semantic Concept Expansion for Image-Text Matching—0
Position Focused Attention Network for Image-Text MatchingCode0
ParNet: Position-aware Aggregated Relation Network for Image-Text matching—0
Deep Cross-Modal Projection Learning for Image-Text MatchingCode0
Stacked Cross Attention for Image-Text MatchingCode1
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial NetworksCode1
Cross-modal Subspace Learning for Fine-grained Sketch-based Image Retrieval—0
Learning Two-Branch Neural Networks for Image-Text Matching TasksCode0
Dual Attention Networks for Multimodal Reasoning and MatchingCode0
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.