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 26–50 of 188 papers

TitleStatusHype
Evaluating Attribute Comprehension in Large Vision-Language ModelsCode0
Towards Deconfounded Image-Text Matching with Causal Inference—0
Dynamic and Compressive Adaptation of Transformers From Images to Videos—0
Image-text matching for large-scale book collectionsCode1
UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal MatchingCode1
Efficient and Long-Tailed Generalization for Pre-trained Vision-Language ModelCode0
Generative Visual Instruction TuningCode0
Composing Object Relations and Attributes for Image-Text MatchingCode1
Advanced Multimodal Deep Learning Architecture for Image-Text Matching—0
Hire: Hybrid-modal Interaction with Multiple Relational Enhancements for Image-Text Matching—0
DEMO: A Statistical Perspective for Efficient Image-Text Matching—0
CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering—0
RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning—0
Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching—0
Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text MatchingCode1
SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining—0
Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models—0
FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues—0
RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-trainingCode1
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal DatasetsCode0
Image-Text Matching with Multi-View Attention—0
ColorSwap: A Color and Word Order Dataset for Multimodal EvaluationCode1
MouSi: Poly-Visual-Expert Vision-Language ModelsCode2
Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided MaskingCode0
Enhancing Image-Text Matching with Adaptive Feature AggregationCode0
Show:102550
← PrevPage 2 of 8Next →

No leaderboard results yet.