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 1–10 of 188 papers

TitleStatusHype
Efficient Medical Vision-Language Alignment Through Adapting Masked Vision ModelsCode1
TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP—0
Descriptive Image-Text Matching with Graded Contextual Similarity—0
Compositional Image-Text Matching and Retrieval by Grounding EntitiesCode0
Instruction-augmented Multimodal Alignment for Image-Text and Element Matching—0
Dependency Structure Augmented Contextual Scoping Framework for Multimodal Aspect-Based Sentiment Analysis—0
Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text MatchingCode2
CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIPCode1
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word EmphasisCode1
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations—0
Show:102550
← PrevPage 1 of 19Next →

No leaderboard results yet.