SOTAVerified

Image-text Retrieval

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 248 papers

TitleStatusHype
Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval—0
Adding simple structure at inference improves Vision-Language CompositionalityCode0
FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model EvaluationCode2
Attacking Attention of Foundation Models Disrupts Downstream TasksCode0
Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation—0
EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models—0
Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval—0
Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models—0
A Vision-Language Foundation Model for Leaf Disease IdentificationCode0
FG-CLIP: Fine-Grained Visual and Textual AlignmentCode4
AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection—0
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs—0
FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations—0
Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language ModelsCode1
SeLIP: Similarity Enhanced Contrastive Language Image Pretraining for Multi-modal Head MRI—0
Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image AnalysisCode2
Anatomy-Aware Conditional Image-Text Retrieval—0
Variance-Aware Loss Scheduling for Multimodal Alignment in Low-Data Settings—0
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning—0
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations—0
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence LearningCode1
Progressive Local Alignment for Medical Multimodal Pre-training—0
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features—0
Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach—0
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal UnderstandingCode3
DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions—0
MASS: Overcoming Language Bias in Image-Text Matching—0
TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval—0
BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific LiteratureCode2
Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training—0
Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text RetrievalCode0
I0T: Embedding Standardization Method Towards Zero Modality GapCode1
Barking Up The Syntactic Tree: Enhancing VLM Training with Syntactic Losses—0
Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning—0
VladVA: Discriminative Fine-tuning of LVLMs—0
Approximate Fiber Product: A Preliminary Algebraic-Geometric Perspective on Multimodal Embedding Alignment—0
Knowledge Transfer Across Modalities with Natural Language Supervision—0
Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training—0
A Survey of Medical Vision-and-Language Applications and Their TechniquesCode1
Nearest Neighbor Normalization Improves Multimodal RetrievalCode1
Multilingual Vision-Language Pre-training for the Remote Sensing DomainCode0
GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric LearningCode0
CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning—0
AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models—0
From Unimodal to Multimodal: Scaling up Projectors to Align ModalitiesCode0
NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training—0
Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotations—0
Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation—0
PC^2: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal RetrievalCode1
FiCo-ITR: bridging fine-grained and coarse-grained image-text retrieval for comparative performance analysisCode0
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.