Papers Image-text matching
“Image-text matching” 태그가 달린 논문 214편 · 필터 해제
Variational Adapter for Cross-modal Similarity Representation
The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching or multi-class image classification datasets lack fine-grained cross-mo…
Domain GeneralizationBinary ClassificationImage ClassificationImage-text matchingTempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an implicit assumption from image-text retrieval: that visual semantics can b…
Video-Text RetrievalImage-text matchingVideo RetrievalMSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation
Evaluating image captions without references remains challenging because global embedding similarity often misses fine-grained mismatches such as hallucinated objects, missing attributes, or incorrect relations. We propo…
Image-text matchingHarnessing Weak Pair Uncertainty for Text-based Person Search
In this paper, we study the text-based person search, which is to retrieve the person of interest via natural language description. Prevailing methods usually focus on the strict one-to-one correspondence pair matching b…
Contrastive LearningImage-text matchingPerson SearchDBMF: A Dual-Branch Multimodal Framework for Out-of-Distribution Detection
The complex and dynamic real-world clinical environment demands reliable deep learning (DL) systems. Out-of-distribution (OOD) detection plays a critical role in enhancing the reliability and generalizability of DL model…
Out-of-Distribution DetectionImage-text matchingHidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning
Contrastive learning has become a standard approach for unsupervised learning from paired data, as demonstrated by CLIP for image-text matching. However, many domains involve more than two modalities and require objectiv…
Cross-Modal RetrievalContrastive LearningImage-text matchingOpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery
Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined classes. We reformulate OVCD as a two-stage pipeline: first generate cl…
Image-text matchingChange DetectionLocal-Global Prompt Learning via Sparse Optimal Transport
Few-shot adaptation of vision-language models (VLMs) like CLIP typically relies on learning textual prompts matched to global image embeddings. Recent works extend this paradigm by incorporating local image-text alignmen…
Image-text matchingPseudo Contrastive Learning for Diagram Comprehension in Multimodal Models
Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large se…
Visual Question AnsweringContrastive LearningImage-text matchingReText: Text Boosts Generalization in Image-Based Person Re-identification
Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining. While multiple existing approaches address the domain gap through complex arch…
Person Re-IdentificationImage ReconstructionImage-text matchingLeveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction
Selective prediction aims to endow predictors with a reject option, to avoid low confidence predictions. However, existing literature has primarily focused on closed-set tasks, such as visual question answering with pred…
Visual Question AnsweringImage-text matchingImage CaptioningABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable performance in various multimodal tasks. However, it still struggles with compositional image-text matching, particularly in accurately associating ob…
Image-text matchingImage Complexity-Aware Adaptive Retrieval for Efficient Vision-Language Models
Vision transformers in vision-language models typically use the same amount of compute for every image, regardless of whether it is simple or complex. We propose ICAR (Image Complexity-Aware Retrieval), an adaptive compu…
Image-text matchingHybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval
Text-based person anomaly retrieval has emerged as a challenging task, with most existing approaches relying on complex deep-learning techniques. This raises a research question: How can the model be optimized to achieve…
Image-text matchingUnleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition
Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while und…
parameter-efficient fine-tuningImage-text matchingATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP
Despite its remarkable success in zero-shot image-text matching, CLIP remains highly vulnerable to adversarial perturbations on images. As adversarial fine-tuning is prohibitively costly, recent works explore various tes…
Image-text matchingLanguage-Guided Invariance Probing of Vision-Language Models
Recent vision-language models (VLMs) such as CLIP, OpenCLIP, EVA02-CLIP and SigLIP achieve strong zero-shot performance, but it is unclear how reliably they respond to controlled linguistic perturbations. We introduce La…
Image-text matchingGPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data
Compared to the prosperity of pre-training models in natural image understanding, the research on large-scale pre-training models for facial knowledge learning is still limited. Current approaches mainly rely on manually…
Image-text matchingText GenerationMSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection
Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, all…
Object LocalizationImage-text matchingScene UnderstandingObject DetectionStructure-aware Contrastive Learning for Diagram Understanding of Multimodal Models
Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when …
Visual Question AnsweringContrastive LearningImage-text matching