SOTAVerified

Cross-Modal Information Retrieval

Cross-Modal Information Retrieval (CMIR) is the task of finding relevant items across different modalities. For example, given an image, find a text or vice versa. The main challenge in CMIR is known as the heterogeneity gap: since items from different modalities have different data types, the similarity between them cannot be measured directly. Therefore, the majority of CMIR methods published to date attempt to bridge this gap by learning a latent representation space, where the similarity between items from different modalities can be measured.

Source: Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 16 papers

TitleStatusHype
VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-wordsCode1
Learning the Best Pooling Strategy for Visual Semantic EmbeddingCode1
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer EncodersCode1
jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images—0
LILE: Look In-Depth before Looking Elsewhere -- A Dual Attention Network using Transformers for Cross-Modal Information Retrieval in Histopathology Archives—0
VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval—0
Modeling Text with Graph Convolutional Network for Cross-Modal Information Retrieval—0
Multi-modal Machine Learning in Engineering Design: A Review and Future Directions—0
Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering—0
Multimodal Representation Alignment for Cross-modal Information Retrieval—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.