A list of research papers on knowledge-enhanced multimodal learning
-
Updated
Dec 8, 2022
A list of research papers on knowledge-enhanced multimodal learning
Python Implementation of lexical vector embedding similarity scoring, zero-shot classification of images and n-gram based scoring to compare textual summaries
[TIP2024] The code of “Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching”
A simple open-sourced SigLIP model finetuned on Genshin Impact's image-text pairs.
BSs Graduation Project implementation [Image-Text Matching]
The Unified Code of Image-Text Retrieval for Further Exploration.
The 3rd place solution code for the Wikipedia - Image/Caption Matching Competition on Kaggle
Implementation of the "Learn No to Say Yes Better" paper.
Easy wrapper for inserting LoRA layers in CLIP.
Code implementation of paper "SEMScene: Semantic-Consistency Enhanced Multi-Level Scene Graph Matching for Image-Text Retrieval" (ACM TOMM 2024).
Cross-modal Retrieval using Transformer Encoder Reasoning Networks (TERN). With use of Metric Learning and FAISS for fast similarity search on GPU
Text Query based Traffic Video Event Retrieval with Global-Local Fusion Embedding
Noise of Web (NoW) is a challenging noisy correspondence learning (NCL) benchmark containing 100K image-text pairs for robust image-text matching/retrieval models.
[ICML 2024] Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
Image-Text Matching Model Zoo
Extended COCO Validation (ECCV) Caption dataset (ECCV 2022)
Official implementation and dataset for the NAACL 2024 paper "ComCLIP: Training-Free Compositional Image and Text Matching"
Unofficial code of paper "Improving description-based person re-identification by multi-granularity image-text alignment." by Niu et al. (partially implemented)
A dead-simple image search and image-text matching system for Bangla using CLIP
Add a description, image, and links to the image-text-matching topic page so that developers can more easily learn about it.
To associate your repository with the image-text-matching topic, visit your repo's landing page and select "manage topics."