image-text-matching

Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.

Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine

The Paper List of Large Multi-Modality Model (Perception, Generation, Unification), Parameter-Efficient Finetuning, Vision-Language Pretraining, Conventional Image-Text Matching for Preliminary Insight.

[AAAI2021] The code of “Similarity Reasoning and Filtration for Image-Text Matching”

Code for "Learning the Best Pooling Strategy for Visual Semantic Embedding", CVPR 2021 (Oral)

Code for journal paper "Learning Dual Semantic Relations with Graph Attention for Image-Text Matching", TCSVT, 2020.

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"

Easy wrapper for inserting LoRA layers in CLIP.

A non-JIT version implementation / replication of CLIP of OpenAI in pytorch

Implementation of the "Learn No to Say Yes Better" paper.

[TIP2023] The code of “Plug-and-Play Regulators for Image-Text Matching”

Code implementation of paper "SEMScene: Semantic-Consistency Enhanced Multi-Level Scene Graph Matching for Image-Text Retrieval".

[ICML 2024] Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

Noise of Web (NoW) is a challenging noisy correspondence learning (NCL) benchmark containing 100K image-text pairs for robust image-text matching/retrieval models.

Text Query based Traffic Video Event Retrieval with Global-Local Fusion Embedding

A dead-simple image search / retrieval and image-text matching system for Bangla using CLIP

[TIP2024] The code of “Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching”

CLIP (Contrastive Language–Image Pre-training) for Bangla.

Unofficial code of paper "Improving description-based person re-identification by multi-granularity image-text alignment." by Niu et al. (partially implemented)