The official code of "Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark"
[ICML 2024] "Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models"
Official implementation of "Meta-Entity Driven Triplet Mining for Aligning Medical Vision-Language Models"
The official code of "Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval"
Fusion at the Foregut: CLIP-Based Prototypical Learning with DINOv2 Refinement for Endoscopic Image Analysis
Official implementation of ACE-LoRA
CLIP-based: Facial Language Image Pretraining Model (trained on FaceCation-15M) (Under Review)
Vision Transformer (ViT)-based pipeline for multimodal image knowledge extraction: fine-grained botanical taxonomy, cultural landmark recognition, and semantic object analysis. Combines pretrained ViTs, domain adapters, and generative language models to produce structured annotations, contextual metadata, and adaptive study resources. + RAG support
To associate your repository with the image-text-alignment topic, visit your repo's landing page and select "manage topics."