Stars
Official code for "Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation" (CVPR 2023)
Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024
Code for Group Critical-token Policy Optimization for Autoregressive Image Generation
[ECCV'2024] HERGen: Elevating Radiology Report Generation with Longitudinal Data
Implementation of “DreamDiffusion: Generating High-Quality Images from Brain EEG Signals”
A series of large language models developed by Baichuan Intelligent Technology
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in breast cancer treatment
MedViLL official code. (Published IEEE JBHI 2021)
BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
Multi-Aspect Vision Language Pretraining - CVPR2024
[NeurIPS'22] Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowe…
Offical code of Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training[ICML 2024]
HI-ML toolbox for deep learning for medical imaging and Azure integration
Dataset and baseline code for the VocalSound dataset (ICASSP2022).
Implements data-driven approaches for the detection of coughs in patients with respiratory illnesses.
Source code of the paper: AI-Generated Video Detection via Spatial-Temporal Anomaly Learning, PRCV 2024.
Created a model which localized important features of a image using Global Average Pooling. Implementation based on research paper ( https://goo.gl/J1OzEr ). Implementation done with tensorflow and…
[CVPR 2022 - Demo Track] - Effective conditioned and composed image retrieval combining CLIP-based features
[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
official implementation of rectified contrastive pseudo supervision