feature extraction from speech signals

Steps in assessing stress using speech include,actively recording an audio. And various features of the audio signal (e.g., pitch, jitter, energy, speaking rate, length, and number of pauses) are t…

This library provides common speech features for ASR including MFCCs and filterbank energies.

Image-based estimation of the heart ventricular volume using deep learning and Gaussian process

Capstone Project for Columbia MSDS Program with Dr.Hemant Palivela

Code for "Aligning Linguistic Words and Visual Semantic Units for Image Captioning", ACM MM 2019

DSMT-Net code

Histopathological Image Classification with Cell Morphology Aware Deep Neural Networks

This is the code for "Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance"

Final Project for Duke University BME590D: Deep Learning Applications in Healthcare

Paper Reading Notes

The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].

A Tensorflow implementation of the paper arXiv:1604.03539

Code repository for Ahn et al (2023) "Co-attention spatial transformer network for unsupervised motion tracking and cardiac strain analysis in 3D echocardiography" Medical Image Analysis

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

Use PEFT or Full-parameter to finetune 300+ LLMs or 60+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

基于LLaVA1.6微调的Xray识别的多模态大模型

Integrated Image-based Deep Learning and Language Models for Primary Diabetes Care

EVA Series: Visual Representation Fantasies from BAAI

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

This repo holds the code for: {Transformer-based Spatio-temporal Analysis for Automatic Classification of Aortic Stenosis Severity from B-mode Ultrasound Cine Series}.

The implemented code of RAMEM, Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels.

Model Code Implementation in Keras from the ConFormer Research Paper

Deformable DETR: Deformable Transformers for End-to-End Object Detection.