A PyTorch Computer Vision (CV) module library for building n-D networks flexibly ~

Video Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone

PyTorch Volume Models for 3D data

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

Code for NeuroImage: Clinical paper "Automatic post-stroke lesion segmentation on MR images using 3D residual convolutional neural network."

A module for creating 3D ResNets with different depths and additional features.

A rule-based algorithm enabled the automatic extraction of disease labels from tens of thousands of radiology reports. These weak labels were used to create deep learning models to classify multiple diseases for three different organ systems in body CT.

Human Facial Fatigue Detection through 3D ResNet with Non-local Attention

This repository contains the source codes for the paper: "PIP: Physical Interaction Prediction via Mental Simulation with Span Selection" published at ECCV 2022.

Given a video-clip we retrieve k-most similar to it from a "database". We extract features from 3 modalities (audio-video-text) and create an embedding using an AutoEncoder.

Visualizing 3D ResNet for Medical Image Classification With Score-CAM