Official implementation of CrossViT. https://arxiv.org/abs/2103.14899

CVPR2020, Multi-scale Interactive Network for Salient Object Detection

This project explores the impact of Multi-Scale CNNs on the classification of EEG signals in Brain-Computer Interface (BCI) systems. By comparing the performance of two models, EEGNet and MSTANN, the study demonstrates how richer temporal feature extractions can enhance CNN models in classifying EEG signals

[TNNLS 2026] SvANet: Exploiting Scale-Variant Attention for Segmenting Small Medical Objects

[ICCV 2021] Official implementation of the paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering"

Nested U-Net with two-level skip connections for speech enhancement

The code of AGCN (Attention-driven Graph Clustering Network), which is accepted by ACM MM 2021.

Source Code for WeatherRemover (WeatherRemover: All-in-one Adverse Weather Removal with Multi-scale Feature Map Compression)

A lightweight multi-scale channel attention network for image super-resolution

Multi-Modal scene recognition using multi-scale encoded features (IMAVIS 2022)

A novel hybrid architecture combining CNNs and Swin Transformers, to address limitations in 3D voxel reconstruction.

Neural Style Transfer with PyTorch: Multi-scale pyramid optimization and L-BFGS refinement for high-quality artistic image generation using VGG19.

Academic page for the paper "CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection" accepted at MICCAI 2026.

This repository contains the code and resources for our research on "CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection"