GitHub

Dual Selective Fusion Transformer Network for Hyperspectral Image Classification

DSFormer is a novel Dual Selective Fusion Transformer Network for HSI classification. It adaptively selects and fuses features from diverse receptive fields to achieve joint spatial-spectral context ...
IEEE

DB-NeRF: An Effective Dual-Branch Representation for Neural Radiance Fields

Abstract: Neural Radiance Fields (NeRF) have demonstrated impressive novel view synthesis capabilities but suffer from slow training and limitations in representational capacity, leading to artifacts ...
Microsoft

从“实心泥塑”到“高精度资产”，TRELLIS.2重构3D生成规则

在 AI 时代，当文生图早已是秒出“大片”，文生视频也能复刻好莱坞级特效时，3D 生成却仍停留在难以令人满意的阶段——细节模糊、结构失真，缺乏立体感。 当你满怀期待地输入“一个透明的玻璃瓶”，AI 却只给出了一个实心的“泥疙瘩”。当你想要一座 ...
来自MSN

Backpropagation from scratch in Python – step by step neural network tutorial

Learn how backpropagation works by building it from scratch in Python! This tutorial explains the math, logic, and coding behind training a neural network, helping you truly understand how deep ...
IEEE

A Graph Neural Network-Based Dual Attention Fusion Network for CSI-Based Activity Recognition

Abstract: Over the past decade, Channel State Information (CSI)-based human activity recognition (HAR) has attracted wide attention. Despite significant advancements, existing CSI-based HAR methods ...