GitHub

Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space

Welcome to the L2M repository! This is the official implementation of our ICCV'25 paper titled "Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space". To enable training from single ...
Scientific Research Publishing

Geo-Refined Point Transformer: Coordinate-Aware Excitation and Positional Upsampling for 3D Scene Segmentation ()

The proposed Coordinate-Aware Feature Excitation (CAFE) module and Position-Aware Upsampling (Pos-Up) module both adhere to ...
IEEE

Hybrid Feature Extraction and Deep Learning Framework for Power Transformer Fault Classification: A Real-World Case Study

Abstract: Reliable fault diagnosis in power transformers is paramount for ensuring grid stability and safeguarding critical assets. This paper proposes a novel deep learning-based diagnostic framework ...
IEEE

Video Summarization using 3D CNNs: A Convolutional Approach to Spatial-Temporal Feature Extraction

Abstract: The advancement of videos has been accelerating quite fast and needs efficient summarization mechanisms. The proposed approach in this work is an unsupervised framework with an efficient ...
ClutchPoints

Sam Darnold reveals why Seahawks are built for deep playoff run

Sam Darnold witnessed the reversal of the last regular season finale he played in. He took a 31-9 Detroit Lions beatdown with the Minnesota Vikings around this time one year ago. Now he has the ...