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 ...

3D hybrid imaging system could address limitations of MRI, CT and ultrasound

In a proof-of-concept study, researchers from the Keck School of Medicine of USC and the California Institute of Technology ...
IEEE

Hierarchical Convolution and Graph Net for Utilizing Structural Information of Image

Abstract: Graph neural network (GNN) models are capable of capturing the intrinsic structure and semantic relationships within data and this mechanism grants them substantial potential advantages in ...
GitHub

ESC: Emulating Self-attention with Convolution for Efficient Image Super-Resolution

In this paper, we tackle the high computational overhead of transformers for lightweight image super-resolution. (SR). Motivated by the observations of self-attention's inter-layer repetition, we ...
IEEE

From Convolution to Attention: A Historical Review and Comparative Analysis of Deep Learning Models in Image Classification

Abstract: Image classification, a core computer vision task, profoundly impacts a computer system’s visual understanding. This paper comprehensively reviews deep - learning - driven image ...
GitHub

ImgCompress: Privacy-First Image Optimizer

I created ImgCompress as a private alternative to cloud-based converters. Most web tools force a choice between convenience and privacy. ImgCompress is a complete local-first image web tool that ...