GitHub

VideoPrism: A Foundational Visual Encoder for Video Understanding

VideoPrism is a general-purpose video encoder designed to handle a wide spectrum of video understanding tasks, including classification, retrieval, localization, captioning, and question answering. It ...
GitHub

Exploring the Potential of Encoder-free Architectures in 3D LMMs

Official repository for the paper "Exploring the Potential of Encoder-free Architectures in 3D LMMs". The encoder-free 3D LMM directly utilizes a token embedding module to convert point cloud data ...
IEEE

FocalCA: A Hybrid-Convolutional-Attention Encoder for Intrusion Detection on UNSW-NB15 Achieving High Accuracy Without Data Balancing

Abstract: This study introduces FocalCA, a Hybrid Convolutional-Attention Encoder model for detecting CyberAttacks using the UNSW-NB15 dataset. Despite the inherent imbalance in the binary ...
IEEE

Robust Precoder Design for User-Centric Network Massive MIMO With Symplectic Optimization

Abstract: In this letter, we propose a symplectic optimization approach for robust precoder design in the user-centric network (UCN) massive MIMO (mMIMO) system. The system implementation of the UCN ...