Fanghui Xue

activity

20192026

collaborators

3 papers

cs.CV2026

VideoSEMA: a scalable and efficient Mamba-like attention for video understanding

Nhat Thanh Tran, Fanghui Xue, Shuai Zhang +4

We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space…

cs.CV2022

Searching Intrinsic Dimensions of Vision Transformers

Fanghui Xue, Biao Yang, Yingyong Qi +1

It has been shown by many researchers that transformers perform as well as convolutional neural networks in many computer vision tasks. Meanwhile, the large computational costs of…

cs.LG2019

Learning Sparse Neural Networks via $ℓ_{0}$ and T $ℓ_{1}$ by a Relaxed Variable Splitting Method with Application to Multi-scale Curve Classification

Fanghui Xue, Jack Xin

We study sparsification of convolutional neural networks (CNN) by a relaxed variable splitting method of $ℓ_{0}$ and transformed- $ℓ_{1}$ (T $ℓ_{1}$ ) penalties, with application t…

VideoSEMA: a scalable and efficient Mamba-like attention for video understanding

Searching Intrinsic Dimensions of Vision Transformers

Learning Sparse Neural Networks via ℓ0​ and Tℓ1​ by a Relaxed Variable Splitting Method with Application to Multi-scale Curve Classification

Learning Sparse Neural Networks via $ℓ_{0}$ and T $ℓ_{1}$ by a Relaxed Variable Splitting Method with Application to Multi-scale Curve Classification