Xinghao Chen

Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs

MetaFormer is Actually What You Need for Vision

The multi-modal fusion in visual question answering: a review of attention mechanisms

MixFormer: End-to-End Tracking with Iterative Mixed Attention

Learn to Match: Automatic Matching Network Design for Visual Tracking

Attention mechanisms in computer vision: A survey

A Survey on Visual Transformer

CMT: Convolutional Neural Networks Meet Vision Transformers