Hezheng Lin

CAT: Cross Attention in Vision Transformer

Hezheng Lin, Cheng Xing, Xiangyu Wu et al. · 2022 IEEE International Conference on Multimedia and Expo (ICME) · 2022 · 214 citations

Engineering, Machine Learning, Attention +17

Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss

Xing Cheng, Hezheng Lin, Xiangyu Wu et al. · ArXiv.org · 2021 · 66 citations · Full text

Engineering, Machine Learning, Video Summarization +21

Learning to Recognize Chest-Xray Images Faster and More Efficiently Based on Multi-Kernel Depthwise Convolution

Mengjie Hu, Hezheng Lin, Zimeng Fan et al. · IEEE Access · 2020 · 54 citations · Full text

Convolutional Neural Network, Engineering, Machine Learning +20

MLTR: Multi-Label Classification with Transformer

Cheng Xing, Hezheng Lin, Xiangyu Wu et al. · 2022 IEEE International Conference on Multimedia and Expo (ICME) · 2022 · 43 citations

Convolutional Neural Network, Engineering, Machine Learning +16

CAT: Cross Attention in Vision Transformer

Hezheng Lin, Cheng Xing, Xiangyu Wu et al. · arXiv (Cornell University) · 2021 · 17 citations · Full text

Convolutional Neural Network, Engineering, Attention Inner Patch +17