Hybrid Offset Position Encoding for Large-Scale Point Cloud Semantic Segmentation by Yu Xiao, Hui Wu, Yisheng Chen, Chongcheng Chen, Ruihai Dong, Ding Lin

Subjects: Get full text

Enhancing the Transformer Model with a Convolutional Feature Extractor Block and Vector-Based Relative Position Embedding for Human Activity Recognition by Xin Guo, Young Kim, Xueli Ning, Se Dong Min

Subjects: Get full text

Positional embeddings and zero-shot learning using BERT for molecular-property prediction by Medard Edmund Mswahili, JunHa Hwang, Jagath C. Rajapakse, Kyuri Jo, Young-Seob Jeong

Subjects: Get full text