3 papers
cs.CV2024
Algorithm Research of ELMo Word Embedding and Deep Learning Multimodal Transformer in Image Description
Xiaohan Cheng, Taiyuan Mei, Yun Zi +3
Zero sample learning is an effective method for data deficiency. The existing embedded zero sample learning methods only use the known classes to construct the embedded space, so t…
eess.IV2024
An Enhanced Encoder-Decoder Network Architecture for Reducing Information Loss in Image Semantic Segmentation
Zijun Gao, Qi Wang, Taiyuan Mei +3
The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segment…
cs.LG2024
Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks
Taiyuan Mei, Yun Zi, Xiaohan Cheng +3
The internal structure and operation mechanism of large-scale language models are analyzed theoretically, especially how Transformer and its derivative architectures can restrict c…