Výsledky vyhledávání - "Gao, PengCheng"

Report

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning

Autor: Yang, Hui-Yue, Chen, Hui, Wang, Ao, Chen, Kai, Lin, Zijia, Tang, Yongliang, Gao, Pengcheng, Quan, Yuming, Han, Jungong, Ding, Guiguang

Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. However, existing methods that directly apply SAM through prompting often overlook the domain shift issue, where SAM perf

Externí odkaz: http://arxiv.org/abs/2411.17217

Zobrazit plný text záznamu

Report

A Differential Smoothness-based Compact-Dynamic Graph Convolutional Network for Spatiotemporal Signal Recovery

Autor: Gao, Pengcheng, Gao, Zicheng, Yuan, Ye

High quality spatiotemporal signal is vitally important for real application scenarios like energy management, traffic planning and cyber security. Due to the uncontrollable factors like abrupt sensors breakdown or communication fault, the spatiotemp

Externí odkaz: http://arxiv.org/abs/2408.02987

Zobrazit plný text záznamu

Report

Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey

Autor: Wang, Xiao, Chen, Guangyao, Qian, Guangwu, Gao, Pengcheng, Wei, Xiao-Yong, Wang, Yaowei, Tian, Yonghong, Gao, Wen

With the urgent demand for generalized deep models, many pre-trained big models are proposed, such as BERT, ViT, GPT, etc. Inspired by the success of these models in single domains (like computer vision and natural language processing), the multi-mod

Externí odkaz: http://arxiv.org/abs/2302.10035

Zobrazit plný text záznamu