Fei Shen

Curiosity-driven cooperation for long-tailed multi-label learning

Canran Xiao, Chuangxin Zhao, Zong Ke, Fei Shen

cn, sg (code pays fourni par la source)

Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation

Hongchuan Ye, Siyuan Chen, Ziqi Zhong, Canran Xiao et autres

Large language models (LLMs) equipped with retrieval—the Retrieval-Augmented Generation (RAG) paradigm—should combine their parametric knowledge with external evidence, yet in practice they often hallucinate, over-trust noisy snippets, or ignore vital context. We introduce TCR (Transparent Conflict Resolution), a plug-and-play framework that makes …

cn, gb, us, sg (code pays fourni par la source)

RESEARCH ON THE APPLICATION OF BIM TECHNOLOGY BASED ON THE CONCEPT OF SMART ENGINEERING IN THE QUALITY CONTROL OF INDUSTRIAL ENGINEERING BUILDINGS

Fei Shen, QIANG MA, Wen Cheng

Abstract:From the perspective of engineering economic benefits and BIM technology application, this paper studies the application effect of intelligent engineering concept, constructs a coupling and coordination model of industrial engineering construction quality control, and conducts an empirical study on the application data …

us (code pays fourni par la source)

User interface image hierarchical structure generation and optimization based on improved transformer

Fei Shen

With the full advent of the digital age, user interface design is facing unprecedented challenges in terms of large-scale generation and personalized adaptation. However, traditional methods show obvious deficiencies when handling complex semantic structures and high-level visual expressions. To this end, the …

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

Qin Guo, Ailing Zeng, Ceyuan Yang, Hanzhong Guo et autres

Although significant advancements have been achieved in the progress of keypoint-guided Text-to-Image diffusion models, existing mainstream keypoint-guided models encounter challenges in controlling the generation of more general non-rigid objects beyond humans (e.g., animals). Moreover, it is difficult to generate multiple overlapping humans …

MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo

Zhenlong Yuan, Cong Liu, Fei Shen, Laurent Li et autres

Recently, patch deformation-based methods have demonstrated significant strength in multi-view stereo by adaptively expanding the reception field of patches to help reconstruct textureless areas. However, such methods mainly concentrate on searching for pixels without matching ambiguity (i.e., reliable pixels) when constructing deformed …

cn (code pays fourni par la source)

DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo

Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li et autres

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but …

cn (code pays fourni par la source)

CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model

Dapeng Zhang, Fei Shen, Rui Zhao, Yinda Chen et autres

Autonomous driving represents a prominent application of artificial intelligence. Recent approaches have shifted from focusing solely on common scenarios to addressing complex, long-tail situations such as subtle human behaviors, traffic accidents, and non-compliant driving patterns. Given the demonstrated capabilities of large language …

cn (code pays fourni par la source)

DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo

Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li et autres

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but …

The study of natural convection with decay heat source in an open horizontal neutron production target

Jianfei Tong, Jiahui Chen, Songlin Wang, Fei Shen et autres

cn (code pays fourni par la source)

MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo

Zhenlong Yuan, Cong Liu, Fei Shen, Laurent Li et autres

Recently, patch deformation-based methods have demonstrated significant strength in multi-view stereo by adaptively expanding the reception field of patches to help reconstruct textureless areas. However, such methods mainly concentrate on searching for pixels without matching ambiguity (i.e., reliable pixels) when constructing deformed …

Introduction of machine fault diagnosis and prognosis

Ruqiang Yan, Fei Shen

cn (code pays fourni par la source)