Search Results for author: Chengyuan Li

Found 16 papers, 2 papers with code

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

no code implementations7 Jan 2025 Chengyuan Li, Suyang Zhou, Jieping Kong, Lei Qi, Hui Xue

Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data.

Anomaly Detection Anomaly Segmentation +5

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

no code implementations30 Sep 2024 Ke Yi, Zengke Liu, Jianwei Zhang, Chengyuan Li, Tong Zhang, Junyang Lin, Jingren Zhou

Based on observing activations from large language models, outliers can be classified into channel-wise and spike outliers.

Quantization

Optimization and Simulation of Startup Control for Space Nuclear Power Systems with Closed Brayton Cycle based on NuHeXSys

no code implementations14 Aug 2024 Chengyuan Li, Leran Guo, Shanfang Huang, Jian Deng

This paper presents the development and optimization of a Space Nuclear Power System (SNPS) utilizing a helium-xenon gas-cooled Closed Brayton Cycle (CBC).

Generative AI Models for Different Steps in Architectural Design: A Literature Review

no code implementations30 Mar 2024 Chengyuan Li, Tianyu Zhang, Xusheng Du, Ye Zhang, Haoran Xie

Although architects recognize the potential of generative AI in design, personal barriers often restrict their access to the latest technological developments, thereby causing the application of generative AI in architectural design to lag behind.

Denoising

Ripple Knowledge Graph Convolutional Networks For Recommendation Systems

no code implementations2 May 2023 Chen Li, Yang Cao, Ye Zhu, Debo Cheng, Chengyuan Li, Yasuhiko Morimoto

Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy.

Deep Learning Knowledge Graphs +1

A Long-term Dependent and Trustworthy Approach to Reactor Accident Prognosis based on Temporal Fusion Transformer

no code implementations28 Oct 2022 Chengyuan Li, Zhifang Qiu, Yugao Ma, Meifu Li

In summary, this work for the first time applies the novel composite deep learning model TFT to the prognosis of key parameters after a reactor accident, and makes a positive contribution to the establishment of a more intelligent and staff-light maintenance method for reactor systems.

Prognosis quantile regression

Representation Learning based and Interpretable Reactor System Diagnosis Using Denoising Padded Autoencoder

no code implementations30 Aug 2022 Chengyuan Li, Zhifang Qiu, Zhangrui Yan, Meifu Li

With the mass construction of Gen III nuclear reactors, it is a popular trend to use deep learning (DL) techniques for fast and effective diagnosis of possible accidents.

Denoising Learning Theory +1

An Unsupervised Learning-based Framework for Effective Representation Extraction of Reactor Accidents

no code implementations28 Aug 2022 Chengyuan Li, Meifu Li, Zhifang Qiu

Thus, the encoder part of the framework is able to automatically infer valid representations from partially missing and noisy monitoring data that reflect the complete and noise-free original data, and the representation vectors can be used for downstream tasks for accident diagnosis or else.

Post-hoc Interpretability based Parameter Selection for Data Oriented Nuclear Reactor Accident Diagnosis System

no code implementations3 Aug 2022 Chengyuan Li, Meifu Li, Zhifang Qiu

The results show that the TRES-CNN based diagnostic model successfully predicts the position and size of breaks in LOCA via selected 15 parameters of HPR1000, with 25% of time consumption while training the model compared the process using total 38 parameters.

Position

RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions

no code implementations4 Sep 2021 Chenjie Wang, Chengyuan Li, Bin Luo, Wei Wang, Jun Liu

Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet.

Instance Segmentation Segmentation +1

Object Detection based on OcSaFPN in Aerial Images with Noise

no code implementations18 Dec 2020 Chengyuan Li, Jun Liu, Hailong Hong, Wenju Mao, Chenjie Wang, Chudi Hu, Xin Su, Bin Luo

On the basis of this, a novel octave convolution-based semantic attention feature pyramid network (OcSaFPN) is proposed to get higher accuracy in object detection with noise.

Attribute Denoising +2

U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation

no code implementations26 Jul 2020 Chenjie Wang, Chengyuan Li, Bin Luo

Most scenes in practical applications are dynamic scenes containing moving objects, so segmenting accurately moving objects is crucial for many computer vision applications.

DymSLAM:4D Dynamic Scene Reconstruction Based on Geometrical Motion Segmentation

no code implementations10 Mar 2020 Chenjie Wang, Bin Luo, Yun Zhang, Qing Zhao, Lu Yin, Wei Wang, Xin Su, Yajun Wang, Chengyuan Li

The only input of DymSLAM is stereo video, and its output includes a dense map of the static environment, 3D model of the moving objects and the trajectories of the camera and the moving objects.

Motion Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.