Search Results for author: Nan Zhou

Found 15 papers, 3 papers with code

GLOBUS: Global building renovation potential by 2070

no code implementations6 Jun 2024 Shufan Zhang, Minda Ma, Nan Zhou, Jinyue Yan

Surpassing the two large emission sectors of transportation and industry, the building sector accounted for 34% and 37% of global energy consumption and carbon emissions in 2021, respectively.

Estimation of Global Building Stocks by 2070: Unlocking Renovation Potential

no code implementations6 Jun 2024 Shufan Zhang, Minda Ma, Nan Zhou, Jinyue Yan, Wei Feng, Ran Yan, Kairui You, Jingjing Zhang, Jing Ke

Buildings produce one-third of carbon emissions globally, however, data absence regarding global floorspace poses challenges in advancing building carbon neutrality.

iVPT: Improving Task-relevant Information Sharing in Visual Prompt Tuning by Cross-layer Dynamic Connection

no code implementations8 Apr 2024 Nan Zhou, Jiaxin Chen, Di Huang

It innovatively incorporates a cross-layer dynamic connection (CDC) for input prompt tokens from adjacent layers, enabling effective sharing of task-relevant information.

Image Classification Semantic Segmentation +1

Capturing Shock Waves by Relaxation Neural Networks

no code implementations1 Apr 2024 Nan Zhou, Zheng Ma

In this paper, we put forward a neural network framework to solve the nonlinear hyperbolic systems.

DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration

1 code implementation ICCV 2023 Nan Zhou, Jiaxin Chen, Di Huang

Furthermore, to alleviate the interference by semantic drift, we develop the semantic calibration (SC) module to align the global shape and class centers of the pretrained and downstream feature distributions.

General Knowledge Image Classification

Decarbonization patterns of residential building operations in China and India

no code implementations24 Jun 2023 Ran Yan, Nan Zhou, Wei Feng, Minda Ma, Xiwang Xiang, Chao Mao

(2) Building electrification played a significant role in decarbonizing space cooling (-87. 7 in China and -130. 2 kilograms of carbon dioxide (kgCO2) per household in India) and appliances (-169. 7 in China and -43. 4 kgCO2 per household in India).

CONA: A novel CONtext-Aware instruction paradigm for communication using large language model

no code implementations26 May 2023 Nan Zhou, Xinghui Tao, Xi Chen

We introduce CONA, a novel context-aware instruction paradigm for effective knowledge dissemination using generative pre-trained transformer (GPT) models.

Language Modelling Large Language Model +1

Density-Aware Convolutional Networks with Context Encoding for Airborne LiDAR Point Cloud Classification

no code implementations14 Oct 2019 Xiang Li, Mingyang Wang, Congcong Wen, Lingjing Wang, Nan Zhou, Yi Fang

Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.

3D Point Cloud Classification General Classification +1

Random Directional Attack for Fooling Deep Neural Networks

1 code implementation6 Aug 2019 Wenjian Luo, Chenwang Wu, Nan Zhou, Li Ni

Unfortunately, as the model is nonlinear in most cases, the addition of perturbations in the gradient direction does not necessarily increase loss.

speech-recognition Speech Recognition

Algorithmic Collusion in Cournot Duopoly Market: Evidence from Experimental Economics

no code implementations21 Feb 2018 Nan Zhou, Li Zhang, Shijian Li, Zhijian Wang

In application, we hope, the frameworks, the algorithm design as well as the experiment environment illustrated in this work, can be an incubator or a test bed for researchers and policymakers to handle the emerging algorithmic collusion.

Global and Local Structure Preserving Sparse Subspace Learning: An Iterative Approach to Unsupervised Feature Selection

no code implementations2 Jun 2015 Nan Zhou, Yangyang Xu, Hong Cheng, Jun Fang, Witold Pedrycz

In this paper, we propose a global and local structure preserving sparse subspace learning (GLoSS) model for unsupervised feature selection.

feature selection

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