Search

Your search keyword '"Zhu, Wenjie"' showing total 187 results
Start Over Author "Zhu, Wenjie" Publication Year Range This year
187 results on '"Zhu, Wenjie"'

1. LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models

Author

Zhang, Yabin, Zhu, Wenjie, He, Chenhang, and Zhang, Lei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Out-of-distribution (OOD) detection is crucial for model reliability, as it identifies samples from unknown classes and reduces errors due to unexpected inputs. Vision-Language Models (VLMs) such as CLIP are emerging as powerful tools for OOD detection by integrating multi-modal information. However, the practical application of such systems is challenged by manual prompt engineering, which demands domain expertise and is sensitive to linguistic nuances. In this paper, we introduce Label-driven Automated Prompt Tuning (LAPT), a novel approach to OOD detection that reduces the need for manual prompt engineering. We develop distribution-aware prompts with in-distribution (ID) class names and negative labels mined automatically. Training samples linked to these class labels are collected autonomously via image synthesis and retrieval methods, allowing for prompt learning without manual effort. We utilize a simple cross-entropy loss for prompt optimization, with cross-modal and cross-distribution mixing strategies to reduce image noise and explore the intermediate space between distributions, respectively. The LAPT framework operates autonomously, requiring only ID class names as input and eliminating the need for manual intervention. With extensive experiments, LAPT consistently outperforms manually crafted prompts, setting a new standard for OOD detection. Moreover, LAPT not only enhances the distinction between ID and OOD samples, but also improves the ID classification accuracy and strengthens the generalization robustness to covariate shifts, resulting in outstanding performance in challenging full-spectrum OOD detection tasks. Codes are available at \url{https://github.com/YBZh/LAPT}., Comment: ECCV2024; Codes and Supp. are available at: https://github.com/YBZh/LAPT

Published
2024

3. Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models

Author

Zhang, Yabin, Zhu, Wenjie, Tang, Hui, Ma, Zhiyuan, Zhou, Kaiyang, and Zhang, Lei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Multimedia
Abstract

With the emergence of pre-trained vision-language models like CLIP, how to adapt them to various downstream classification tasks has garnered significant attention in recent research. The adaptation strategies can be typically categorized into three paradigms: zero-shot adaptation, few-shot adaptation, and the recently-proposed training-free few-shot adaptation. Most existing approaches are tailored for a specific setting and can only cater to one or two of these paradigms. In this paper, we introduce a versatile adaptation approach that can effectively work under all three settings. Specifically, we propose the dual memory networks that comprise dynamic and static memory components. The static memory caches training data knowledge, enabling training-free few-shot adaptation, while the dynamic memory preserves historical test features online during the testing process, allowing for the exploration of additional data insights beyond the training set. This novel capability enhances model performance in the few-shot setting and enables model usability in the absence of training data. The two memory networks employ the same flexible memory interactive strategy, which can operate in a training-free mode and can be further enhanced by incorporating learnable projection layers. Our approach is tested across 11 datasets under the three task settings. Remarkably, in the zero-shot scenario, it outperforms existing methods by over 3\% and even shows superior results against methods utilizing external training data. Additionally, our method exhibits robust performance against natural distribution shifts. Codes are available at \url{https://github.com/YBZh/DMN}., Comment: CVPR2024; Codes are available at \url{https://github.com/YBZh/DMN}

Published
2024

4. Edge Computing Enabled Real-Time Video Analysis via Adaptive Spatial-Temporal Semantic Filtering

Author

Chen, Xiang, Zhu, Wenjie, Chen, Jiayuan, Zhang, Tong, Yi, Changyan, and Cai, Jun

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia, Computer Science - Networking and Internet Architecture
Abstract

This paper proposes a novel edge computing enabled real-time video analysis system for intelligent visual devices. The proposed system consists of a tracking-assisted object detection module (TAODM) and a region of interesting module (ROIM). TAODM adaptively determines the offloading decision to process each video frame locally with a tracking algorithm or to offload it to the edge server inferred by an object detection model. ROIM determines each offloading frame's resolution and detection model configuration to ensure that the analysis results can return in time. TAODM and ROIM interact jointly to filter the repetitive spatial-temporal semantic information to maximize the processing rate while ensuring high video analysis accuracy. Unlike most existing works, this paper investigates the real-time video analysis systems where the intelligent visual device connects to the edge server through a wireless network with fluctuating network conditions. We decompose the real-time video analysis problem into the offloading decision and configurations selection sub-problems. To solve these two sub-problems, we introduce a double deep Q network (DDQN) based offloading approach and a contextual multi-armed bandit (CMAB) based adaptive configurations selection approach, respectively. A DDQN-CMAB reinforcement learning (DCRL) training framework is further developed to integrate these two approaches to improve the overall video analyzing performance. Extensive simulations are conducted to evaluate the performance of the proposed solution, and demonstrate its superiority over counterparts.

Published
2024

14. Investigation on Dynamic On-Resistance of GaN Power Devices Using Double Pulse Test

Author

Hu, Zhihao, Tan, Kun, Zhu, Wenjie, Zhao, Changhui, Jiang, Junsong, Zhang, Jixuan, Tang, Xi, Hu, Cungang, Cao, Wenping, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Hu, Cungang, editor, and Cao, Wenping, editor

Published
2024
Full Text
View/download PDF

15. Fast Response Control of Three-Phase CSR Under Grid Voltage Sag

Author

Zhang, Jixuan, Cao, Wenping, Zhu, Wenjie, Liu, Rongyang, Hu, Cungang, Wu, Wei, Pan, Tianhong, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Hu, Cungang, editor, and Cao, Wenping, editor

Published
2024
Full Text
View/download PDF

16. Open-Circuit Fault Detection Method for Full-Bridge Modular Multilevel Converter Sub-Modules

Author

Yu, Zhiwu, Yang, Weiye, Zhang, Pinjia, Zhu, Wenjie, Liu, Bi, Hu, Cungang, Cao, Wenping, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Hu, Cungang, editor, and Cao, Wenping, editor

Published
2024
Full Text
View/download PDF

17. A Review on the Temporal-Spatial Correlation Based Multiple Horizon Wind Power Forecasting Methods

Author

Yan, Juan, Wu, Haiping, Huang, Zibo, Zhang, Pinjia, Chen, Qingsong, Zhu, Wenjie, Hu, Cungang, Cao, Wenping, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Hu, Cungang, editor, and Cao, Wenping, editor

Published
2024
Full Text
View/download PDF

47. Ecosystem services to support sustainable development: The modifiable areal unit problem in the transition between evaluation and management units.

Author

Zhu, Wenjie, Jin, Xiaobin, Zhang, Xiaolin, Liu, Jingping, and Zhou, Yinkang

Abstract

Understanding the role of ecosystem services (ES) and their interactions at different spatial scales in territorial space governance is crucial for sustainable development. However, a unified analysis of scale and zoning effects on ES supporting sustainable development remains a theoretical and practical gap. Therefore, this study utilized the traditional concept of the modifiable areal unit problem (MAUP) to establish the ES‐MAUP framework. Additionally, the highly urbanized region of Southern Jiangsu, China, was selected as a case study area to quantitatively evaluate four typical regulating ecosystem services in 2020: urban cooling (UC), flood mitigation (FM), soil conservation (SC), and net primary productivity (NPP). The spatial characteristic information of these four ES was effectively preserved with increasing spatial scale. Significant differences existed in the hotspot patterns of NPP, UC, and SC among different zoning units. Across the three zoning units, the correlations between NPP‐UC, NPP‐SC, and UC‐SC exhibited consistent positive trends, while notable differences in correlations between other ES pairs, such as NPP‐FM and UC‐FM. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

48. Urban Spatiotemporal Event Prediction Using Convolutional Neural Network and Road Feature Fusion Network.

Author

Jiang, Yirui, Zhao, Shan, Li, Hongwei, Wu, Huijing, and Zhu, Wenjie

Subjects
CONVOLUTIONAL neural networks, SMART cities, INFORMATION networks, PROBLEM solving, ALGORITHMS
Abstract

The security challenges faced by smart cities are attracting more attention from more people. Criminal activities and disasters can have a significant impact on the stability of a city, resulting in a loss of safety and property for its residents. Therefore, predicting the occurrence of urban events in advance is of utmost importance. However, current methods fail to consider the impact of road information on the distribution of cases and the fusion of information at different scales. In order to solve the above problems, an urban spatiotemporal event prediction method based on a convolutional neural network (CNN) and road feature fusion network (FFN) named CNN-rFFN is proposed in this paper. The method is divided into two stages: The first stage constructs feature map and structure of CNN then selects the optimal feature map and number of CNN layers. The second stage extracts urban road network information using multiscale convolution and incorporates the extracted road network feature information into the CNN. Some comparison experiments are conducted on the 2018–2019 urban patrol events dataset in Zhengzhou City, China. The CNN-rFFN method has an R2 value of 0.9430, which is higher than the CNN, CNN-LSTM, Dilated-CNN, ResNet, and ST-ResNet algorithms. The experimental results demonstrate that the CNN-rFFN method has better performance than other methods. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

49. Pedestrian Fall Detection Methods for Public Traffic Areas: A Literature Review.

Author

Zhao, Rongyong, Zhu, Wenjie, Han, Chuanfeng, Wei, Bingyu, Zhang, Hao, Rahman, Arifur, and Li, Cuiling

Subjects
LITERATURE reviews, PUBLIC spaces, BIBLIOMETRICS, MEDICAL assistance, INTERNET of things
Abstract

Crowd accident surveys have shown that regardless of the initial triggering factors, pedestrian fall behavior is the most critical factor causing and aggravating crowd accidents in public traffic areas (PTAs). The application of pedestrian fall behavior detection methods in PTAs is significant. Once deployed, they would prevent many pedestrians from losing life in crowded traffic area accidents. However, most existing methods are still focused on medical assistance for the elderly. Therefore, this paper conducted bibliometric and content analyses, combining fall detection-related keywords from internationally recognized literature databases and benchmark pedestrian behavior datasets. Based on the analysis of the state-of-the-art (SOTA) achievements in fall detection methods, the fall detection methods were classified into different categories according to the research approach. This study undertakes a comprehensive analysis of five predominant methods, namely, computer vision, Internet of Things, smartphone, kinematic, and wearable device-based methods. Furthermore, the benchmark datasets, including fall scenarios, were introduced and compared. Finally, this study provides a detailed discussion of existing fall detection methods, and possible future directions are identified considering the application requirements in PTAs. This overview may help researchers understand the SOTA fall detection methods and devise new methodologies by improving and synthesizing the highlighted issues in PTAs. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results