Search

Your search keyword '"Wei, Jianan"' showing total 275 results
Start Over Author "Wei, Jianan"
275 results on '"Wei, Jianan"'

1. Nonverbal Interaction Detection

Author

Wei, Jianan, Zhou, Tianfei, Yang, Yi, and Wang, Wenguan

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

This work addresses a new challenge of understanding human nonverbal interaction in social contexts. Nonverbal signals pervade virtually every communicative act. Our gestures, facial expressions, postures, gaze, even physical appearance all convey messages, without anything being said. Despite their critical role in social life, nonverbal signals receive very limited attention as compared to the linguistic counterparts, and existing solutions typically examine nonverbal cues in isolation. Our study marks the first systematic effort to enhance the interpretation of multifaceted nonverbal signals. First, we contribute a novel large-scale dataset, called NVI, which is meticulously annotated to include bounding boxes for humans and corresponding social groups, along with 22 atomic-level nonverbal behaviors under five broad interaction types. Second, we establish a new task NVI-DET for nonverbal interaction detection, which is formalized as identifying triplets in the form from images. Third, we propose a nonverbal interaction detection hypergraph (NVI-DEHR), a new approach that explicitly models high-order nonverbal interactions using hypergraphs. Central to the model is a dual multi-scale hypergraph that adeptly addresses individual-to-individual and group-to-group correlations across varying scales, facilitating interactional feature learning and eventually improving interaction prediction. Extensive experiments on NVI show that NVI-DEHR improves various baselines significantly in NVI-DET. It also exhibits leading performance on HOI-DET, confirming its versatility in supporting related tasks and strong generalization ability. We hope that our study will offer the community new avenues to explore nonverbal signals in more depth., Comment: ECCV 2024; Project page: https://github.com/weijianan1/NVI

Published
2024

2. Nonverbal Interaction Detection

Author

Wei, Jianan, Zhou, Tianfei, Yang, Yi, Wang, Wenguan, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor

Published
2025
Full Text
View/download PDF

4. Neural-Logic Human-Object Interaction Detection

Author

Li, Liulei, Wei, Jianan, Wang, Wenguan, and Yang, Yi

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

The interaction decoder utilized in prevalent Transformer-based HOI detectors typically accepts pre-composed human-object pairs as inputs. Though achieving remarkable performance, such paradigm lacks feasibility and cannot explore novel combinations over entities during decoding. We present L OGIC HOI, a new HOI detector that leverages neural-logic reasoning and Transformer to infer feasible interactions between entities. Specifically, we modify the self-attention mechanism in vanilla Transformer, enabling it to reason over the triplet and constitute novel interactions. Meanwhile, such reasoning process is guided by two crucial properties for understanding HOI: affordances (the potential actions an object can facilitate) and proxemics (the spatial relations between humans and objects). We formulate these two properties in first-order logic and ground them into continuous space to constrain the learning process of our approach, leading to improved performance and zero-shot generalization capabilities. We evaluate L OGIC HOI on V-COCO and HICO-DET under both normal and zero-shot setups, achieving significant improvements over existing methods., Comment: Accepted to NeurIPS 2023; Code: https://github.com/weijianan1/LogicHOI

Published
2023

23. Tackling Non-stationarity in Decentralized Multi-Agent Reinforcement Learning with Prudent Q-Learning

Author

Wei, Jianan, Wang, Liang, Tao, Xianping, Hu, Hao, Wu, Haijun, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Zhao, Xiang, editor, Yang, Shiyu, editor, Wang, Xin, editor, and Li, Jianxin, editor

Published
2022
Full Text
View/download PDF

34. Review of imbalanced fault diagnosis technology based on generative adversarial networks.

Author

Chen, Hualin, Wei, Jianan, Huang, Haisong, Yuan, Yage, and Wang, Jiaxin

Subjects
GENERATIVE adversarial networks, PROBABILISTIC generative models, FAULT diagnosis, MACHINE learning, PLANT maintenance, FAILURE mode & effects analysis, DIAGNOSIS methods
Abstract

In the field of industrial production, machine failures not only negatively affect productivity and product quality, but also lead to safety accidents, so it is crucial to accurately diagnose machine failures in time and take appropriate measures. However, machines cannot operate with faults for extended periods, and the diversity of fault modes results in limited data collection, posing challenges to building accurate fault prediction models. Despite recent advancements, intelligent fault diagnosis methods based on traditional sampling and machine learning have shown notable progress. Nonetheless, these methods heavily rely on human expertise, making it challenging to extract comprehensive feature information. To address these challenges, numerous imbalance fault diagnosis methods based on generative adversarial networks (GANs) have emerged, GANs can generate realistic samples that conform to the distribution of the original data, showing promising results in diagnosing imbalances in critical components such as bearings and gears, despite their great potential, GAN methods also face challenges, including difficulties in training and generating abnormal samples. However, whether it is GAN-based resampling technology or traditional sampling technology, there are fewer reviews on noise-containing imbalance, intra- and inter-class dual imbalance, multi-class imbalance, time series imbalance and other problems in small samples, and there is a lack of a more comprehensive summary of the solutions to the above imbalance problems. Therefore, the purpose of this paper is to deeply explore the imbalance problems under various failure modes, and review and analyze the research methods and results based on GANs on this basis. By suggesting future research directions, this paper aims to provide guidance and reference for research in the field of industrial production maintenance. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

42. The Benefit of the Optimized Formula of Yinxieling in Psoriasis Vulgaris via Regulation on Autophagy Based on microRNA Expression Profile and Network Pharmacology Analysis

Author

Lu,Yue, Pan,Simin, Li,Wenzhen, Qi,Yao, Li,Li, Yan,Yu-Hong, Wei,Jianan, Yao,Dan-Ni, Wu,Jingjing, Deng,Hao, Ye,Shuyan, Chen,Haiming, Chen,Qubo, Gao,Hengjun, Han,Ling, Lu,Chuanjian, Lu,Yue, Pan,Simin, Li,Wenzhen, Qi,Yao, Li,Li, Yan,Yu-Hong, Wei,Jianan, Yao,Dan-Ni, Wu,Jingjing, Deng,Hao, Ye,Shuyan, Chen,Haiming, Chen,Qubo, Gao,Hengjun, Han,Ling, and Lu,Chuanjian

Abstract

Yue Lu,1– 3,* Simin Pan,4,* Wenzhen Li,5 Yao Qi,6,7 Li Li,1– 3 Yu-Hong Yan,1– 3 Jianan Wei,1– 3 Dan-Ni Yao,1– 3 Jingjing Wu,1– 3 Hao Deng,1– 3 Shuyan Ye,1– 3 Haiming Chen,1– 3 Qubo Chen,1– 3 Hengjun Gao,6,7 Ling Han,1– 3 Chuanjian Lu1– 3 1State Key Laboratory of Dampness Syndrome of Chinese Medicine, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine (Guangdong Provincial Hospital of Chinese Medicine), Guangzhou, People’s Republic of China; 2Guangdong Provincial Key Laboratory of Clinical Research on Traditional Chinese Medicine Syndrome, Guangzhou, People’s Republic of China; 3Guangdong-Hong Kong-Macau Joint Laboratory on Chinese Medicine and Immune Disease Research, Guangzhou University of Chinese Medicine, Guangzhou, People’s Republic of China; 4The Second Clinical College, Guangzhou University of Chinese Medicine, Guangzhou, People’s Republic of China; 5The Clinical College of Acupuncture Rehabilitation, Guangzhou University of Chinese Medicine, Guangzhou, People’s Republic of China; 6Shanghai Molecular Medicine Engineering Technology Research Center, Shanghai, People’s Republic of China; 7Shanghai National Engineering Research Center of Biochip, Shanghai, People’s Republic of China*These authors contributed equally to this workCorrespondence: Ling Han; Chuanjian Lu, Email linghan99@gzucm.edu.cn; lcj@gzucm.edu.cnBackground: Psoriasis is a widespread chronic, immune-mediated skin disease with frequent recurrences, and is extremely harmful to the physical and mental health of patients, causing enormous suffering and exerting considerable economic burdens on the health care system as a whole. In more than a decade of clinical use, the optimized formula of Yinxieling (PSORI-CM01) has consistently demonstrated its effectiveness for treating psoriasis. However, its underlying mechanism remains largely unexplored.Methods: The network pharmacology analysis was conducted to predict the

Published
2024

44. In situ laser-assisted decoration of Au nanoparticles on 3D porous graphene for enhanced 2-CEES sensing.

Author

Zhang, Ling, Yang, Jie, Yang, Junchao, Wei, Jianan, Zhou, Chuan, Zhao, Jiang, and Huang, Qibin

Abstract

The fabrication of gas-sensing devices with high sensitivity and low limit of detection (LOD) for monitoring chemical warfare agents and their simulants is of great importance. Metal oxide-based semiconducting nanomaterials and their heterojunctions hold great promise in chemiresistive gas sensing. However, the demands of high working temperature, integration on interdigitated electrodes (IDEs) and requirement of additional heaters impede their popularity. This work demonstrates in situ laser-assisted preparation of Au-decorated laser-induced graphene (LIG/Au) hetero-material as a flexible and effective near-room-temperature 2-chloroethyl ethyl sulfide (2-CEES) sensor. The structure of the sensor was simplified via omitting the IDE and an additional heating module. After optimizing the concentration of the HAuCl4 precursor solution and power of secondary scribing, the LIG/Au-0.1 M gas sensor exhibited an enhanced response of 7.85‰ to 1.0 ppm 2-CEES, which is twice that of pure LIG. Furthermore, its LOD was as low as 5.8 ppb. The sensing mechanism analysis revealed that the decoration of Au nanoparticles enriched the active sites of LIG/Au-0.1 M and provided catalytic and sensitization effects. The present study not only provides an appealing 2-CEES gas sensor but also demonstrates an effective method for large-scale fabrication of other high-performance sensing devices. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results