检索结果-内蒙古大学图书馆

SoccerNet 2023 Challenges Results

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cioppa, Anthony Giancola, Silvio Somers, Vladimir Magera, Floriane Zhou, Xin Mkhallati, Hassan Deliège, Adrien Held, Jan Hinojosa, Carlos Mansourian, Amir M. Miralles, Pierre Barnich, Olivier De Vleeschouwer, Christophe Alahi, Alexandre Ghanem, Bernard Van Droogenbroeck, Marc Kamal, Abdullah Maglo, Adrien Clapés, Albert Abdelaziz, Amr Xarles, Artur Orcesi, Astrid Scott, Atom Liu, Bin Lim, Byoungkwon Chen, Chen Deuser, Fabian Yan, Feng Yu, Fufu Shitrit, Gal Wang, Guanshuo Choi, Gyusik Kim, Hankyul Guo, Hao Fahrudin, Hasby Koguchi, Hidenari Ardö, Håkan Salah, Ibrahim Yerushalmy, Ido Muhammad, Iftikar Uchida, Ikuma Be'ery, Ishay Rabarisoa, Jaonary Lee, Jeongae Fu, Jiajun Yin, Jianqin Xu, Jinghang Nang, Jongho Denize, Julien Li, Junjie Zhang, Junpei Kim, Juntae Synowiec, Kamil Kobayashi, Kenji Zhang, Kexin Habel, Konrad Nakajima, Kota Jiao, Licheng Ma, Lin Wang, Lizhi Wang, Luping Li, Menglong Zhou, Mengying Nasr, Mohamed Abdelwahed, Mohamed Liashuha, Mykola Falaleev, Nikolay Oswald, Norbert Jia, Qiong Pham, Quoc-Cuong Song, Ran Hérault, Romain Peng, Rui Chen, Ruilong Liu, Ruixuan Baikulov, Ruslan Fukushima, Ryuto Escalera, Sergio Lee, Seungcheon Chen, Shimin Ding, Shouhong Someya, Taiga Moeslund, Thomas B. Li, Tianjiao Shen, Wei Zhang, Wei Li, Wei Dai, Wei Luo, Weixin Zhao, Wending Zhang, Wenjie Yang, Xinquan Ma, Yanbiao Joo, Yeeun Zeng, Yingsen Gan, Yiyang Zhu, Yongqiang Zhong, Yujie Ruan, Zheng Li, Zhiheng Huang, Zhijian Meng, Ziyu Belgium Saudi Arabia Sportradar Norway UCLouvain Belgium EPFL Switzerland EVS Broadcast Equipment Belgium Baidu Research United States Belgium Sharif University of Technology Iran Footovision France Zewail City of Science Technology and Innovation Egypt Université Paris-Saclay CEA France Universitat de Barcelona Spain Computer Vision Center Spain Nagoya University Japan Research Center for Applied Mathematics and Machine Intelligence Zhejiang Lab China AIBrain United States OPPO Research Institute China Germany Meituan China Tencent Youtu Lab China Amazon Prime Video Sport United States Sogang University Korea Republic of The University of Tokyo Japan Spiideo Sweden University of Tsukuba Japan School of Artificial Intelligence Beijing University of Posts and Telecommunications China Normandie Univ INSA Rouen LITIS France Shanghai Jiao Tong University China Key Laboratory of Intelligent Perception and Image Understanding The Ministry of Education Xidian University China NASK - National Research Institute Poland Robo Space China Tongji University China Sportlight Technology United Kingdom School of Control Science and Engineering Shandong University China lRomul Russia Aalborg University Denmark Turing AI Cultures GmbH Germany Information Systems Technology and Design Singapore University of Technology and Design Singapore Sun Yat-sen University China

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leader-boards are available on https://***. Baselines and development kits can be found on https://***/SoccerNet. © 2023, CC BY.

关键词： Computer vision

Affect estimation in 3d space using multi-task active learning for regression

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wu, Dongrui Huang, Jian Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

—Acquisition of labeled training samples for affective computing is usually costly and time-consuming, as affects are intrinsically subjective, subtle and uncertain, and hence multiple human assessors are needed to evaluate each affective sample. Particularly, for affect estimation in the 3D space of valence, arousal and dominance, each assessor has to perform the evaluations in three dimensions, which makes the labeling problem even more challenging. Many sophisticated machine learning approaches have been proposed to reduce the data labeling requirement in various other domains, but so far few have considered affective computing. This paper proposes two multi-task active learning for regression approaches, which select the most beneficial samples to label, by considering the three affect primitives simultaneously. Experimental results on the VAM corpus demonstrated that our optimal sample selection approaches can result in better estimation performance than random selection and several traditional single-task active learning approaches. Thus, they can help alleviate the data labeling problem in affective computing, i.e., better estimation performance can be obtained from fewer labeling queries. Copyright © 2018, The Authors. All rights reserved.

关键词： Regression analysis

Learning a discriminative feature network for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yu, Changqian Wang, Jingbo Peng, Chao Gao, Changxin Yu, Gang Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Key Laboratory of Machine Perception Peking University Megvii Inc.

Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction. To tackle these two problems, we propose a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network. Specifically, to handle the intra-class inconsistency problem, we specially design a Smooth Network with Channel Attention Block and global average pooling to select the more discriminative features. Furthermore, we propose a Border Network to make the bilateral features of boundary distinguishable with deep semantic boundary supervision. Based on our proposed DFN, we achieve stateof-the-art performance 86.2% mean IOU on PASCAL VOC 2012 and 80.3% mean IOU on Cityscapes dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantic Segmentation

Impulsive Multisynchronization of Coupled Multistable Neural Networks with Time-Varying Delay

学校读者我要写书评

暂无评论

IEEE Transactions on Neural Networks and Learning Systems 2017年第7期28卷 1560-1571页

作者： Wang, Yan-Wu Yang, Wu Xiao, Jiang-Wen Zeng, Zhi-Gang School of Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

This paper studies the synchronization problem of coupled delayed multistable neural networks (NNs) with directed topology. To begin with, several sufficient conditions are developed in terms of algebraic inequalities such that every subnetwork has multiple locally exponentially stable periodic orbits or equilibrium points. Then two new concepts named dynamical multisynchronization (DMS) and static multisynchronization (SMS) are introduced to describe the two novel kinds of synchronization manifolds. Using the impulsive control strategy and the Razumikhin-Type technique, some sufficient conditions for both the DMS and the SMS of the controlled coupled delayed multistable NNs with fixed and switching topologies are derived, respectively. Simulation examples are presented to illustrate the effectiveness of the proposed results. © 2012 IEEE.

关键词： Topology

Dynamic vehicle scheduling based on HTN 36

学校读者我要写书评

暂无评论

Dynamic vehicle scheduling based on HTN

第36届中国控制会议

作者： Yindong Shen Zhongyi Zeng Zhewei Wu School of Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education

ISBN: (纸本)9781538629185

Vehicle scheduling plays a crucial role in public transport bus companies. An efficient schedule can help bus companies reduce operating costs while being an essential guide to daily operations. However, the precompiled schedule is usually hard to be adhered to in practice due to the diversity of traffic and driving conditions. Therefore, dynamic vehicle scheduling becomes an important supplement to the daily operations. In this paper, a dynamic vehicle scheduling approach based on Hierarchical Task Network(HTN) is proposed. In the approach, two dynamic vehicle scheduling strategies are devised according to the practical scheduling philosophy. The first is to reschedule for individual vehicle independently, the objective is to maximize the execution of the precompiled schedule. The second is to reschedule for multiple vehicles simultaneously, which aims to maintain the scheduled headways. The two strategies are achieved in the HTN planning through different task decomposition processes, which are constrained by vehicle resources currently available. To verify the feasibility, this approach is implemented based on the Simple Hierarchical Ordered Planner 2(SHOP2), which is a domainindependent and state-based forward HTN planner. Experimental results show that the approach has good adaptability to solve dynamic vehicle schedule problem, meanwhile, it can be helpful to deal with the abnormal services agilely and hence to increase the service quality of public transit.

关键词： public transit dynamic vehicle scheduling scheduling strategies HTN planning SHOP2

Global Rice Multi-Class Segmentation Dataset (RiceSEG): A Comprehensive and Diverse High-Resolution RGB-Annotated images for the Development and Benchmarking of Rice Segmentation Algorithms

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhou, Junchi Wang, Haozhou Kato, Yoichiro Nampally, Tejasri Rajalakshmi, P. Balram, M. Katsura, Keisuke Lu, Hao Mu, Yue Yang, Wanneng Gao, Yangmingrui Xiao, Feng Chen, Hongtao Chen, Yuhao Li, Wenjuan Wang, Jingwen Yu, Fenghua Zhou, Jian Wang, Wensheng Hu, Xiaochun Yang, Yuanzhu Ding, Yanfeng Guo, Wei Liu, Shouyang Engineering Research Center of Plant Phenotyping Ministry of Education Jiangsu Collaborative Innovation Center for Modern Crop Production Academy for Advanced Interdisciplinary Studies Sanya Institute of Nanjing Agricultural University Nanjing Agricultural University Nanjing China Graduate School of Agricultural and Life Sciences The University of Tokyo Tokyo Japan Department of Artificial Intelligence Indian Institute of Technology Hyderabad India Department of Electrical Engineering Indian Institute of Technology Hyderabad India Institute of Biotechnology Professor Jayashankar Telangana Agricultural State University Hyderabad India Graduate School of Agriculture Kyoto University Kyoto Japan Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China National Key Laboratory of Crop Genetic Improvement National Center of Plant Gene Research Hubei Key Laboratory of Agricultural Bioinformatics Huazhong Agricultural University Wuhan China State Key Laboratory of Efficient Utilization of Arid and Semi-arid Arable Land in Northern China the Institute of Agricultural Resources and Regional Planning Chinese Academy of Agricultural Sciences Beijing China Center for Geospatial Information Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shenzhen China School of Information and Electrical Engineering Shenyang Agricultural University Shenyang China Rice Research Institute Jilin Academy of Agricultural Sciences Changchun China Institute of Crop Sciences National Key Facility for Crop Gene Resources and Genetic Improvement Chinese Academy of Agricultural Sciences Beijing China Yuan Long Ping High-Tech Agriculture Co. Ltd. Changsha China

Developing computer vision–based rice phenotyping techniques is crucial for precision field management and accelerating breeding, thereby continuously advancing rice production. Among phenotyping tasks, distinguishing image components is a key prerequisite for characterizing plant growth and development at the organ scale, enabling deeper insights into eco-physiological processes. However, due to the fine structure of rice organs and complex illumination within the canopy, this task remains highly challenging, underscoring the need for a high-quality training dataset. Such datasets are scarce, both due to a lack of large, representative collections of rice field images and the time-intensive nature of annotation. To address this gap, we established the first comprehensive multi-class rice semantic segmentation dataset, RiceSEG. We gathered nearly 50,000 high-resolution, ground-based images from five major rice-growing countries (China, Japan, India, the Philippines, and Tanzania), encompassing over 6,000 genotypes across all growth stages. From these original images, 3,078 representative samples were selected and annotated with six classes (background, green vegetation, senescent vegetation, panicle, weeds, and duckweed) to form the RiceSEG dataset. Notably, the sub-dataset from China spans all major genotypes and rice-growing environments from the northeast to the south. Both state-of-the-art convolutional neural networks and transformer-based semantic segmentation models were used as baselines. While these models perform reasonably well in segmenting background and green vegetation, they face difficulties during the reproductive stage, when canopy structures are more complex and multiple classes are involved. These findings highlight the importance of our dataset for developing specialized segmentation models for rice and other crops. The RiceSEG dataset is publicly available at ***. © 2025, CC BY.

关键词： Semantic Segmentation

Heterogeneous belief formation method based on BP neural network

学校读者我要写书评

暂无评论

Heterogeneous belief formation method based on BP neural net...

2018 2nd International Conference on Electronic Information Technology and Computer Engineering (EITCE 2018)

作者： Yifan Zhuang Hongwei Wang Xi Chen School of Automation Huazhong University of Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China School of Management Huazhong University of Science and Technology

The BDI model has always been the focus of subject modeling research, which includes three kinds of thinking states of the rational subject: Belief, Desire and Intention. Belief is the cognition of agent to the world;it is a collection of environmental information, other agent information, and its own information that the agent has;and it is also the basis of the agent's thinking activity. Due to differences in the individual's living environment and experience, the formation of heterogeneous beliefs is an important issue in the BDI model study. This article divides individual belief set into two parts: knowledge belief and achievable belief. This article proposes an overall framework for the formation of individual heterogeneity beliefs: First, the individual's knowledge experience is modeled, and the empirical knowledge is structured and quantified into binary propositions;then the BP neural network learn and memory propositions of different combinations to form heterogeneous beliefs. Experiments show that this method can simulate the heterogeneity of individual beliefs caused by the individual's own experience, and can realize the belief generation mechanism of gradual information flow, limited attention and heterogeneous priors.

关键词： agent Heterogeneous belief formation method based on BP neural network

Event-Triggered Distributed Extended Kalman Filtering with Randomly Occurring Deception Attack: A Variance-Constrained Approach

学校读者我要写书评

暂无评论

Event-Triggered Distributed Extended Kalman Filtering with R...

第37届中国控制会议

作者： Weihao Song Jianan Wang Jiayuan Shan Housheng Su School of Aerospace Engineering Beijing Institute of Technology School of Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology

In this paper, a distributed extended Kalman filtering algorithm is developed for a class of discrete-time nonlinear systems subject to stochastic disturbances and randomly occurring deception attacks. In order to utilize the limited communication and computation resources efficiently, the event-triggered communication scheme is introduced such that data transmission is executed only when the predefined condition is violated. Furthermore, a set of independent Bernoulli random variables with known statistical properties is defined to characterize the phenomenon of randomly occurring deception attacks. An upper bound for the estimation error covariance considering the event-triggered meachanism and linearization errors is derived via the varianceconstrained approach. The filter gain for each node can be calculated recursively by solving two Raccati-like difference equations to minimize such an upper bound, which is suitable for online application. Finally, an illustrative example is presented to verify the feasibility and effectiveness of the proposed algorithm.

关键词： Distributed filtering Event-triggered scheme Deception attacks Variance constraints

IMPROVING PERSON RE-IDENTIFICATION BY ADAPTIVE HARD SAMPLE MINING

学校读者我要写书评

暂无评论

IMPROVING PERSON RE-IDENTIFICATION BY ADAPTIVE HARD SAMPLE M...

IEEE International Conference on image processing

作者： Kezhou Chen Yang Chen Chuchu Han Nong Sang Changxin Gao Ruolin Wang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China School of Civil Engineering Wuhan University Wuhan China

The field of person re-identification has made significant advances riding on the wave of deep learning. However, owing to the fact that there are much more easy examples than those meaningful hard examples in dataset, the training tends to stagnate quickly and the model may suffer from over-fitting. Therefore, the hard sample mining method is fateful to optimize the model and improve the learning efficiency. In this paper, an Adaptive Hard Sample Mining algorithm is proposed for training a robust person re-identification model. No need for hand-picking the images in the batch or designing the loss function for both positive and negative pairs, we can briefly calculate the hard level by comparing the prediction result with the true label of the sample. Meanwhile, an adaptive threshold of hard level can make the algorithm not only stay in step with training process harmoniously but also alleviate the under-fitting and over-fitting problem simultaneously. Besides, the designed network to implement the approach has good generalization performance that can be combined with various of existing models readily. Experimental results on Market-1501 and DukeMTMC-reID datasets clearly demonstrate the effectiveness of the proposed algorithm.

关键词： Training Adaptation models Computational modeling Machine learning Robustness Cameras Task analysis