检索结果-内蒙古大学图书馆

OadTR: Online action detection with transformers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Xiang Zhang, Shiwei Qing, Zhiwu Shao, Yuanjie Zuo, Zhengrong Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China DAMO Academy Alibaba Group China

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global interactions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://***/wangxiang1230/OadTR. Copyright © 2021, The Authors. All rights reserved.

关键词： Recurrent neural networks

Local Neighbor Propagation on Graphs for Robust Feature Matching

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Guo, Hanlin Xiao, Guobao Su, Lumei Zhou, Jiaxing Wang, Dahan Xiamen Key Laboratory of Frontier Electric Power Equipment and Intelligent Control School of Electrical Engineering and Automation Xiamen University of Technology China Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Information Science and Engineering Xiamen University China College of Computer and Control Engineering Minjiang University China Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computer and Information Engineering Xiamen University of Technology China

Establishing reliable correspondences between two sets of feature points is a critical preprocessing step in many computer vision and pattern recognition tasks. In this paper, we propose a novel robust Local Neighbor Propagation on Graphs based feature matching (LNPG) method, to obtain good correspondences for feature matching. LNPG starts from a novel neighborhood graph construction strategy. The strategy leverages the spatial consistency constraint to generate a series of neighborhood sets, and employs the residual information to preserve the local neighborhood relationships of potential inliers (i.e., true matches). Subsequently, LNPG incorporates local neighbor propagation into the graph to enhance connections between data in different neighborhoods, by using the path-based similarity measurement and the adaptive graph partition. In addition, LNPG includes a novel consistency-filtering-based clustering algorithm for robust feature matching. This clustering algorithm introduces a reliable neighborhood consistency measure function and an effective cluster merging criterion for cluster detection and cluster merging during the clustering process, respectively. Overall, LNPG not only effectively distinguishes inliers from outliers, but also reliably classifies inliers into different transformation models between pairs of images. Experiments on publicly available datasets with different types of image transformations show the superiority of our LNPG in comparison with other state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

Self-supervised learning for semi-supervised temporal action proposal

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Xiang Zhang, Shiwei Qing, Zhiwu Shao, Yuanjie Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China DAMO Academy Alibaba Group China

Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation. Particularly, we design an effective Self-supervised Semi-supervised Temporal Action Proposal (SSTAP) framework. The SSTAP contains two crucial branches, i.e., temporal-aware semi-supervised branch and relation-aware self-supervised branch. The semi-supervised branch improves the proposal model by introducing two temporal perturbations, i.e., temporal feature shift and temporal feature flip, in the mean teacher framework. The self-supervised branch defines two pretext tasks, including masked feature reconstruction and clip-order prediction, to learn the relation of temporal clues. By this means, SSTAP can better explore unlabeled videos, and improve the discriminative abilities of learned action features. We extensively evaluate the proposed SSTAP on THUMOS14 and ActivityNet v1.3 datasets. The experimental results demonstrate that SSTAP significantly outperforms state-of-the-art semi-supervised methods and even matches fully-supervised methods. Code is available at https://***/wangxiang1230/SSTAP. © 2021, CC BY.

关键词： Supervised learning

A Novel Optimization Method for Raw Coal Blending in Coal Preparation Plants Based on Interval Programming

学校读者我要写书评

暂无评论

A Novel Optimization Method for Raw Coal Blending in Coal Pr...

Chinese Automation Congress (CAC)

作者： Jiahui Lei Hanwen Liu Jun Zhao Wei Wang Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China CHN Energy Wuda Coal Processing Co. Ltd. Wuhai China

In the process of coal blending and washing in coal preparation plants, there are various raw coals with different quality that changes greatly, which results in poor quality and low profit. To solve these problems, a novel optimization method for raw coal blending based on interval programming is proposed. Interval numbers are introduced to represent the fluctuation range of ash and sulfur content at each density level of raw coals. A predictive model of quantity and quality of dense medium cyclone products is constructed, which uses Hermite interpolation to obtain washability curves of each raw coal and adopts fitting methods to obtain the distribution curve. In order to obtain optimal coal blending schemes, considering operation and maintenance costs of raw coal feeding line, a mixed integer nonlinear programming (MINLP) model is built, whose objective is to maximize profit with the main constraints of clean coal quality and inventory of raw coal. Interval possibility is introduced to transform constraints with interval number and a customized branch and bound algorithm is used to solve it. In order to verify the effectiveness of the method in this paper, experiments are conducted using manufacturing data from a domestic coal preparation plant. The experimental results indicate that the proposed method is practical and has better economic performance.

关键词：

Fire Detection Based on Improved Feature Fusion

学校读者我要写书评

暂无评论

Fire Detection Based on Improved Feature Fusion

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Xinrong Cao Jincai Wu Zuoyong Li Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China School of Electronic Electrical Engineering and Physics Fujian University of Technology Fuzhou China Sichuang Technology Co. Ltd. Fuzhou China

Fire is a serious disaster that endangers life and property worldwide. Accurate and prompt fire detection can provide early warning information for firefighting efforts. Deep learning-based object detection algorithms have proven to be useful in the field of fire detection. However, fire detection is a particularly challenging task, due to the low-resolution of fire images and the presence of blurring and deformation in the targets. Existing fire detection methods are limited by poor detection accuracy and slow speed in complex fire scenarios. To address these challenges, we propose a fire detection algorithm based on improved YOLOv5s. Firstly, the attention module is embedded into the network structure. We introduce this attention module into the last layer of the backbone to enhance feature extraction ability. Secondly, we modify the Neck structure to fully fuse different feature maps. Through fusing extra low-level features from the backbone, it utilizes various receptive fields to enhance the expression of feature. Thirdly, SIoU is introduced to achieve faster convergence during the training. SIoU take into account the direction of the mismatch to redefine penalty indicators. The experimental results show that our proposed algorithm outperforms commonly used models. Even compared to specific fire detectors, our model exhibits certain advantages.

关键词：

Data-driven Sparse Bayesian Learning Discovery of Hysteresis Effects in Electrospinning Processes

学校读者我要写书评

暂无评论

Data-driven Sparse Bayesian Learning Discovery of Hysteresis...

第34届中国控制与决策会议

作者： Hongwei Sun Yasen Wang Yaozhong Zheng Xiang Huang Hai-Tao Zhang School of Artificial Intelligence and Automation and Key Laboratory of Image Processing and Intelligent ControlSchool of AutomationHuazhong University of Science and Technology State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology

Electrospinning is an efficient and feasible method to fabricate hairline fibers from polymers or ***,the hysteresis nonlinearity among pump flow and jet diameter during electrospinning process strongly hinders the improvement of its *** alleviate this effect,it is an urgent yet challenging mission to discover hysteresis effects in near-field Electrospinning *** this work,a nonlinear autoregressive exogenous model is developed for described electrospinning ***,a pure data-driven sparse B ayesian learning(SBL) method is applied to distill the pump flow-jet diameter hysteresis ***,extensive experiments are conducted to verify the discovered effects by the SBL identification method.

关键词： Electrospinning hysteresis nonlinear autoregressive exogenous(NARX) sparse Bayesian learning(SBL)

Weakly supervised person search with region siamese networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Han, Chuchu Su, Kai Yu, Dongdong Yuan, Zehuan Gao, Changxin Sang, Nong Yang, Yi Wang, Changhu Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology ByteDance University of Technology Sydney

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is whether a good person search model can be trained without the need of identity supervision. In this paper, we present a weakly supervised setting where only bounding box annotations are available. Based on this new setting, we provide an effective baseline model termed Region Siamese Networks (R-SiamNets). Towards learning useful representations for recognition in the absence of identity labels, we supervise the R-SiamNet with instance-level consistency loss and cluster-level contrastive loss. For instance-level consistency learning, the R-SiamNet is constrained to extract consistent features from each person region with or without out-of-region context. For cluster-level contrastive learning, we enforce the aggregation of closest instances and the separation of dissimilar ones in feature space. Extensive experiments validate the utility of our weakly supervised method. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark, which surpasses several fully supervised methods, such as OIM [36] and MGTS [4], by a clear margin. More promising performance can be reached by incorporating extra training data. We hope this work could encourage the future research in this field. Copyright © 2021, The Authors. All rights reserved.

关键词： Supervised learning

Weakly Supervised Person Search with Region Siamese Networks

学校读者我要写书评

暂无评论

Weakly Supervised Person Search with Region Siamese Networks

International Conference on Computer Vision (ICCV)

作者： Chuchu Han Kai Su Dongdong Yu Zehuan Yuan Changxin Gao Nong Sang Yi Yang Changhu Wang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology ByteDance University of Technology Sydney

ISBN: (纸本)9781665428132

关键词： Training Computer vision Annotations Supervised learning Training data Benchmark testing Feature extraction

Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Yuhang Huang, Tengteng Yao, Haotian Zhang, Chi Shao, Yuanjie Han, Chuchu Gao, Changxin Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Megvii Technology China

Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the instance features from a cluster with the same pseudo label. However, a cluster may contain images with different identities (label noises) due to the imperfect clustering results, which makes the uni-centroid representation inappropriate. In this paper, we present a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster. MCM can effectively alleviate the issue of label noises by selecting proper positive/negative centroids for the query image. Moreover, we further propose two strategies to improve the contrastive learning process. First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intra-domain information by comparing samples only from the same domain. Second, we propose Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples. We integrate MCM, DSCL, and SONI into a unified framework named Multi-Centroid Representation Network (MCRN). Extensive experiments demonstrate the superiority of MCRN over state-of-the-art approaches on multiple UDA re-ID tasks and fully unsupervised re-ID tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning