检索结果-内蒙古大学图书馆

Cross-Domain Person Re-identification Combining Feature Concatenation and Attention

学校读者我要写书评

暂无评论

Cross-Domain Person Re-identification Combining Feature Conc...

作者： Feng Pan Lin Wang Yansha Zhang Jie Wang College of Data Science and Information Engineering Guizhou Minzu University Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province

To improve the insufficient generalization and poor cross-domain capability of the existing direct cross-dataset person re-identification methods,a cross-domain person re-identification method combining feature concatenation and attention(FCANet) is *** deep features of the network are concatenated to complement the feature information and obtain discriminatively feature,and the position attention module is introduced to enhance the data feature representation capability of the cross-domain task,using the joint training network of label smooth cross-entropy loss and triplet loss,model training in the source domain,and directly deploy to the target domain for *** verify the performance of the proposed method,it was experimented on three public datasets of Market1501,DukeMTMC-reID and MSMT17,which mAP and Rank1can reach 51.4%and 62.7% on *** results show that the proposed method has good performance in improving the generalization of cross-domain tasks,and the recognition accuracy outperforms the domain generalization algorithms of comparison.

关键词：

Matching Image with Multiple Local Features

学校读者我要写书评

暂无评论

Matching Image with Multiple Local Features

International Conference on pattern recognition

作者： Yudong Cao Honggang Zhang Yanyan Gao Xiaojun Xu Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Liaoning University of Technology Jinzhou China

In this paper, we present the fusional feature composed of Affine-SIFT, MSER and color moment invariants. The fusional feature is more robust and distinctive than a single local feature. Instead of adding three local features together simply, an efficient two-level matching strategy is devised with the fusional feature, which speeds up the establishment of the local correspondences. To remove partial false positives, an affine transformation is estimated with the weighted RANSAC which decreases iteration times. The experimental results show that our approach can achieve more accurate correspondence. We prospect to apply the fusional feature and match strategy to image retrieval in the end.

关键词： Geometry pattern recognition Image color analysis Nearest neighbor searches Robustness Computer vision Stereo vision

Rapid disparity prediction for dynamic scenes

学校读者我要写书评

暂无评论

Rapid disparity prediction for dynamic scenes

9th International Symposium on Advances in Visual Computing, ISVC 2013

作者： Jiang, Jun Cheng, Jun Chen, Baowen Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Chinese University of Hong Kong Hong Kong Hong Kong Shsenzhen Institute of Information Technology China Guangdong Provincial Key Laboratory of Robotics and Intelligent System China Shenzhen Key Laboratory of Computer Vision and Pattern Recognition China

ISBN: (纸本)9783642419133

Real-time 3D sensing plays a critical role in robotic navigation, video surveillance and human-computer interaction, etc. When computing 3D structures of dynamic scenes from stereo sequences, spatiotemporal stereo and scene flow methods can produce temporally coherent disparity. However, most existing methods do not utilize the previous disparity map sufficiently to compute the next disparity map, and the searching space of correspondences limits the speed of disparity computation for each image pair. This paper proposes an effective scheme to predict disparity maps from stereo sequences. In particular, we apply a robust 3D registration algorithm based on the angular-invariant feature to estimate the ego-motion of the stereo rig between consecutive frames, and present the transformation between consecutive disparity maps. The scheme can produce a sequence of temporally coherent disparity maps rapidly. We apply the new scheme to real outdoor scenes, and thorough empirical studies indicate the effectiveness of the new scheme for practical applications. © 2013 Springer-Verlag.

关键词： Human computer interaction

Deep facial expression recognition: A survey

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Shan Deng, Weihong Pattern Recognition and Intelligent System Laboratory School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

With the transition of facial expression recognition (FER) from laboratory-controlled to challenging in-the-wild conditions and the recent success of deep learning techniques in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. In this paper, we provide a comprehensive survey on deep FER, including datasets and algorithms that provide insights into these intrinsic problems. First, we introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets. We then describe the standard pipeline of a deep FER system with the related background knowledge and suggestions of applicable implementations for each stage. For the state of the art in deep FER, we review existing novel deep neural networks and related training strategies that are designed for FER based on both static images and dynamic image sequences, and discuss their advantages and limitations. Competitive performances on widely used benchmarks are also summarized in this section. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and corresponding opportunities in this field as well as future directions for the design of robust deep FER systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Surveys

A deeper look at facial expression dataset bias

学校读者我要写书评

暂无评论

arXiv 2019年

Datasets play an important role in the progress of facial expression recognition algorithms, but they may suffer from obvious biases caused by different cultures and collection conditions. To look deeper into this bias, we first conduct comprehensive experiments on dataset recognition and cross-dataset generalization tasks, and for the first time explore the intrinsic causes of the dataset discrepancy. The results quantitatively verify that current datasets have a strong build-in bias and corresponding analyses indicate that the conditional probability distributions between source and target datasets are different. However, previous researches are mainly based on shallow features with limited discriminative ability under the assumption that the conditional distribution remains unchanged across domains. To address these issues, we further propose a novel deep Emotion-Conditional Adaption Network (ECAN) to learn domain-invariant and discriminative feature representations, which can match both the marginal and the conditional distributions across domains simultaneously. In addition, the largely ignored expression class distribution bias is also addressed by a learnable re-weighting parameter, so that the training and testing domains can share similar class distribution. Extensive cross-database experiments on both lab-controlled datasets (CK+, JAFFE, MMI and Oulu-CASIA) and real-world databases (AffectNet, FER2013, RAF-DB 2.0 and SFEW 2.0) demonstrate that our ECAN can yield competitive performances across various facial expression transfer tasks and outperform the state-of-the-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

REPRESENTATIVE REFERENCE-SET AND BETWEENNESS CENTRALITY FOR SCENE IMAGE CATEGORIZATION

学校读者我要写书评

暂无评论

REPRESENTATIVE REFERENCE-SET AND BETWEENNESS CENTRALITY FOR ...

IEEE International Conference on Image Processing

作者： Qun Li Zhen Qin Lunshao Chai Honggang Zhang Jim Guo Bir Bhanu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China University of California Riverside CA USA

ISBN: (纸本)9781479923427

Reference-based image classification approach introduces a reference-set for both image representation and dictionary learning. It significantly reduces the dimensionality of represented images and shows outstanding performance even with randomly selected reference images and simple distance measure. In this paper, we improve upon existing work with two major contributions. First, we show that a more representative reference-set contributes to better classification accuracy. To this end, we carefully adapt the K-means clustering algorithm in the feature space to select a distinguished reference-set. Second, in the image classification process, we propose to represent each image by measuring its betweenness centrality in a social network composed of the representative reference-set in each class, leading to a more coherent distance measure that considers the overall connectivity between the probe image and the reference-set. Extensive experiment results demonstrate that our proposed scheme achieves better performance than existing methods.

关键词： Scene categorization reference-based scheme K-means social network betweenness Social Media Social Networks images Image classification distance measurement Eigenvector image representation Imagery (Psychotherapy)

Towards transferable adversarial attack against deep face recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhong, Yaoyao Deng, Weihong Pattern Recognition and Intelligent System Laboratory School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

—Face recognition has achieved great success in the last five years due to the development of deep learning methods. However, deep convolutional neural networks (DCNNs) have been found to be vulnerable to adversarial examples. In particular, the existence of transferable adversarial examples could severely hinder the robustness of DCNNs since this type of attacks could be applied in a fully black-box manner without queries on the target system. In this work, we first investigate the characteristics of transferable adversarial attacks in face recognition by showing the superiority of feature-level methods over label-level methods. Then, to further improve transferability of feature-level adversarial examples, we propose DFANet, a dropout-based method used in convolutional layers, which could increase the diversity of surrogate models and obtain ensemble-like effects. Extensive experiments on state-of-the-art face models with various training databases, loss functions and network architectures show that the proposed method can significantly enhance the transferability of existing attack methods. Finally, by applying DFANet to the LFW database, we generate a new set of adversarial face pairs that can successfully attack four commercial APIs without any queries. This TALFW database is available to facilitate research on the robustness and defense of deep face recognition. Copyright © 2020, The Authors. All rights reserved.

关键词： Face recognition

Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Lulu Zheng, Fujia Zeng, Weihao He, Keqing Xu, Weiran Jiang, Huixing Wu, Wei Wu, Yanan Pattern Recognition & Intelligent System Laboratory China Beijing University of Posts and Telecommunications Beijing China Meituan Group Beijing China

The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings. To explore the lightweight fine-tuning methods for domain adaptation of dialogue summarization, in this paper, we propose an efficient and generalizable Domain-Oriented Prefix-tuning model, which utilizes a domain word initialized prefix module to alleviate domain entanglement and adopts discrete prompts to guide the model to focus on key contents of dialogues and enhance model generalization. We conduct zero-shot experiments and build domain adaptation benchmarks on two multi-domain dialogue summarization datasets, TODSum and QMSum. Adequate experiments and qualitative analysis prove the effectiveness of our methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Smoke Image Segmentation Based on Color Model

学校读者我要写书评

暂无评论

Smoke Image Segmentation Based on Color Model

第11届创新与管理国际学术会议（ICIM2014）

作者： Deng Xing Yu Zhongming Wang Lin Li Jinlan School of Science Guizhou Minzu University Guizhou provincial key laboratory of pattern recognition and intelligent system Liupanshui Normal University

Smoke is the most significant feature in the process of fire,so it's possible to rely on smoke detection to detect *** the smoke image segmentation is the most difficult and also indispensable step in the analysis of smoke image *** order to improve its accuracy and effectively exclude the disturbances of non-smoke image,and lower the false alarm rate,it puts forward a kind of smoke image segmentation based on color *** uses K-means clustering in Lab color space and threshold segmentation in HSV color space,then merges the two ***,it uses the method of shen filter and regional mark to denoise,Experimental results on segmentation of smoke image show that the proposed method is able to segment smoke from the background.

关键词： Image segmentation K-means algorithm Color space LAB HSV