检索结果-内蒙古大学图书馆

M3F: Multi-Modal Continuous Valence-Arousal Estimation in the Wild

学校读者我要写书评

暂无评论

M3F: Multi-Modal Continuous Valence-Arousal Estimation in th...

International Conference on Automatic Face and Gesture Recognition

作者： Yuan-Hang Zhang Rulin Huang Jiabei Zeng Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

In this paper, we propose a multi-modal multi-feature (M$^{3}F$) approach for in-the-wild valence-arousal estimation. In the proposed M$^{3}F$ framework, we fuse both visual features from videos and acoustic features from the audio tracks to estimate the valence and arousal. We follow a CNN-RNN paradigm, where the spatio-temporal visual features are extracted with a 3D convolutional network and/or a pretrained 2D convolutional network, and a bidirectional recurrent neural network. We evaluated the M$^{3}F$ framework on the validation set provided by the Affective Behavior Analysis in-the-wild (ABAW) Challenge, held in conjunction with the IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2020, and it significantly outperforms the baseline method.

关键词： Feature extraction Visualization Three-dimensional displays Two dimensional displays Videos Training Estimation

PAS-Net: Pose-based and Appearance-based Spatiotemporal Networks Fusion for Action Recognition

学校读者我要写书评

暂无评论

PAS-Net: Pose-based and Appearance-based Spatiotemporal Netw...

International Conference on Automatic Face and Gesture Recognition

作者： Changzhen Li Jie Zhang Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

Human poses play important roles in action analysis. However, most state-of-the-art approaches in action recognition ignore the importance of human poses and rarely leverage the pose information for further improving the recognition performance. In this paper, we propose a novel network architecture, which simultaneously considers the appearance information and pose knowledge for robust action recognition. We explore various architectures for fusing the appearance and pose information rather than simply averaging scores at the final layer. Moreover, a novel training strategy is proposed to reduce the influence of overfitting for limited training data. Extensive experiments show that our method achieves competitive performance on the popular benchmarks, i.e., UCF-101 and HMDB-51.

关键词： Feature extraction Three-dimensional displays Spatiotemporal phenomena Computer architecture Two dimensional displays Fuses Training

Poisoning attack against estimating from pairwise comparisons

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Cao, Xiaochun Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen518055 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Big Data Mining and Knowledge Management The School of Economics and Management University of Chinese Academy of Sciences Beijing100049 China

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendation, information retrieval and so on, attackers have strong motivation and incentives to manipulate or disrupt the ranking list. They could inject malicious comparisons into the training data to fool the target ranking algorithm. Such a technique is called "poisoning attack" in regression and classification tasks. In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attack on the pairwise ranking algorithms, which can be generally formalized as the dynamic and static games between the ranker and the attacker, and can be modeled as certain kinds of integer programming problems mathematically. To break the computational hurdle of the underlying integer programming problems, we reformulate them into the distributionally robust optimization (DRO) problems, which are computational tractable. Based on such DRO formulations, we propose two efficient poisoning attack algorithms and establish the associated theoretical guarantees including the existence of Nash equilibrium and the generalization ability bounds. The effectiveness of the suggested poisoning attack strategies is demonstrated by a series of toy simulations and several real data experiments. These experimental results show that the proposed methods can significantly reduce the performance of the ranker in the sense that the correlation between the true ranking list and the aggregated results with toxic data can be decreased dramatically. © 2021, CC BY-NC-ND.

关键词： Toys

An Efficient PointLSTM for Point Clouds Based Gesture Recognition

学校读者我要写书评

暂无评论

An Efficient PointLSTM for Point Clouds Based Gesture Recogn...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuecong Min Yanxiao Zhang Xiujuan Chai Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Agricultural Information Institute Chinese Academy of Agricultural Sciences Beijing China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Point clouds contain rich spatial information, which provides complementary cues for gesture recognition. In this paper, we formulate gesture recognition as an irregular sequence recognition problem and aim to capture long-term spatial correlations across point cloud sequences. A novel and effective PointLSTM is proposed to propagate information from past to future while preserving the spatial structure. The proposed PointLSTM combines state information from neighboring points in the past with current features to update the current states by a weight-shared LSTM layer. This method can be integrated into many other sequence learning approaches. In the task of gesture recognition, the proposed PointLSTM achieves state-of-the-art results on two challenging datasets (NVGesture and SHREC'17) and outperforms previous skeleton-based methods. To show its advantages in generalization, we evaluate our method on MSR Action3D dataset, and it produces competitive results with previous skeleton-based methods.

关键词： Three-dimensional displays Gesture recognition Feature extraction Task analysis Data mining Logic gates Computer vision

Learning from pseudo lesion: A self-supervised framework for covid-19 diagnosis

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Zhongliang Jin, Zhihao Li, Xuechen Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019 and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by Ground Glass Opacity (GGO), a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo lesions generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo COVID-19 images. The pairs of normal and pseudo COVID-19 images were then used to train an encoder-decoder architecture based U-Net for image restoration, which does not require any labelled data. The pretrained encoder was then fine-tuned using labelled data for COVID-19 diagnosis task. Two public COVID- 19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis and the accuracy of the proposed method outperformed the supervised model pretrained on large scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively. © 2021, CC BY-NC-SA.

关键词： Coronavirus

Learning from suspected target: Bootstrapping performance for breast cancer detection in mammography

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xiao, Li Zhu, Cheng Liu, Junjun Luo, Chunlong Liu, Peifang Zhao, Yi Key Laboratory of Intelligent Information Processing Advanced Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Tianjin Medical University Cancer Institute Hospital

Deep learning object detection algorithm has been widely used in medical image analysis. Currently all the object detection tasks are based on the data annotated with object classes and their bounding boxes. On the other hand, medical images such as mammography usually contain normal regions or objects that are similar to the lesion region, and may be misclassified in the testing stage if they are not taken care of. In this paper, we address such problem by introducing a novel top likelihood loss together with a new sampling procedure to select and train the suspected target regions, as well as proposing a similarity loss to further identify suspected targets from targets. Mean average precision (mAP) according to the predicted targets and specificity, sensitivity, accuracy, AUC values according to classification of patients are adopted for performance comparisons. We firstly test our proposed method on a private dense mammogram dataset. Results show that our proposed method greatly reduce the false positive rate and the specificity is increased by 0.25 on detecting mass type cancer. It is worth mention that dense breast typically has a higher risk for developing breast cancers and also are harder for cancer detection in diagnosis, and our method outperforms a reported result from performance of radiologists. Our method is also validated on the public Digital Database for Screening Mammography (DDSM) dataset, brings significant improvement on mass type cancer detection and outperforms the most state-of-the-art work. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

Reverse Perspective Network for Perspective-Aware Object Counting

学校读者我要写书评

暂无评论

Reverse Perspective Network for Perspective-Aware Object Cou...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yifan Yang Guorong Li Zhe Wu Li Su Qingming Huang Nicu Sebe School of Computer Science and Technology UCAS Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Trento Trento Italy

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

One of the critical challenges of object counting is the dramatic scale variations, which is introduced by arbitrary perspectives. We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs. The reverse perspective network explicitly evaluates the perspective distortions, and efficiently corrects the distortions by uniformly warping the input images. Then the proposed network delivers images with similar instance scales to the regressor. Thus the regression network doesn't need multi-scale receptive fields to match the various scales. Besides, to further solve the scale problem of more congested areas, we enhance the corresponding regions of ground-truth with the evaluation errors. Then we force the regressor to learn from the augmented ground-truth via an adversarial process. Furthermore, to verify the proposed model, we collected a vehicle counting dataset based on Unmanned Aerial Vehicles (UAVs). The proposed dataset has fierce scale variations. Extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts.

关键词： Distortion Training Feature extraction Estimation Convolution Kernel Adaptation models

Joint Coronary Centerline Extraction And Lumen Segmentation From Ccta Using Cnntracker And Vascular Graph Convolutional Network

学校读者我要写书评

暂无评论

Joint Coronary Centerline Extraction And Lumen Segmentation ...

IEEE International Symposium on Biomedical Imaging

作者： Ruochen Gao Zhihui Hou Jun Li Hu Han Bin Lu S. Kevin Zhou Medical Imaging Robotics Analytic Computing Laboratory/Engineering (MIRACLE) Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Fuwai Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Peng Cheng Laboratory Shenzhen China

Automatic analysis of coronary artery in coronary computed tomography angiography (CCTA) is important for clinicians to diagnose and evaluate coronary artery disease (CAD). Often there are two analysis tasks involved: centerline extraction and lumen segmentation, which are related yet often treated separately in the literature. In this work, we leverage their mutual relationship and propose an automatic approach for joint centerline extraction and lumen segmentation from CCTA using a hybrid of deep learning models. Our approach features the following designs, including: (i) the use of CNNTracker that traces out the centerline from seeds to detected ostia or the end of vessels, which fixes the breakage issue commonly found in previous pixel-based segmentation methods; (ii) a vascular Graph Convolutional Network (GCN) that leverages the geometric shape prior for accurate mesh-based lumen segmentation; (iii) the alternation between CNNTracker and GCN that refines the centerline and reduces the drift in tracking. We experiment the proposed method on CCTA data from 101 patients and achieve state-of-the-art performance in both centerline extraction and lumen segmentation of the right coronary artery (RCA), left anterior descending (LAD), and left circumflex (LCX).

关键词： Deep learning Solid modeling Image segmentation Shape Predictive models Feature extraction Data mining

Optimizing Partial Area Under the Top-k Curve: Theory and Practice

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Zitai Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Security Department Alibaba Group Hangzhou311121 China School of Cyber Science and Technology Sun Yat-Sen University Shenzhen Campus Shenzhen518107 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

Top-k error has become a popular metric for large-scale classification benchmarks due to the inevitable semantic ambiguity among classes. Existing literature on top-k optimization generally focuses on the optimization method of the top-k objective, while ignoring the limitations of the metric itself. In this paper, we point out that the top-k objective lacks enough discrimination such that the induced predictions may give a totally irrelevant label a top rank. To fix this issue, we develop a novel metric named partial Area Under the top-k Curve (AUTKC). Theoretical analysis shows that AUTKC has a better discrimination ability, and its Bayes optimal score function could give a correct top-K ranking with respect to the conditional probability. This shows that AUTKC does not allow irrelevant labels to appear in the top list. Furthermore, we present an empirical surrogate risk minimization framework to optimize the proposed metric. Theoretically, we present (1) a sufficient condition for Fisher consistency of the Bayes optimal score function;(2) a generalization upper bound which is insensitive to the number of classes under a simple hyperparameter setting. Finally, the experimental results on four benchmark datasets validate the effectiveness of our proposed framework. © 2022, CC BY.

关键词： Machine learning