检索结果-内蒙古大学图书馆

Noise Robust Hard Example Mining for Human Detection with Efficient Depth-Thermal Fusion

学校读者我要写书评

暂无评论

Noise Robust Hard Example Mining for Human Detection with Ef...

International Conference on Automatic Face and Gesture Recognition

作者： Zijian Zhao Jie Zhang Shiguang Shan Key Lab of Intelligent Information Processing Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

Identity-preserving human detection is important for the privacy-protecting applications. IPHD [1] is a newly collected identity-preserving dataset that only contains depth and thermal images, which have much less information than RGB images. While less information and weakly lab.led ground-truth boxes make it difficult to locate the objects correctly. In this paper, we adopt an efficient depth-thermal fusion approach to combine these two different inputs and enhance the representation. Moreover, a noise robust hard example mining algorithm is proposed to deal with weakly lab.led data. The experiments show that our single model with single scale testing can get the AP=88.1 at IoU=0.5, which is a significant improvement compared with other competition results.

关键词： Noise robustness Feature extraction Training Head Thermal noise Kernel Detectors

Selfgait: A Spatiotemporal Representation Learning Method for Self-Supervised Gait Recognition

学校读者我要写书评

暂无评论

Selfgait: A Spatiotemporal Representation Learning Method fo...

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Yiqun Liu Yi Zeng Jian Pu Hongming Shan Peiyang He Junping Zhang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Institute of Science and Technology for Brain-inspired Intelligence Fudan University China

ISBN: (纸本)9781728176055;9781728176062

Gait recognition plays a vital role in human identification since gait is a unique biometric feature that can be perceived at a distance. Although existing gait recognition methods can learn gait features from gait sequences in different ways, the performance of gait recognition suffers from insufficient lab.led data, especially in some practical scenarios associated with short gait sequences or various clothing styles. It is unpractical to lab.l the numerous gait data. In this work, we propose a self-supervised gait recognition method, termed SelfGait, which takes advantage of the massive, diverse, unlab.led gait data as a pre-training process to improve the representation abilities of spatiotemporal backbones. Specifically, we employ the horizontal pyramid mapping (HPM) and micro-motion template builder (MTB) as our spatiotemporal backbones to capture the multi-scale spatiotemporal representations. Experiments on CASIA-B and OU-MVLP benchmark gait datasets demonstrate the effectiveness of the proposed SelfGait compared with four state-of-the-art gait recognition methods.

关键词： Learning systems Image recognition Conferences Clothing Speech recognition Signal processing Boosting

UniCon: Unified context network for robust active speaker detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Yuanhang Liu, Xiao Liang, Susan Wu, Zhongqin Chen, Xilin Yang, Shuang Shan, Shiguang Beijing China Tomorrow Advancing Life Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences China

We introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD). Traditional methods for ASD usually operate on each candidate's precropped face track separately and do not sufficiently consider the relationships among the candidates. This potentially limits performance, especially in challenging scenarios with low-resolution faces, multiple candidates, etc. Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candidate's face, relational context to capture the visual relationships among the candidates and contrast audio-visual affinities with each other, and temporal context to aggregate long-term information and smooth out local uncertainties. Based on such information, our model optimizes all candidates in a unified process for robust and reliable ASD. A thorough ablation study is performed on several challenging ASD benchmarks under different settings. In particular, our method outperforms the state-of-the-art by a large margin of about 15% mean Average Precision (mAP) absolute on two challenging subsets: one with three candidate speakers, and the other with faces smaller than 64 pixels. Together, our UniCon achieves 92.0% mAP on the AVA-ActiveSpeaker validation set, surpassing 90% for the first time on this challenging dataset at the time of submission. Project website: https://***/. Copyright © 2021, The Authors. All rights reserved.

关键词： Computer vision

Routinggan: Routing age progression and regression with disentangled learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Zhizhong Zhang, Junping Shan, Hongming Shanghai Key Lab of Intelligent Information Processing School of Computer Science China Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China

Although impressive results have been achieved for age progression and regression, there remain two major issues in generative adversarial networks (GANs)-based methods: 1) conditional GANs (cGANs)-based methods can learn various effects between any two age groups in a single model, but are insufficient to characterize some specific patterns due to completely shared convolutions filters;and 2) GANs-based methods can, by utilizing several models to learn effects independently, learn some specific patterns, however, they are cumbersome and require age lab.l in advance. To address these deficiencies and have the best of both worlds, this paper introduces a dropout-like method based on GAN (RoutingGAN) to route different effects in a high-level semantic feature space. Specifically, we first disentangle the age-invariant features from the input face, and then gradually add the effects to the features by residual routers that assign the convolution filters to different age groups by dropping out the outputs of others. As a result, the proposed RoutingGAN can simultaneously learn various effects in a single model, with convolution filters being shared in part to learn some specific effects. Experimental results on two benchmarked datasets demonstrate superior performance over existing methods both qualitatively and quantitatively. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

LightXML: Transformer with dynamic negative sampling for high-performance extreme multi-lab.l text classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jiang, Ting Wang, Deqing Sun, Leilei Yang, Huayi Zhao, Zhengyang Zhuang, Fuzhen SKLSDE and BDBC Lab Beihang University Beijing China Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing China Beijing Advanced Innovation Center for Imaging Theory and Technology Academy for Multidisciplinary Studies Capital Normal University Beijing China

Extreme Multi-lab.l text Classification (XMC) is a task of finding the most relevant lab.ls from a large lab.l set. Nowadays deep learning-based methods have shown significant success in XMC. However, the existing methods (e.g., AttentionXML and X-Transformer etc) still suffer from 1) combining several models to train and predict for one dataset, and 2) sampling negative lab.ls statically during the process of training lab.l ranking model, which reduces both the efficiency and accuracy of the model. To address the above problems, we proposed LightXML, which adopts end-to-end training and dynamic negative lab.ls sampling. In LightXML, we use generative cooperative networks to recall and rank lab.ls, in which lab.l recalling part generates negative and positive lab.ls, and lab.l ranking part distinguishes positive lab.ls from these lab.ls. Through these networks, negative lab.ls are sampled dynamically during lab.l ranking part training by feeding with the same text representation. Extensive experiments show that LightXML outperforms state-of-the-art methods in five extreme multi-lab.l datasets with much smaller model size and lower computational complexity. In particular, on the Amazon dataset with 670K lab.ls, LightXML can reduce the model size up to 72% compared to AttentionXML. Our code is availab.e at http://***/kongds/LightXML. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Sequential Recommendation via Cross-Domain Novelty Seeking Trait Mining

学校读者我要写书评

暂无评论

Journal of Computer Science & technology 2020年第2期35卷 305-319页

作者： Fu-Zhen Zhuang Ying-Min Zhou Hao-Chao Ying Fu-Zheng Zhang Xiang Ao Xing Xie Qing He Hui Xiong Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China School of Public Health Zhejiang University School of MedicineHangzhou 310027China Meituan-Dianping Group Beijing 100102China Microsoft Research Asia Beijing 100080China Department of Management Science and Information Systems Rutgers UniversityNew Jersey 07102U.S.A.

Transfer learning has attracted a large amount of interest and research in last decades, and some effort has been made to build more precise recommendation systems. Most previous transfer recommendation systems assume that the target domain shares the same/similar rating patterns with the auxiliary source domain, which is used to improve the recommendation performance. However, almost all existing transfer learning work does not consider the characteristics of sequential data. In this paper, we study the new cross-domain recommendation scenario by mining novelty-seeking trait. Recent studies in psychology suggest that novelty-seeking trait is highly related to consumer behavior, which has a profound business impact on online recommendation. Previous work performed on only one single target domain may not fully characterize users' novelty-seeking trait well due to the data scarcity and sparsity, leading to the poor recommendation performance. Along this line, we propose a new cross-domain novelty-seeking trait mining model (CDNST for short) to improve the sequential recommendation performance by transferring the knowledge from auxiliary source domain. We conduct systematic experiments on three domain datasets crawled from Douban to demonstrate the effectiveness of our proposed model. Moreover, we analyze the directed influence of the temporal property at the source and target domains in detail.

关键词： sequential recommendation novelty-seeking trait transfer learning

Improving fake news detection by using an entity-enhanced framework to fuse diverse multimodal clues

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qi, Peng Cao, Juan Li, Xirong Liu, Huan Sheng, Qiang Mi, Xiaoyue He, Qin Lv, Yongbiao Guo, Chenyang Yu, Yingchao Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Institute of Artificial Intelligence Hebi China Key Lab of DEKE Renmin University of China Beijing China Zhengzhou University Zhengzhou China Hangzhou ZhongkeRuijian Technology Co. Ltd. Hangzhou China

Recently, fake news with text and images have achieved more effective diffusion than text-only fake news, raising a severe issue of multimodal fake news detection. Current studies on this issue have made significant contributions to developing multimodal models, but they are defective in modeling the multimodal content sufficiently. Most of them only preliminarily model the basic semantics of the images as a supplement to the text, which limits their performance on detection. In this paper, we find three valuable text-image correlations in multimodal fake news: entity inconsistency, mutual enhancement, and text complementation. To effectively capture these multimodal clues, we innovatively extract visual entities (such as celebrities and landmarks) to understand the news-related high-level semantics of images, and then model the multimodal entity inconsistency and mutual enhancement with the help of visual entities. Moreover, we extract the embedded text in images as the complementation of the original text. All things considered, we propose a novel entity-enhanced multimodal fusion framework, which simultaneously models three cross-modal correlations to detect diverse multimodal fake news. Extensive experiments demonstrate the superiority of our model compared to the state of the art. Copyright © 2021, The Authors. All rights reserved.

关键词： Social networking (online)

SVLR: Genome Structure Variant Detection Using Long Read Sequencing Data 1

学校读者我要写书评

暂无评论

16th International Symposium on Bioinformatics Research and Applications, ISBRA 2020

作者： Gu, Wenyan Zhou, Aizhong Wang, Lusheng Sun, Shiwei Cui, Xuefeng Zhu, Daming School of Computer Science and Technology Shandong University Qingdao China Department of Computer Science City University of Hong Kong Kowloon Hong Kong Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9783030578213

ISBN: (纸本)9783030578206

Genome structural variants have great impacts on human phenotype and diversity, and have been linked to numerous diseases. Long read sequencing technologies arise to make it possible to find structural variants of as long as ten thousand nucleotides. Thus, long read based structural variant detection has been drawing attention of many recent research projects, and many tools have been developed for long reads to detect structural variants recently. In this article, we present a new method, called SVLR, to detect Structural Variants based on Long Read sequencing data. Comparing to existing methods, SVLR can detect three new kinds of structural variants: block replacements, block interchanges and translocations. Although these new structural variants are structurally more complicated, SVLR achieves accuracies that are comparable to those of the classic structural variants. Moreover, for the classic structural variants that can be detected by state-of-the-art methods (e.g., SVIM and Sniffles), our experiments demonstrate recall improvements of up-to without harming the precisions (i.e., above). We also point out three directions to further improve structural variant detection in the future. Source codes: https://***/GWYSDU/SVLR. © 2020, Springer Nature Switzerland AG.

关键词： Genes

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning