检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

23,135 篇 会议
91 篇 期刊文献
15 册 图书

馆藏范围

23,240 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,631 篇 工学
- 11,162 篇 计算机科学与技术...
- 3,337 篇 软件工程
- 2,414 篇 机械工程
- 1,662 篇 光学工程
- 1,204 篇 电气工程
- 973 篇 控制科学与工程
- 738 篇 信息与通信工程
- 381 篇 仪器科学与技术
- 322 篇 生物工程
- 239 篇 生物医学工程（可授...
- 188 篇 电子科学与技术（可...
- 109 篇 化学工程与技术
- 104 篇 安全科学与工程
- 99 篇 测绘科学与技术
- 85 篇 建筑学
- 82 篇 土木工程
- 82 篇 交通运输工程
- 56 篇 力学（可授工学、理...
3,696 篇 医学
- 3,684 篇 临床医学
- 76 篇 基础医学(可授医学...
3,137 篇 理学
- 1,880 篇 物理学
- 1,604 篇 数学
- 547 篇 统计学（可授理学、...
- 466 篇 生物学
- 243 篇 系统科学
- 107 篇 化学
491 篇 管理学
- 290 篇 图书情报与档案管...
- 212 篇 管理科学与工程(可...
- 74 篇 工商管理
252 篇 艺术学
- 251 篇 设计学（可授艺术学...
58 篇 法学
38 篇 农学
25 篇 教育学
19 篇 经济学
10 篇 军事学
3 篇 文学

主题

10,396 篇 computer vision
3,893 篇 pattern recognit...
3,101 篇 training
2,104 篇 computational mo...
1,898 篇 visualization
1,800 篇 cameras
1,487 篇 feature extracti...
1,475 篇 three-dimensiona...
1,464 篇 shape
1,447 篇 image segmentati...
1,287 篇 robustness
1,234 篇 computer archite...
1,213 篇 semantics
1,112 篇 benchmark testin...
1,111 篇 conferences
1,104 篇 layout
1,093 篇 object detection
1,085 篇 computer science
1,026 篇 codes
907 篇 face recognition

机构

137 篇 univ sci & techn...
124 篇 univ chinese aca...
121 篇 chinese univ hon...
108 篇 tsinghua univers...
108 篇 carnegie mellon ...
105 篇 microsoft resear...
97 篇 zhejiang univ pe...
91 篇 swiss fed inst t...
85 篇 university of sc...
84 篇 zhejiang univers...
81 篇 shanghai ai lab ...
79 篇 university of ch...
75 篇 shanghai jiao to...
69 篇 microsoft res as...
68 篇 alibaba grp peop...
66 篇 adobe research
65 篇 national laborat...
64 篇 peking univ peop...
61 篇 univ oxford oxfo...
59 篇 peng cheng labor...

作者

80 篇 van gool luc
71 篇 timofte radu
65 篇 zhang lei
43 篇 luc van gool
40 篇 yang yi
37 篇 loy chen change
34 篇 li stan z.
33 篇 liu yang
33 篇 xiaoou tang
33 篇 murino vittorio
33 篇 chen chen
33 篇 qi tian
33 篇 li fei-fei
32 篇 tian qi
32 篇 sun jian
30 篇 ying shan
30 篇 pascal fua
29 篇 darrell trevor
28 篇 li xin
28 篇 hanqing lu

语言

23,162 篇 英文
52 篇 其他
20 篇 中文
5 篇 土耳其文
2 篇 日文

检索条件"任意字段=IEEE/CVF Conference on Computer Vision and Pattern Recognition"

共 23241 条记录，以下是4821-4830 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation

Closing the Loop: Joint Rain Generation and Removal via Dise...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Ye, Yuntong Chang, Yi Zhou, Hanyu Yan, Luxin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Natl Key Lab Sci & Technol Multispectral Informat Wuhan Peoples R China Peng Cheng Lab AI Ctr Shenzhen Peoples R China

ISBN: (纸本)9781665445092

Existing deep learning-based image deraining methods have achieved promising performance for synthetic rainy images, typically rely on the pairs of sharp images and simulated rainy counterparts. However, these methods suffer from significant performance drop when facing the real rain, because of the huge gap between the simplified synthetic rain and the complex real rain. In this work, we argue that the rain generation and removal are the two sides of the same coin and should be tightly coupled. To close the loop, we propose to jointly learn real rain generation and removal procedure within a unified disentangled image translation framework. Specifically, we propose a bidirectional disentangled translation network, in which each unidirectional network contains two loops of joint rain generation and removal for both the real and synthetic rain image, respectively. Meanwhile, we enforce the disentanglement strategy by decomposing the rainy image into a clean background and rain layer (rain removal), in order to better preserve the identity background via both the cycle-consistency loss and adversarial loss, and ease the rain layer translating between the real and synthetic rainy image. A counterpart composition with the entanglement strategy is symmetrically applied for rain generation. Extensive experiments on synthetic and real-world rain datasets show the superiority of proposed method compared to state-of-the-arts.

关键词： computer vision Rain pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Mesh Saliency: An Independent Perceptual Measure or A Derivative of Image Saliency?

Mesh Saliency: An Independent Perceptual Measure or A Deriva...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Song, Ran Zhang, Wei Zhao, Yitian Liu, Yonghuai Rosin, Paul L. Shandong Univ Sch Control Sci & Engn Jinan Peoples R China Shandong Univ Inst Brain & Brain Inspired Sci Jinan Peoples R China Chinese Acad Sci Ningbo Inst Mat Technol & Engn Ningbo Peoples R China Edge Hill Univ Dept Comp Sci Ormskirk England Cardiff Univ Sch Comp Sci & Informat Cardiff S Glam Wales

ISBN: (纸本)9781665445092

While mesh saliency aims to predict regional importance of 3D surfaces in agreement with human visual perception and is well researched in computer vision and graphics, latest work with eye-tracking experiments shows that state-of-the-art mesh saliency methods remain poor at predicting human fixations. Cues emerging prominently from these experiments suggest that mesh saliency might associate with the saliency of 2D natural images. This paper proposes a novel deep neural network for learning mesh saliency using image saliency ground truth to 1) investigate whether mesh saliency is an independent perceptual measure or just a derivative of image saliency and 2) provide a weakly supervised method for more accurately predicting mesh saliency. Through extensive experiments, we not only demonstrate that our method outperforms the current state-of-the-art mesh saliency method by 116% and 21% in terms of linear correlation coefficient and AUC respectively, but also reveal that mesh saliency is intrinsically related with both image saliency and object categorical information. Codes are available at https://***/rsong/MIMO-GAN.

关键词： Graphics Deep learning Correlation coefficient computer vision Three-dimensional displays Codes Current measurement

来源：评论

学校读者我要写书评

暂无评论

Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding

Embracing Uncertainty: Decoupling and De-bias for Robust Tem...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Zhou, Hao Zhang, Chongyang Luo, Yan Chen, Yanjun Hu, Chuanping Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China Zhengzhou Univ Zhengzhou Peoples R China

ISBN: (纸本)9781665445092

Temporal grounding aims to localize temporal boundaries within untrimmed videos by language queries, but it faces the challenge of two types of inevitable human uncertainties: query uncertainty and label uncertainty. The two uncertainties stem from human subjectivity, leading to limited generalization ability of temporal grounding. In this work, we propose a novel DeNet (Decoupling and Debias) to embrace human uncertainty: Decoupling - We explicitly disentangle each query into a relation feature and a modified feature. The relation feature, which is mainly based on skeleton-like words (including nouns and verbs), aims to extract basic and consistent information in the presence of query uncertainty. Meanwhile, modified feature assigned with style-like words (including adjectives, adverbs, etc) represents the subjective information, and thus brings personalized predictions;De-bias - We propose a de-bias mechanism to generate diverse predictions, aim to alleviate the bias caused by single-style annotations in the presence of label uncertainty. Moreover, we put forward new multi-label metrics to diversify the performance evaluation. Extensive experiments show that our approach is more effective and robust than state-of-the-arts on Charades-STA and ActivityNet Captions datasets.

关键词： Performance evaluation computer vision Uncertainty Grounding Annotations Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Toward Interactive Modulation for Photo-Realistic Image Restoration

Toward Interactive Modulation for Photo-Realistic Image Rest...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Cai, Haoming He, Jingwen Qiao, Yu Dong, Chao Chinese Acad Sci Shenzhen Inst Adv Technol Key Lab Human Machine Intelligence Synergy Syst Shenzhen Peoples R China Shanghai AI Lab Shanghai Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc SIAT Branch Shenzhen Peoples R China

ISBN: (纸本)9781665448994

Modulating image restoration level aims to generate a restored image by altering a factor that represents the restoration strength. Previous works mainly focused on optimizing the mean squared reconstruction error, which brings high reconstruction accuracy but lacks finer texture details. This paper presents a Controllable Unet Generative Adversarial Network (CUGAN) to generate high frequency textures in the modulation tasks. CUGAN consists of two modules - base networks and condition networks. The base networks comprise a generator and a discriminator. In the generator, we realize the interactive control of restoration levels by tuning the weights of different features from different scales in the Unet architecture. Moreover, we adaptively modulate the intermediate features in the discriminator according to the severity of degradations. The condition networks accept the condition vector (encoded degradation information) as input, then generate modulation parameters for both the generator and the discriminator. During testing, users can control the output effects by tweaking the condition vector. We also provide a smooth transition between GAN and MSE effects by a simple transition method. Extensive experiments demonstrate that the proposed CUGAN achieves excellent performance on image restoration modulation tasks.

关键词： Degradation Modulation Generative adversarial networks Generators Image restoration pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Wide-Baseline Multi-Camera Calibration using Person Re-Identification

Wide-Baseline Multi-Camera Calibration using Person Re-Ident...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Xu, Yan Li, Yu-Jhe Weng, Xinshuo Kitani, Kris Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781665445092

We address the problem of estimating the 3D pose of a network of cameras for large-environment wide-baseline scenarios, e.g., cameras for construction sites, sports stadiums, and public spaces. This task is challenging since detecting and matching the same 3D keypoint observed from two very different camera views is difficult, making standard structure-from-motion (SfM) pipelines inapplicable. In such circumstances, treating people in the scene as "keypoints" and associating them across different camera views can be an alternative method for obtaining correspondences. Based on this intuition, we propose a method that uses ideas from person re-identification (re-ID) for wide-baseline camera calibration. Our method first employs a re-ID method to associate human bounding boxes across cameras, then converts bounding box correspondences to point correspondences, and finally solves for camera pose using multi-view geometry and bundle adjustment. Since our method does not require specialized calibration targets except for visible people, it applies to situations where frequent calibration updates are required. We perform extensive experiments on datasets captured from scenes of different sizes (80m2, 350m2, 600m2), camera settings (indoor and outdoor), and human activities (walking, playing basketball, construction). Experiment results show that our method achieves similar performance to standard SfM methods relying on manually labeled point correspondences.

关键词： Pose estimation Pipelines Manuals Cameras Robustness Calibration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods ...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Perez-Pellitero, Eduardo Catley-Chandar, Sibi Shaw, Richard Leonardis, Ales Timofte, Radu Zhang, Zexin Liu, Cen Peng, Yunbo Lin, Yue Yu, Gaocheng Zhang, Jin Ma, Zhe Wang, Hongbin Chen, Xiangyu Wang, Xintao Wu, Haiwei Liu, Lin Dong, Chao Zhou, Jiantao Yan, Qingsen Zhang, Song Chen, Weiye Liu, Yuhang Zhang, Zhen Zhang, Yanning Shi, Javen Qinfeng Gong, Dong Zhu, Dan Sun, Mengdi Chen, Guannan Hu, Yang Li, Haowei Zou, Baozhu Liu, Zhen Lin, Wenjie Jiang, Ting Jiang, Chengzhi Li, Xinpeng Han, Mingyan Fan, Haoqiang Sun, Jian Liu, Shuaicheng Marin-Vega, Juan Sloth, Michael Schneider-Kamp, Peter Rottger, Richard Li, Chunyang Bao, Long He, Gang Xu, Ziyao Xu, Li Zhan, Gen Sun, Ming Wen, Xing Li, Junlin Li, Jinjing Li, Chenghua Gang, Ruipeng Li, Fangya Liu, Chenming Feng, Shuang Lei, Fei Liu, Rui Ruan, Junxiang Dai, Tianhong Li, Wei Lu, Zhan Liu, Hengyan Huang, Peian Ren, Guangyu Luo, Yonglin Liu, Chang Tu, Qiang Ma, Sai Cao, Yizhen Tel, Steven Heyrman, Barthelemy Ginhac, Dominique Lee, Chul Kim, Gahyeon Park, Seonghyun An Gia Vien Truong Thanh Nhat Mai Yoon, Howoon Tu Vo Holston, Alexander Zaheer, Sheir Park, Chan Y. Huawei Noahs Ark Lab Hong Kong Peoples R China Univ Wurzburg Wurzburg Germany Swiss Fed Inst Technol Zurich Switzerland Netease Games AI Lab Shanghai Peoples R China AntGroup Hangzhou Peoples R China Univ Macau Macau Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Tencent PCG Shenzhen Peoples R China Univ Sci & Technol China Hefei Peoples R China Univ Adelaide Adelaide SA Australia Xidian Univ Xian Peoples R China Northwestern Polytech Univ Xian Peoples R China Univ New South Wales Sydney NSW Australia BOE Technol Grp Co Ltd Beijing Peoples R China CZUR Technol Grp Co Ltd Liaoning Peoples R China Megvii Technol Beijing Peoples R China Univ Southern Denmark Dept Math & Comp Sci IMADA Aarhus Denmark Esoft Syst Odense Denmark Xiaomi Beijing Peoples R China ByteDance Beijing Peoples R China Kuaishou Technol Beijing Peoples R China Commun Univ China Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China NRTA Acad Broadcasting Sci Beijing Peoples R China Tetras AI Technol Hangzhou Peoples R China Imperial Coll London London England Tsinghua Univ Beijing Peoples R China Univ Edinburgh Edinburgh Midlothian Scotland Sun Yat Sen Univ Guangzhou Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China Beijing Inst Technol Beijing Peoples R China NRTA Acad Broadcasting Sciencience Beijing Peoples R China Univ Burgundy ImViA Lab Dijon France Dongguk Univ Dept Multimedia Engn Seoul South Korea Gachon Univ Seongnam South Korea KC Machine Learning Lab Seoul South Korea

ISBN: (纸本)9781665487399

This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations, which might suffer from under- or over-exposed regions and different sources of noise. The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).

关键词： computer vision Runtime conferences Imaging Dynamic range Particle measurements Market research

来源：评论

学校读者我要写书评

暂无评论

Augmentation Strategies for Learning with Noisy Labels

Augmentation Strategies for Learning with Noisy Labels

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Nishi, Kento Ding, Yi Rich, Alex Hollerer, Tobias Lynbrook High Sch San Jose CA 95129 USA Univ Calif Santa Barbara Santa Barbara CA 93106 USA

ISBN: (纸本)9781665445092

Imperfect labels are ubiquitous in real-world datasets. Several recent successful methods for training deep neural networks (DNNs) robust to label noise have used two primary techniques: filtering samples based on loss during a warm-up phase to curate an initial set of cleanly labeled samples, and using the output of a network as a pseudo-label for subsequent loss calculations. In this paper, we evaluate different augmentation strategies for algorithms tackling the "learning with noisy labels" problem. We propose and examine multiple augmentation strategies and evaluate them using synthetic datasets based on CIFAR-10 and CIFAR-100, as well as on the real-world dataset ClothinglM. Due to several commonalities in these algorithms, we find that using one set of augmentations for loss modeling tasks and another set for learning is the most effective, improving results on the state-of-the-art and other previous methods. Furthermore, we find that applying augmentation during the warm-up period can negatively impact the loss convergence behavior of correctly versus incorrectly labeled samples. We introduce this augmentation strategy to the state-of-the-art technique and demonstrate that we can improve performance across all evaluated noise levels. In particular, we improve accuracy on the CIFAR-10 benchmark at 90% symmetric noise by more than 15% in absolute accuracy, and we also improve performance on the Clothing1M dataset.

关键词： Training Deep learning Machine learning algorithms Filtering Neural networks pattern recognition Noise measurement

来源：评论

学校读者我要写书评

暂无评论

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation

BBAM: Bounding Box Attribution Map for Weakly Supervised Sem...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Lee, Jungbeom Yi, Jihun Shin, Chaehun Yoon, Sungroh Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ ISRC INMC ASRI Seoul South Korea Seoul Natl Univ Inst Engn Res Seoul South Korea

ISBN: (纸本)9781665445092

Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which operates on the low-level information intrinsic to an image. In this work, we utilize higher-level information from the behavior of a trained object detector, by seeking the smallest areas of the image from which the object detector produces almost the same result as it does from the whole image. These areas constitute a bounding-box attribution map (BBAM), which identifies the target object in its bounding box and thus serves as pseudo ground-truth for weakly supervised semantic and instance segmentation. This approach significantly outperforms recent comparable techniques on both the PASCAL VOC and MS COCO benchmarks in weakly supervised semantic and instance segmentation. In addition, we provide a detailed analysis of our method, offering deeper insight into the behavior of the BBAM.

关键词： Image segmentation computer vision Annotations Semantics Detectors Benchmark testing Generators

来源：评论

学校读者我要写书评

暂无评论

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

Neural Body: Implicit Neural Representations with Structured...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Peng, Sida Zhang, Yuanqing Xu, Yinghao Wang, Qianqian Shuai, Qing Bao, Hujun Zhou, Xiaowei Zhejiang Univ Hangzhou Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Cornell Univ Ithaca NY 14853 USA

ISBN: (纸本)9781665445092

This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views. Some recent works have shown that learning implicit neural representations of 3D scenes achieves remarkable view synthesis quality given dense input views. However, the representation learning will be ill-posed if the views are highly sparse. To solve this ill-posed problem, our key idea is to integrate observations over video frames. To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh, so that the observations across frames can be naturally integrated. The deformable mesh also provides geometric guidance for the network to learn 3D representations more efficiently. To evaluate our approach, we create a multi-view dataset named ZJU-MoCap that captures performers with complex motions. Experiments on ZJU-MoCap show that our approach outperforms prior works by a large margin in terms of novel view synthesis quality. We also demonstrate the capability of our approach to reconstruct a moving person from a monocular video on the People-Snapshot dataset.

关键词： Geometry Deformable models computer vision Codes Three-dimensional displays Neural networks Dynamics

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

Anomaly Detection in Video via Self-Supervised and Multi-Tas...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Georgescu, Mariana-Iuliana Barbalau, Antonio Ionescu, Radu Tudor Khan, Fahad Shahbaz Popescu, Marius Shah, Mubarak Univ Bucharest Bucharest Romania MBZ Univ Artificial Intelligence Abu Dhabi U Arab Emirates SecurifAI Bucharest Romania Univ Cent Florida Orlando FL 32816 USA

ISBN: (纸本)9781665445092

Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.

关键词： Training computer vision Three-dimensional displays Event detection computer architecture Benchmark testing Predictive models

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 479 480 481 482 483 484 485 486 487 488 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：