Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops最新文献_第3页

Can Deep Learning Recognize Subtle Human Activities? 深度学习能识别细微的人类活动吗?

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2020-06-01 Epub Date: 2020-08-05

Vincent Jacquot, Zhuofan Ying, Gabriel Kreiman

{"title":"Can Deep Learning Recognize Subtle Human Activities?","authors":"Vincent Jacquot, Zhuofan Ying, Gabriel Kreiman","doi":"","DOIUrl":"","url":null,"abstract":"Deep Learning has driven recent and exciting progress in computer vision, instilling the belief that these algorithms could solve any visual task. Yet, datasets commonly used to train and test computer vision algorithms have pervasive confounding factors. Such biases make it difficult to truly estimate the performance of those algorithms and how well computer vision models can extrapolate outside the distribution in which they were trained. In this work, we propose a new action classification challenge that is performed well by humans, but poorly by state-of-the-art Deep Learning models. As a proof-of-principle, we consider three exemplary tasks: drinking, reading, and sitting. The best accuracies reached using state-of-the-art computer vision models were 61.7%, 62.8%, and 76.8%, respectively, while human participants scored above 90% accuracy on the three tasks. We propose a rigorous method to reduce confounds when creating datasets, and when comparing human versus computer vision performance. Source code and datasets are publicly available.","PeriodicalId":89346,"journal":{"name":"Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops","volume":"2020 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8291217/pdf/nihms-1622711.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39206816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PI-Net: A Deep Learning Approach to Extract Topological Persistence Images. PI-Net：提取拓扑持久性图像的深度学习方法。

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2020-06-01 Epub Date: 2020-07-28 DOI: 10.1109/cvprw50498.2020.00425

Anirudh Som, Hongjun Choi, Karthikeyan Natesan Ramamurthy, Matthew P Buman, Pavan Turaga

{"title":"PI-Net: A Deep Learning Approach to Extract Topological Persistence Images.","authors":"Anirudh Som, Hongjun Choi, Karthikeyan Natesan Ramamurthy, Matthew P Buman, Pavan Turaga","doi":"10.1109/cvprw50498.2020.00425","DOIUrl":"10.1109/cvprw50498.2020.00425","url":null,"abstract":"Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. This is greatly attributed to the robustness topological representations provide against different types of physical nuisance variables seen in real-world data, such as view-point, illumination, and more. However, key bottlenecks to their large scale adoption are computational expenditure and difficulty incorporating them in a differentiable architecture. We take an important step in this paper to mitigate these bottlenecks by proposing a novel one-step approach to generate PIs directly from the input data. We design two separate convolutional neural network architectures, one designed to take in multi-variate time series signals as input and another that accepts multi-channel images as input. We call these networks Signal PI-Net and Image PI-Net respectively. To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data. We explore the use of the proposed PI-Net architectures on two applications: human activity recognition using tri-axial accelerometer sensor data and image classification. We demonstrate the ease of fusion of PIs in supervised deep learning architectures and speed up of several orders of magnitude for extracting PIs from data. Our code is available at https://github.com/anirudhsom/PI-Net.","PeriodicalId":89346,"journal":{"name":"Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops","volume":"2020 ","pages":"3639-3648"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7521829/pdf/nihms-1605052.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38438584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning of Warping Functions for Shape Analysis. 形状分析中翘曲函数的深度学习。

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2020-06-01 Epub Date: 2020-07-28 DOI: 10.1109/cvprw50498.2020.00441

Elvis Nunez, Shantanu H Joshi

引用次数: 12

A topological encoding convolutional neural network for segmentation of 3D multiphoton images of brain vasculature using persistent homology. 利用持久同源性分割脑血管三维多光子图像的拓扑编码卷积神经网络。

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2020-06-01 Epub Date: 2020-07-28 DOI: 10.1109/cvprw50498.2020.00503

Mohammad Haft-Javaherian, Martin Villiger, Chris B Schaffer, Nozomi Nishimura, Polina Golland, Brett E Bouma

{"title":"A topological encoding convolutional neural network for segmentation of 3D multiphoton images of brain vasculature using persistent homology.","authors":"Mohammad Haft-Javaherian, Martin Villiger, Chris B Schaffer, Nozomi Nishimura, Polina Golland, Brett E Bouma","doi":"10.1109/cvprw50498.2020.00503","DOIUrl":"10.1109/cvprw50498.2020.00503","url":null,"abstract":"The clinical evidence suggests that cognitive disorders are associated with vasculature dysfunction and decreased blood flow in the brain. Hence, a functional understanding of the linkage between brain functionality and the vascular network is essential. However, methods to systematically and quantitatively describe and compare structures as complex as brain blood vessels are lacking. 3D imaging modalities such as multiphoton microscopy enables researchers to capture the network of brain vasculature with high spatial resolutions. Nonetheless, image processing and inference are some of the bottlenecks for biomedical research involving imaging, and any advancement in this area impacts many research groups. Here, we propose a topological encoding convolutional neural network based on persistent homology to segment 3D multiphoton images of brain vasculature. We demonstrate that our model out-performs state-of-the-art models in terms of the Dice coefficient and it is comparable in terms of other metrics such as sensitivity. Additionally, the topological characteristics of our model's segmentation results mimic manual ground truth. Our code and model are open source at https://github.com/mhaft/DeepVess.","PeriodicalId":89346,"journal":{"name":"Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops","volume":"2020 ","pages":"4262-4271"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8059194/pdf/nihms-1689459.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38900659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pattern Recognition and Computer Vision: Third Chinese Conference, PRCV 2020, Nanjing, China, October 16–18, 2020, Proceedings, Part II 模式识别与计算机视觉:第三届中国会议，PRCV 2020，中国南京，2020年10月16-18日，会议录，第二部分

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2020-01-01 DOI: 10.1007/978-3-030-60639-8

Yuxin Peng, Qingshan Liu, Huchuan Lu, Zhenan Sun, Chenglin Liu, Xilin Chen, H. Zha, Jian Yang

引用次数: 0

Pattern Recognition and Computer Vision: Third Chinese Conference, PRCV 2020, Nanjing, China, October 16–18, 2020, Proceedings, Part III 模式识别与计算机视觉:第三届中国会议，PRCV 2020，中国南京，2020年10月16-18日，会议录，第三部分

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2020-01-01 DOI: 10.1007/978-3-030-60636-7

Zhiguo Cao

引用次数: 0

Pattern Recognition and Computer Vision: Third Chinese Conference, PRCV 2020, Nanjing, China, October 16–18, 2020, Proceedings, Part I 模式识别与计算机视觉:第三届中国会议，PRCV 2020，中国南京，2020年10月16-18日，会议录，第一部分

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2020-01-01 DOI: 10.1007/978-3-030-60633-6

Mingyue Ding, B. Bhanu, Friedrich M. Wahl, Jonathan M. Roberts

引用次数: 0

Correction to: Personalized Travel Recommendation via Multi-view Representation Learning 更正:基于多视图表示学习的个性化旅行推荐

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2019-11-08 DOI: 10.1007/978-3-030-31726-3_46

Yujun Zhang, B. Han, Xinbo Gao, Haoran Li

引用次数: 0

Pattern Recognition and Computer Vision: Second Chinese Conference, PRCV 2019, Xi’an, China, November 8–11, 2019, Proceedings, Part I 模式识别与计算机视觉:第二届中国会议，PRCV 2019，中国西安，2019年11月8-11日，会议录，第一部分

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2019-01-01 DOI: 10.1007/978-3-030-31654-9

Zhouchen Lin, Liang Wang, Jian Yang, Guangming Shi, T. Tan, N. Zheng, Xilin Chen, Yanning Zhang

引用次数: 0

Intersection To Overpass: Instance Segmentation On Filamentous Structures With An Orientation-Aware Neural Network And Terminus Pairing Algorithm. 交叉到立交桥:基于方向感知神经网络和端点配对算法的丝状结构实例分割。

Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops Pub Date : 2019-01-01 DOI: 10.1109/cvprw.2019.00021

Yi Liu, Abhishek Kolagunda, Wayne Treible, Alex Nedo, Jeffrey Caplan, Chandra Kambhamettu

{"title":"Intersection To Overpass: Instance Segmentation On Filamentous Structures With An Orientation-Aware Neural Network And Terminus Pairing Algorithm.","authors":"Yi Liu, Abhishek Kolagunda, Wayne Treible, Alex Nedo, Jeffrey Caplan, Chandra Kambhamettu","doi":"10.1109/cvprw.2019.00021","DOIUrl":"https://doi.org/10.1109/cvprw.2019.00021","url":null,"abstract":"Filamentous structures play an important role in biological systems. Extracting individual filaments is fundamental for analyzing and quantifying related biological processes. However, segmenting filamentous structures at an instance level is hampered by their complex architecture, uniform appearance, and image quality. In this paper, we introduce an orientation-aware neural network, which contains six orientation-associated branches. Each branch detects filaments with specific range of orientations, thus separating them at junctions, and turning intersections to overpasses. A terminus pairing algorithm is also proposed to regroup filaments from different branches, and achieve individual filaments extraction. We create a synthetic dataset to train our network, and annotate real full resolution microscopy images of microtubules to test our approach. Our experiments have shown that our proposed method outperforms most existing approaches for filaments extraction. We also show that our approach works on other similar structures with a road network dataset.","PeriodicalId":89346,"journal":{"name":"Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops","volume":"2019 ","pages":"125-133"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/cvprw.2019.00021","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38879116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2