检索结果-内蒙古大学图书馆

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Casanova, Arantxa Cucurull, Guillem Drozdzal, Michal Romero, Adriana Bengio, Yoshua Montreal Inst Learning Algorithms Montreal PQ Canada Comp Vis Ctr Barcelona Spain Facebook AI Res Menlo Pk CA USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided convolutions or successive dilated convolutions. However, it is not clear which operation leads to best results. In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN). FC-DRN has a densely connected backbone composed of residual networks. Following standard image segmentation architectures, receptive field enlargement operations that change the representation level are interleaved among residual networks. This allows the model to exploit the benefits of both residual and dense connectivity patterns, namely: gradient flow, iterative refinement of representations, multi-scale feature combination and deep supervision. In order to highlight the potential of our model, we test it on the challenging CamVid urban scene understanding benchmark and make the following observations: 1) downsampling operations outperform dilations when the model is trained from scratch, 2) dilations are useful during the finetuning step of the model, 3) coarser representations require less refinement steps, and 4) ResNets (by model construction) are good regularizers, since they can reduce the model capacity when needed. Finally, we compare our architecture to alternative methods and report state-of-the-art result on the Camvid dataset, with at least twice fewer parameters.

关键词： Semantics Spatial resolution computer architecture Convolutional codes Computational modeling computer vision Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the ieee computer society conference on computer vision and pattern recognition

Proceedings of the IEEE Computer Society Conference on Compu...

引用

29th ieee conference on computer vision and pattern recognition, cvpr 2016

ISBN: (纸本)9781467388504

The proceedings contain 640 papers. The topics discussed include: generation and comprehension of unambiguous object description;image question answering using convolutional neural network with dynamic parameter prediction;neural module networks;learning to assign orientations to feature points;affinity CNN: learning pixel-centric pairwise relations for figure/ground embedding;occlusion boundary detection via deep exploration of context;exploit bounding box annotations for multi-label object recognition;MCMC shape sampling for image segmentation with nonparametric shape priors;learning action maps of large environments via first-person vision;sample and filter: nonparametric scene parsing via efficient filtering;training region-based object detectors with online hard example mining;learning with side information through modality hallucination;HyperNet: towards accurate region proposal generation and joint object detection;macroscopic interferometry: rethinking depth estimation with frequency-domain time-of-flight;ASP vision: optically computing the first layer of convolutional neural networks using angle sensitive pixels;hierarchical recurrent neural encoder for video representation with application to captioning;and from keyframes to key objects: video summarization by representative object proposal selection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognizing American Sign Language Gestures from within Continuous Videos 31

Recognizing American Sign Language Gestures from within Cont...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Ye, Yuancheng Tian, Yingli Huenerfauth, Matt Liu, Jingya CUNY Grad Ctr New York NY 10021 USA CUNY City Coll New York NY 10021 USA Rochester Inst Technol Rochester NY 14623 USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

In this paper, we propose a novel hybrid model, 3D recurrent convolutional neural networks (3DRCNN), to recognize American Sign Language (ASL) gestures and localize their temporal boundaries within continuous videos, by fusing multi-modality features. Our proposed 3DRCNN model integrates 3D convolutional neural network (3DCNN) and enhanced fully connected recurrent neural network (FC-RNN), where 3DCNN learns multi-modality features from RGB, motion, and depth channels, and FC-RNN captures the temporal information among short video clips divided from the original video. Consecutive clips with the same semantic meaning are singled out by applying the sliding window approach to segment the clips on the entire video sequence. To evaluate our method, we collected a new ASL dataset which contains two types of videos: Sequence videos (in which a human performs a list of specific ASL words) and Sentence videos (in which a human performs ASL sentences, containing multiple ASL words). The dataset is fully annotated for each semantic region (i.e. the time duration of each word that the human signer performs) and contains multiple input channels. Our proposed method achieves 69.2% accuracy on the Sequence videos for 27 ASL words, which demonstrates its effectiveness of detecting ASL gestures from continuous videos.

关键词： Videos Assistive technology Gesture recognition Three-dimensional displays Task analysis Feature extraction Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

SparsePPG: Towards Driver Monitoring Using Camera-Based Vital Signs Estimation in Near-Infrared 31

SparsePPG: Towards Driver Monitoring Using Camera-Based Vita...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Nowara, Ewa Magdalena Marks, Tim K. Mansour, Hassan Veeraraghavan, Ashok MERL Cambridge MA 02139 USA Rice Univ Houston TX 77005 USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Camera-based measurement of the heartbeat signal from minute changes in the appearance of a person's skin is known as remote photoplethysmography (rPPG). Methods for rPPG have improved considerably in recent years, making possible its integration into applications such as telemedicine. Driver monitoring using in-car cameras is another potential application of this emerging technology. Unfortunately, there are several challenges unique to the driver monitoring context that must be overcome. First, there are drastic illumination changes on the driver's face, both during the day (as sun filters in and out of overhead trees, etc.) and at night (from streetlamps and oncoming headlights), which current rPPG algorithms cannot account for: We argue that these variations are significantly reduced by narrow-bandwidth near-infrared (NIR) active illumination at 940 nm, with matching bandpass filter on the camera. Second, the amount of motion during driving is significant. We perform a preliminary analysis of the motion magnitude and argue that any in-car solution must provide better robustness to motion artifacts. Third, low signal-tonoise ratio (SNR) and false peaks due to motion have the potential to confound the rPPG signal. To address these challenges, we develop a novel rPPG signal tracking and denoising algorithm (sparsePPG) based on Robust Principal Components Analysis and sparse frequency spectrum estimation. We release a new dataset of face videos collected simultaneously in RGB and NIR. We demonstrate that in each of these frequency ranges, our new method performs as well as or better than current state-of-the-art rPPG algorithms. Overall, our preliminary study indicates that while driver vital signs monitoring using cameras is promising, much work needs to be done in terms of improving robustness to motion artifacts before it becomes practical.

关键词： computer vision pattern recognition conferences

来源：评论

学校读者我要写书评

暂无评论

IFQ-Net: Integrated Fixed-point Quantization Networks for Embedded vision 31

IFQ-Net: Integrated Fixed-point Quantization Networks for Em...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Gao, Hongxing Tao, Wei Wen, Dongchao Chen, Tse-Wei Osa, Kinya Kato, Masami Canon Informat Technol Beijing Co LTD Beijing Peoples R China Canon Inc Device Technol Dev Headquarters Tokyo Japan

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Deploying deep models on embedded devices has been a challenging problem since the great success of deep learning based networks. Fixed-point networks, which represent their data with low bits fixed-point and thus give remarkable savings on memory usage, are generally preferred. Even though current fixed-point networks employ relative low bits (e.g. 8-bits), the memory saving is far from enough for the embedded devices. On the other hand, quantization deep networks, for example XNOR-Net and HWGQ-Net, quantize the data into 1 or 2 bits resulting in more significant memory savings but still contain lots of floating-point data. In this paper, we propose a fixed-point network for embedded vision tasks through converting the floating-point data in a quantization network into fixed-point. Furthermore, to overcome the data loss caused by the conversion, we propose to compose floating-point data operations across multiple layers (e.g. convolution, batch normalization and quantization layers) and convert them into fixedpoint. We name the fixed-point network obtained through such integrated conversion as Integrated Fixed-point Quantization Networks (IFQ-Net). We demonstrate that our IFQ-Net gives 2.16x and 18x more savings on model size and runtime feature map memory respectively with similar accuracy on ImageNet. Furthermore, based on YOLOv2, we design IFQ-Tinier-YOLO face detector which is a fixed-point network with 256x reduction in model size (246k Bytes) than Tiny-YOLO. We illustrate the promising performance of our face detector in terms of detection rate on Face Detection Data Set and Bencmark (FDDB) and qualitative results of detecting small faces of Wider Face dataset.

关键词： Quantization (signal) Convolution Face Computational modeling Task analysis Detectors Runtime

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Hallucination Network for Fine-Grained Object recognition

Cross-Domain Hallucination Network for Fine-Grained Object R...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Lin, Jin-Fu Lin, Yen-Liang King, Erh-Kan Su, Hung-Ting Hsu, Winston H. Natl Taiwan Univ Taipei Taiwan GE Global Res Niskayuna NY USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Existing fine-grained object recognition methods often require high-resolution images to better discriminate the subordinate classes. However, this assumption does not always hold in current surveillance systems, where the distinguished parts may not be clearly presented. Besides, data insufficiency and class imbalance make the problem even more challenging. In this paper, we leverage high-resolution images collected from Internet to improve the vehicle recognition in the surveillance environments. A cross-domain hallucination network is proposed to minimize the domain discrepancy and enhance the quality of low-resolution surveillance images. To better align the cross-domain features and boost the recognition performance, we extend the original framework to part-based hallucination networks, where the parts are automatically extracted based on the maximum responses from the convolution filters. We evaluate our method on a public surveillance vehicle dataset (BoxCars21k). Experimental results demonstrate that our approach outperforms the state-of-the-art methods.

关键词： cross-domain hallucination fine-grained classification

来源：评论

学校读者我要写书评

暂无评论

SkeletonNet: Shape Pixel to Skeleton Pixel

SkeletonNet: Shape Pixel to Skeleton Pixel

引用

ieee computer society conference on computer vision and pattern recognition Workshops (cvprW)

作者： Sabari Nathan Priya Kansal Couger Inc.

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

Deep Learning for Geometric Shape Understating has organized a challenge for extracting different kinds of skeletons from the images of different objects. This competition is organized in association with cvpr 2019. There are three different tracks of this competition. The present manuscript describes the method used to train the model for the dataset provided in the first track. The first track aims to extract skeleton pixels from the shape pixels of 89 different objects. For the purpose of extracting the skeleton, a U-net model which is comprised of an encoder-decoder structure has been used. In our proposed architecture, unlike the plain decoder in the traditional U net, we have designed the decoder in the format of HED architecture, wherein we have introduced 4 side layers and fused them to one dilation convolutional layer to connect the broken links of the skeleton. Our proposed architecture achieved the F1 score of 0.77 on test data.

关键词： Skeleton Decoding Training computer architecture Image edge detection Task analysis computer vision

来源：评论

学校读者我要写书评

暂无评论

SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation 31

SINT++: Robust Visual Tracking via Adversarial Positive Inst...

引用

31st Meeting of the ieee/CVF conference on computer vision and pattern recognition, cvpr 2018

作者： Wang, Xiao Li, Chenglong Luo, Bin Tang, Jin School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9781538664209

Existing visual trackers are easily disturbed by occlusion, blur and large deformation. We think the performance of existing visual trackers may be limited due to the following issues: I) Adopting the dense sampling strategy to generate positive examples will make them less diverse;ii) The training data with different challenging factors are limited, even through collecting large training dataset. Collecting even larger training dataset is the most intuitive paradigm, but it may still can not cover all situations and the positive samples are still monotonous. In this paper, we propose to generate hard positive samples via adversarial learning for visual tracking. Specifically speaking, we assume the target objects all lie on a manifold, hence, we introduce the positive samples generation network (PSGN) to sampling massive diverse training data through traversing over the constructed target object manifold. The generated diverse target object images can enrich the training dataset and enhance the robustness of visual trackers. To make the tracker more robust to occlusion, we adopt the hard positive transformation network (HPTN) which can generate hard samples for tracking algorithm to recognize. We train this network with deep reinforcement learning to automatically occlude the target object with a negative patch. Based on the generated hard positive samples, we train a Siamese network for visual tracking and our experiments validate the effectiveness of the introduced algorithm. The project page of this paper can be found from the website1. © 2018 ieee.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal 31

Stacked Conditional Generative Adversarial Networks for Join...

引用

31st Meeting of the ieee/CVF conference on computer vision and pattern recognition, cvpr 2018

作者： Wang, Jifeng Li, Xiang Yang, Jian DeepInsight at PCALab Nanjing University of Science and Technology China Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (纸本)9781538664209

Understanding shadows from a single image consists of two types of task in previous studies, containing shadow detection and shadow removal. In this paper, we present a multi-task perspective, which is not embraced by any existing work, to jointly learn both detection and removal in an end-to-end fashion that aims at enjoying the mutually improved benefits from each other. Our framework is based on a novel STacked Conditional Generative Adversarial Network (ST-CGAN), which is composed of two stacked CGANs, each with a generator and a discriminator. Specifically, a shadow image is fed into the first generator which produces a shadow detection mask. That shadow image, concatenated with its predicted mask, goes through the second generator in order to recover its shadow-free image consequently. In addition, the two corresponding discriminators are very likely to model higher level relationships and global scene characteristics for the detected shadow region and reconstruction via removing shadows, respectively. More importantly, for multi-task learning, our design of stacked paradigm provides a novel view which is notably different from the commonly used one as the multi-branch version. To fully evaluate the performance of our proposed framework, we construct the first large-scale benchmark with 1870 image triplets (shadow image, shadow mask image, and shadow-free image) under 135 scenes. Extensive experimental results consistently show the advantages of STC-GAN over several representative state-of-the-art methods on two large-scale publicly available datasets and our newly released one. © 2018 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

In Defense of Active Part Selection for Fine-Grained Classification

引用

pattern recognition and Image Analysis 2018年第4期28卷 658-663页

作者： Korsch, D. Denzler, J. Computer Vision Group Friedrich Schiller University Jena Jena Germany

Fine-grained classification is a recognition task where subtle differences distinguish between different classes. To tackle this classification problem, part-based classification methods are mostly used. Partbased methods learn an algorithm to detect parts of the observed object and extract local part features for the detected part regions. In this paper we show that not all extracted part features are always useful for the classification. Furthermore, given a part selection algorithm that actively selects parts for the classification we estimate the upper bound for the fine-grained recognition performance. This upper bound lies way above the current state-of-the-art recognition performances which shows the need for such an active part selection method. Though we do not present such an active part selection algorithm in this work, we propose a novel method that is required by active part selection and enables sequential part-based classification. This method uses a support vector machine (SVM) ensemble and allows to classify an image based on arbitrary number of part features. Additionally, the training time of our method does not increase with the amount of possible part features. This fact allows to extend the SVM ensemble with an active part selection component that operates on a large amount of part feature proposals without suffering from increasing training time. © 2018, Pleiades Publishing, Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：