检索结果-内蒙古大学图书馆

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

作者： Verbin, Dor Mildenhall, Ben Hedman, Peter Barron, Jonathan T. Zickler, Todd Srinivasan, Pratul P. Google Res Mountain View CA 94043 USA Harvard Univ Cambridge MA USA

ISBN: (纸本)9798350353013;9798350353006

Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This problem is especially challenging for diffuse objects: it is ill-conditioned because diffuse materials severely blur incoming light, and it is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination-even from diffuse objects-by exploiting unintended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatiallyvarying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who inadvertently cast shadows upon it.

关键词： computer Graphics Inverse Rendering Non-line-of-sight Imaging

来源：评论

学校读者我要写书评

暂无评论

FUSION OF STEREO AND MOTION vision FOR 3-D RECONSTRUCTION 11

FUSION OF STEREO AND MOTION VISION FOR 3-D RECONSTRUCTION

引用

conference A: computer vision and Applications, at the 11th IAPR International conference on pattern recognition

作者： WALDMANN, J MERHAV, S IEEE ITACTABR-12225 S JOSE CAMPOSSPBRAZIL

ISBN: (纸本)081862910X

This paper describes a robotic vision system based on the fusion of stereo and motion vision for 3-D reconstruction. Its performance under occlusions is improved by considering the image matching noise dynamics in the motion module. The stereo module is based on the maximum a posteriori estimate of depth given the measured stereo disparity. Simulations with noisy synthetic images showed that the the system is capable of 3-D reconstruction and of resolving occluding from occluded objects with potential for real-time operation. © 1992 ieee.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Model-driven segmentation of articulating humans in Laplacian Eigenspace

引用

ieee TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2008年第10期30卷 1771-1785页

作者： Sundaresan, Aravind Chellappa, Rama SRI Int Ctr Artificial Intelligence Menlo Pk CA 94025 USA Univ Maryland Ctr Automat Res College Pk MD 20742 USA

We propose a general approach using Laplacian Eigenmaps and a graphical model of the human body to segment 3D voxel data of humans into different articulated chains. In the bottom-up stage, the voxels are transformed into a high-dimensional (6D or less) Laplacian Eigenspace (LE) of the voxel neighborhood graph. We show that the LE is effective at mapping voxels on long articulated chains to nodes on smooth 1D curves that can be easily discriminated, and we prove these properties using representative graphs. We fit 1D splines to voxels belonging to different articulated chains such as the limbs, head, and trunk, and we determine the boundary between splines by thresholding the spline fit error, which is high at junctions. A top-down probabilistic approach is then used to register the segmented chains, utilizing both their mutual connectivity and their individual properties such as length and thickness. Our approach enables us to deal with complex poses such as those where the limbs form loops. We use the segmentation results to automatically estimate the human body models. Although we use human subjects in our experiments, the method is fairly general and can be applied to voxel-based registration of any articulated object, which is composed of long chains. We present results on real and synthetic data that illustrate the usefulness of this approach.

关键词： pattern recognition image processing computer vision segmentation graph-theoretic methods region growing partitioning object recognition

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation

Heterogeneous Grid Convolution for Adaptive, Efficient, and ...

引用

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

作者： Hamaguchi, Ryuhei Furukawa, Yasutaka Onishi, Masaki Sakurada, Ken Natl Inst Adv Ind Sci & Technol Tokyo Japan Simon Fraser Univ Burnaby BC Canada

ISBN: (纸本)9781665445092

This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional architecture. More concretely, the approach builds a data-adaptive graph structure from a convolutional layer by a differentiable clustering method, pools features to the graph, performs a novel direction-aware graph convolution, and unpool features back to the convolutional layer. By using the developed module, the paper proposes heterogeneous grid convolutional networks, highly efficient yet strong extension of existing architectures. We have evaluated the proposed approach on four image understanding tasks, semantic segmentation, object localization, road extraction, and salient object detection. The proposed method is effective on three of the four tasks. Especially, the method outperforms a strong baseline with more than 90% reduction in floating-point operations for semantic segmentation, and achieves the state-of-the-art result for road extraction. We will share our code, model, and data.

关键词： Convolutional codes Location awareness Image segmentation Convolution Roads Semantics computer architecture

来源：评论

学校读者我要写书评

暂无评论

Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation 32

Arbitrary Shape Scene Text Detection with Adaptive Text Regi...

引用

32nd ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wang, Xiaobing Jiang, Yingying Luo, Zhenbo Liu, Cheng-Lin Choi, Hyunsoo Kim, Sungjin Samsung Res China Beijing Beijing 100028 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Samsung Res Seoul 06765 South Korea

ISBN: (纸本)9781728132938

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTWI500, TotalText, ICDAR2013, ICDAR2015 and MSRATD500, show that the proposed method achieves state-of-the-art in scene text detection.

关键词： Categorization recognition: Detection Retrieval vision Applications and Systems

来源：评论

学校读者我要写书评

暂无评论

Multi-class Token Transformer for Weakly Supervised Semantic Segmentation

Multi-class Token Transformer for Weakly Supervised Semantic...

引用

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

作者： Xu, Lian Ouyang, Wanli Bennamoun, Mohammed Boussaid, Farid Xu, Dan Univ Western Australia Nedlands WA Australia Univ Sydney SenseTime Comp Vis Grp Sydney NSW Australia Hong Kong Univ Sci & Technol Hong Kong Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer model can also effectively capture class-specific attention for more discriminative object localization by learning multiple class tokens within the transformer. To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens. The proposed MCTformer can successfully produce class-discriminative object localization maps from the class-to-patch attentions corresponding to different class tokens. We also propose to use a patchlevel pairwise affinity, which is extracted from the patchto-patch transformer attention, to further refine the localization maps. Moreover, the proposed framework is shown to fully complement the Class Activation Mapping (CAM) method, leading to remarkably superior WSSS results on the PASCAL VOC and MS COCO datasets. These results underline the importance of the class token for WSSS.(-1)

关键词： Location awareness computer vision Shape Semantics Object detection Transformers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Interpolation-based Semi-supervised Learning for Object Detection

Interpolation-based Semi-supervised Learning for Object Dete...

引用

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

作者： Jeong, Jisoo Verma, Vikas Hyun, Minsung Kannala, Juho Kwak, Nojun Seou1 Natl Univ Seoul South Korea Aalto Univ Espoo Finland Mila Quebec Artificial Intelligence Inst Montreal PQ Canada SK Hynix Icheon Si South Korea

ISBN: (纸本)9781665445092

Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much. In this paper, we propose an Interpolation-based Semi-supervised learning method for object Detection (ISD), which considers and solves the problems caused by applying conventional Interpolation Regularization (IR) directly to object detection. We divide the output of the model into two types according to the objectness scores of both original patches that are mixed in IR. Then, we apply a separate loss suitable for each type in an unsupervised manner. The proposed losses dramatically improve the performance of semi-supervised learning as well as supervised learning. In the supervised learning setting, our method improves the baseline methods by a significant margin. In the semi-supervised learning setting, our algorithm improves the performance on a benchmark dataset (PASCAL VOC and MSCOCO) in a benchmark architecture (SSD).

关键词： Interpolation Supervised learning Object detection Detectors computer architecture Semisupervised learning Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Graph-context Attention Networks for Size-varied Deep Graph Matching

Graph-context Attention Networks for Size-varied Deep Graph ...

引用

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

作者： Jiang, Zheheng Rahmani, Hossein Angelov, Plamen Black, Sue Williams, Bryan M. Lancaster Univ Bailrigg Lancaster LA1 4WA England

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Deep learning for graph matching has received growing interest and developed rapidly in the past decade. Although recent deep graph matching methods have shown excellent performance on matching between graphs of equal size in the computer vision area, the size-varied graph matching problem, where the number of keypoints in the images of the same category may vary due to occlusion, is still an open and challenging problem. To tackle this, we firstly propose to formulate the combinatorial problem of graph matching as an Integer Linear Programming (ILP) problem, which is more flexible and efficient to facilitate comparing graphs of varied sizes. A novel Graph-context Attention Network (GCAN), which jointly capture intrinsic graph structure and cross-graph information for improving the discrimination of node features, is then proposed and trained to resolve this ILP problem with node correspondence supervision. We further show that the proposed GCAN model is efficient to resolve the graph-level matching problem and is able to automatically learn node-to-node similarity via graph-level matching. The proposed approach is evaluated on three public keypoint-matching datasets and one graph-matching dataset for blood vessel patterns, with experimental results showing its superior performance over existing state-of-the-art algorithms for keypoint and graph-level matching.

关键词： Training Deep learning computer vision Neural networks Integer linear programming Blood vessels pattern matching

来源：评论

学校读者我要写书评

暂无评论

End-to-end Learning of Driving Models from Large-scale Video Datasets 30

End-to-end Learning of Driving Models from Large-scale Video...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Xu, Huazhe Gao, Yang Yu, Fisher Darrell, Trevor Univ Calif Berkeley Berkeley CA 94720 USA

ISBN: (纸本)9781538604571

Robust perception-action models should be learned from training data with diverse visual appearances and realistic behaviors, yet current approaches to deep visuomotor policy learning have been generally limited to in-situ models learned from a single vehicle or simulation environment. We advocate learning a generic vehicle motion model from large scale crowd-sourced video data, and develop an end-to-end trainable architecture for learning to predict a distribution over future vehicle egomotion from instantaneous monocular camera observations and previous vehicle state. Our model incorporates a novel FCN-LSTM architecture, which can be learned from large-scale crowd-sourced vehicle action data, and leverages available scene segmentation side tasks to improve performance under a privileged learning paradigm. We provide a novel large-scale dataset of crowd-sourced driving behavior suitable for training our model, and report results predicting the driver action on held out sequences across diverse conditions.

关键词： Predictive models Visualization Data models computer architecture Motion segmentation Training

来源：评论

学校读者我要写书评

暂无评论

Feature Decomposition and Reconstruction Learning for Effective Facial Expression recognition

Feature Decomposition and Reconstruction Learning for Effect...

引用

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

作者： Ruan, Delian Yan, Yan Lai, Shenqi Chai, Zhenhua Shen, Chunhua Wang, Hanzi Xiamen Univ Xiamen Peoples R China Meituan Vis Intelligence Ctr Beijing Peoples R China Univ Adelaide Adelaide SA Australia

ISBN: (纸本)9781665445092

In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRI, mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network (MN). In particular, FDN first decomposes the basic features extracted from a backbone network into a set of facial action-aware latent features to model expression similarities. Then, FRN captures the intra-feature and inter feature relationships for latent features to characterize expression-specific variations, and reconstructs the expression feature. To this end, two modules including an intra-feature relation modeling module and an inter-feature relation modeling module are developed in FRN. Experimental results on both the in-the-lab databases (including CK+, MMI, and Oulu-CASIA) and the in-the-wild databases (including RAF-DB and SFEW) show that the proposed FDRL method consistently achieves higher recognition accuracy than several state-of-the-art methods. This clearly highlights the benefit of feature decomposition and reconstruction for classifying expressions.

关键词： computer vision Databases Face recognition Feature extraction

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：