2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)最新文献

筛选
英文 中文
Classifying and Comparing Approaches to Subspace Clustering with Missing Data 缺失数据子空间聚类的分类与比较方法
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00081
Connor Lane, Ron Boger, Chong You, M. Tsakiris, B. Haeffele, R. Vidal
{"title":"Classifying and Comparing Approaches to Subspace Clustering with Missing Data","authors":"Connor Lane, Ron Boger, Chong You, M. Tsakiris, B. Haeffele, R. Vidal","doi":"10.1109/ICCVW.2019.00081","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00081","url":null,"abstract":"In recent years, many methods have been proposed for the task of subspace clustering with missing data (SCMD), and its complementary problem, high-rank matrix completion (HRMC). Given incomplete data drawn from a union of subspaces, these methods aim to simultaneously cluster each data point and recover the unobserved entries. In this work, we review the current state of this literature. We organize the existing methods into five distinct families and discuss their relative strengths and weaknesses. This classification exposes some gaps in the current literature, which we fill by introducing a few natural extensions of prior methods. Finally, we provide a thorough and unbiased evaluation of representative methods on synthetic data. Our experiments demonstrate a clear advantage for alternating between projected zero-filled sparse subspace clustering, and per-group matrix completion. Understanding why this intuitive but heuristic method performs well is an open problem for future theoretical study.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121815072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 13
Cross-Modal Person Search: A Coarse-to-Fine Framework using Bi-Directional Text-Image Matching 跨模态人物搜索:基于双向文本-图像匹配的从粗到精框架
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00223
Xiaojing Yu, Tianlong Chen, Yang Yang, M. Mugo, Zhangyang Wang
{"title":"Cross-Modal Person Search: A Coarse-to-Fine Framework using Bi-Directional Text-Image Matching","authors":"Xiaojing Yu, Tianlong Chen, Yang Yang, M. Mugo, Zhangyang Wang","doi":"10.1109/ICCVW.2019.00223","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00223","url":null,"abstract":"Searching person images from a gallery based on natural language descriptions remains to be a challenging and under-explored cross-modal retrieval problem. To improve the accuracy off an image-based retrieval task, e.g., person re-identification (Person Re-Id), re-ranking is known to be an effective post-processing tool. In this paper, we extend re-ranking from uni-modal retrieval to cross-modal retrieval for the first time, and develop a bi-directional coarse-to-fine framework (BCF) for cross-modal person search. Built on a recent state-of-the-art Person Re-Id model, BCF exploits first text-to-image and then image-to-text relevance, in a two-stage refinement fashion. BCF ranks competitively against a strong baseline on the newly-introduced WIDER Person Search dataset, boosting validation set performance by 9.01%(top-1)/3.87%(mAP) for val1 and 6.60%(top-1)/3.49%(mAP) for val2, respectively. With a high score, our solution ranks competitively in the ICCV 2019 WIDER Person Search by Language Challenge.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116697784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Dynamic Block Sparse Reparameterization of Convolutional Neural Networks 卷积神经网络的动态块稀疏重参数化
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00367
Dharma Teja Vooturi, G. Varma, Kishore Kothapalli
{"title":"Dynamic Block Sparse Reparameterization of Convolutional Neural Networks","authors":"Dharma Teja Vooturi, G. Varma, Kishore Kothapalli","doi":"10.1109/ICCVW.2019.00367","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00367","url":null,"abstract":"Sparse neural networks are efficient in both memory and compute when compared to dense neural networks. But on parallel hardware such as GPU, sparse neural networks result in small or no runtime performance gains. On the other hand, structured sparsity patterns like filter, channel and block sparsity result in large performance gains due to regularity induced by structure. Among structured sparsities, block sparsity is a generic structured sparsity pattern with filter and channel sparsity being sub cases of block sparsity. In this work, we focus on block sparsity and generate efficient block sparse convolutional neural networks using our approach DBSR (Dynamic block sparse reparameterization). Our DBSR approach, when applied on image classification task over Imagenet dataset, decreases parameters and FLOPS of ResneXt50 by a factor of 2x with only increase of 0.48 in Top-1 error. And when extended to the task of semantic segmentation, our approach reduces parameters and FLOPS by 30% and 20% respectively with only 1% decrease in mIoU for ERFNet over Cityscapes dataset. To ease developments in this line of work, we open sourced our code on github (https://github.com/idharmateja/bsnn).","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116772718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 13
A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-Identification 小尺度人物再识别的半监督最大边际度量学习方法
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00230
T. Ali, S. Chaudhuri
{"title":"A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-Identification","authors":"T. Ali, S. Chaudhuri","doi":"10.1109/ICCVW.2019.00230","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00230","url":null,"abstract":"In video surveillance, person re-identification is the task of searching person images in non-overlapping cameras. Though supervised methods for person re-identification have attained impressive performance, obtaining large scale cross-view labeled training data is very expensive. However, unlabelled data is available in abundance. In this paper, we propose a semi-supervised metric learning approach that can utilize information in unlabelled data with the help of a few labelled training samples. We also address the small sample size problem that inherently occurs due to the few labeled training data. Our method learns a discriminative space where within class samples collapse to singular points, achieving the least within class variance, and then use a maximum margin criterion over a high dimensional kernel space to maximally separate the distinct class samples. A maximum margin criterion with two levels of high dimensional mappings to kernel space is used to obtain better cross-view discrimination of the identities. Cross-view affinity learning with reciprocal nearest neighbor constraints is used to mine new pseudo-classes from the unlabelled data and update the distance metric iteratively. We attain state-of-the-art performance on four challenging datasets with a large margin.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121125486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
SalGaze: Personalizing Gaze Estimation using Visual Saliency SalGaze:使用视觉显著性进行个性化凝视估计
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00148
Zhuoqing Chang, J. Matias Di Martino, Qiang Qiu, Steven Espinosa, G. Sapiro
{"title":"SalGaze: Personalizing Gaze Estimation using Visual Saliency","authors":"Zhuoqing Chang, J. Matias Di Martino, Qiang Qiu, Steven Espinosa, G. Sapiro","doi":"10.1109/ICCVW.2019.00148","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00148","url":null,"abstract":"Traditional gaze estimation methods typically require explicit user calibration to achieve high accuracy. This process is cumbersome and recalibration is often required when there are changes in factors such as illumination and pose. To address this challenge, we introduce SalGaze, a framework that utilizes saliency information in the visual content to transparently adapt the gaze estimation algorithm to the user without explicit user calibration. We design an algorithm to transform a saliency map into a differentiable loss map that can be used for the optimization of CNN-based models. SalGaze is also able to greatly augment standard point calibration data with implicit video saliency calibration data using a unified framework. We show accuracy improvements over 24% using our technique on existing methods.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123295569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 10
Cross-Granularity Attention Network for Semantic Segmentation 语义分割的跨粒度注意网络
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00241
Lingyu Zhu, T. Wang, Emre B. Aksu, Joni-Kristian Kämäräinen
{"title":"Cross-Granularity Attention Network for Semantic Segmentation","authors":"Lingyu Zhu, T. Wang, Emre B. Aksu, Joni-Kristian Kämäräinen","doi":"10.1109/ICCVW.2019.00241","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00241","url":null,"abstract":"Despite the remarkable progress of semantic segmentation in recent years, much remains to be addressed in order to achieve better semantic coherence and boundary delineation. In this paper, we propose a novel convolutional neural network (CNN) architecture for semantic segmentation which explicitly addresses these two issues. Specifically, we propose a categorical attention mechanism to propagate consistent category-oriented information across multi-granularity contextual interpretations to close the semantic gap residing in CNN feature hierarchy. This novel design alleviates the semantic information loss during the feature combination and transformation process in decoder network. We further integrate a contour branch in our architecture to enhance the boundary awareness of the semantic feature derived in the form of a novel element-wise contour attention at each level of feature hierarchy. Additionally, we introduce a cross-granularity contour enhancement mechanism to propagate rich boundary cues from early layers to deep layers. We perform extensive quantitative evaluations in close proximity to object boundaries which confirms its superior effectiveness in boundary delineation. These novel mechanisms which boost the essentials in segmentation, i.e., region-wise semantic coherence and accurate object contour localization, allow our architecture \"MeshNet\" to obtain state-of-the-art performance on two challenging datasets, i.e., PASCAL VOC 2012 and Cityscapes.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123798478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
NoUCSR: Efficient Super-Resolution Network without Upsampling Convolution 无上采样卷积的高效超分辨率网络
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00420
Dongliang Xiong, Kai Huang, Siang Chen, Bowen Li, Haitian Jiang, Wenyuan Xu
{"title":"NoUCSR: Efficient Super-Resolution Network without Upsampling Convolution","authors":"Dongliang Xiong, Kai Huang, Siang Chen, Bowen Li, Haitian Jiang, Wenyuan Xu","doi":"10.1109/ICCVW.2019.00420","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00420","url":null,"abstract":"Deep learning approaches have been ubiquitous in single image super-resolution ever since the success of SRCNN. However, the superior performance is based on high requirement of computational resources, limiting the application of deep learning approaches in resource-constrained embedded and mobile devices. In this paper, we firstly show that the convolution layers in upsampling block are parameter-and computation-intensive. Secondly, we find that replacing upsampling convolution by concatenating different level features can reduce parameters and inference runtime significantly, while keeping same performance. Finally, we introduce an efficient model without upsampling convolution called NoUCSR, and present variant models optimizing parameter, inference runtime and performance respectively at the constraint of MSRResNet. The experiments show that NoUCSR can achieve a better tradeoff among parameter, inference runtime and performance than state-of-the-art methods.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115512218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Assessment of Optical See-Through Head Mounted Display Calibration for Interactive Augmented Reality 交互式增强现实中光学透明头戴式显示器校准的评估
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00546
Giorgio Ballestin, Manuela Chessa, F. Solari
{"title":"Assessment of Optical See-Through Head Mounted Display Calibration for Interactive Augmented Reality","authors":"Giorgio Ballestin, Manuela Chessa, F. Solari","doi":"10.1109/ICCVW.2019.00546","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00546","url":null,"abstract":"Interaction in Augmented Reality environments requires the precise alignment of virtual elements added to the real scene. This can be achieved if the egocentric perception of the augmented scene is coherent in both the virtual and the real reference frames. To this aim, a proper calibration of the complete system, composed of the Augmented Reality device, the user and the environment, should be performed. Over the years, several calibration techniques have been proposed, and objectively evaluating their performance has shown to be troublesome. Since only the user can assess the hologram alignment fidelity, most researchers quantify the calibration error with subjective data from user studies. This paper describes the calibration process of an optical see-through device, based on a visual alignment method, and proposes a technique to objectively quantify the residual misalignment error.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116409592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Depth-Guided Dense Dynamic Filtering Network for Bokeh Effect Rendering 用于散景效果渲染的深度引导密集动态过滤网络
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00424
Kuldeep Purohit, Maitreya Suin, Praveen Kandula, Rajagopalan Ambasamudram
{"title":"Depth-Guided Dense Dynamic Filtering Network for Bokeh Effect Rendering","authors":"Kuldeep Purohit, Maitreya Suin, Praveen Kandula, Rajagopalan Ambasamudram","doi":"10.1109/ICCVW.2019.00424","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00424","url":null,"abstract":"Bokeh effect refers to the soft defocus blur of the background, which can be achieved with different aperture and shutter settings in a camera. In this work, we present a learning-based method for rendering such synthetic depth-of-field effect on input bokeh-free images acquired using ordinary monocular cameras. The proposed network is composed of an efficient densely connected encoder-decoder backbone structure with a pyramid pooling module. Our network leverages the task-specific efficacy of joint intensity estimation and dynamic filter synthesis for the spatially-aware blurring process. Since the rendering task requires distinguishing between large foreground and background regions and their relative depth, our network is further guided by pre-trained salient-region segmentation and depth-estimation modules. Experiments on diverse scenes show that our model elegantly introduces the desired effects in the input images, enhancing their aesthetic quality while maintaining a natural appearance. Along with extensive ablation analysis and visualizations to validate its components, the effectiveness of the proposed network is also demonstrated by achieving the second-highest score in the AIM 2019 Bokeh Effect challenge: fidelity track.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114170893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 24
To Bundle Adjust or Not: A Comparison of Relative Geolocation Correction Strategies for Satellite Multi-View Stereo 是否捆绑调整:卫星多视点立体相对地理位置校正策略比较
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Pub Date : 2019-10-01 DOI: 10.1109/ICCVW.2019.00274
R. Marí, C. D. Franchis, E. Meinhardt, G. Facciolo
{"title":"To Bundle Adjust or Not: A Comparison of Relative Geolocation Correction Strategies for Satellite Multi-View Stereo","authors":"R. Marí, C. D. Franchis, E. Meinhardt, G. Facciolo","doi":"10.1109/ICCVW.2019.00274","DOIUrl":"https://doi.org/10.1109/ICCVW.2019.00274","url":null,"abstract":"The generation of up-to-date accurate 3D models from multi-view satellite images has recently become a hot research topic. A well-known challenge of this problem is to put all cameras into a common frame of reference, since depending on the satellite geopositioning equipment the camera parameters may contain errors of up to tens of meters on the ground. In this context, bundle adjustment based techniques, relying on the identification of a set of tie-points and the correction of the camera models to make them coincident, have become a generally accepted practice. However, new approaches capable of producing state-of-the-art results without the use of prior bundle adjustment have also been proposed. This work aims to compare both strategies and assess the practical impact of using bundle adjustment for 3D reconstruction from multi-view satellite images.","PeriodicalId":300667,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122188506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书