In this paper, we tackle the problem of co-localization in real-world images. Co-localization is the problem of simultaneously localizing (with bounding boxes) objects of the same class across a set of distinct images. Although similar problems such as co-segmentation and weakly supervised localization have been previously studied, we focus on being able to perform co-localization in real-world settings, which are typically characterized by large amounts of intra-class variation, inter-class diversity, and annotation noise. To address these issues, we present a joint image-box formulation for solving the co-localization problem, and show how it can be relaxed to a convex quadratic program which can be efficiently solved. We perform an extensive evaluation of our method compared to previous state-of-the-art approaches on the challenging PASCAL VOC 2007 and Object Discovery datasets. In addition, we also present a large-scale study of co-localization on ImageNet, involving ground-truth annotations for 3, 624 classes and approximately 1 million images.
{"title":"Co-localization in Real-World Images","authors":"K. Tang, Armand Joulin, Li-Jia Li, Li Fei-Fei","doi":"10.1109/CVPR.2014.190","DOIUrl":"https://doi.org/10.1109/CVPR.2014.190","url":null,"abstract":"In this paper, we tackle the problem of co-localization in real-world images. Co-localization is the problem of simultaneously localizing (with bounding boxes) objects of the same class across a set of distinct images. Although similar problems such as co-segmentation and weakly supervised localization have been previously studied, we focus on being able to perform co-localization in real-world settings, which are typically characterized by large amounts of intra-class variation, inter-class diversity, and annotation noise. To address these issues, we present a joint image-box formulation for solving the co-localization problem, and show how it can be relaxed to a convex quadratic program which can be efficiently solved. We perform an extensive evaluation of our method compared to previous state-of-the-art approaches on the challenging PASCAL VOC 2007 and Object Discovery datasets. In addition, we also present a large-scale study of co-localization on ImageNet, involving ground-truth annotations for 3, 624 classes and approximately 1 million images.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124081526","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}
The underlying idea of multitask learning is that learning tasks jointly is better than learning each task individually. In particular, if only a few training examples are available for each task, sharing a jointly trained representation improves classification performance. In this paper, we propose a novel multitask learning method that learns a low-dimensional representation jointly with the corresponding classifiers, which are then able to profit from the latent inter-class correlations. Our method scales with respect to the original feature dimension and can be used with high-dimensional image descriptors such as the Fisher Vector. Furthermore, it consistently outperforms the current state of the art on the SUN397 scene classification benchmark with varying amounts of training data.
{"title":"Scalable Multitask Representation Learning for Scene Classification","authors":"Maksim Lapin, B. Schiele, Matthias Hein","doi":"10.1109/CVPR.2014.186","DOIUrl":"https://doi.org/10.1109/CVPR.2014.186","url":null,"abstract":"The underlying idea of multitask learning is that learning tasks jointly is better than learning each task individually. In particular, if only a few training examples are available for each task, sharing a jointly trained representation improves classification performance. In this paper, we propose a novel multitask learning method that learns a low-dimensional representation jointly with the corresponding classifiers, which are then able to profit from the latent inter-class correlations. Our method scales with respect to the original feature dimension and can be used with high-dimensional image descriptors such as the Fisher Vector. Furthermore, it consistently outperforms the current state of the art on the SUN397 scene classification benchmark with varying amounts of training data.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124152318","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}
We present a novel way to automatically summarize and represent the storyline of a TV episode by visualizing character interactions as a chart. We also propose a scene detection method that lends itself well to generate over-segmented scenes which is used to partition the video. The positioning of character lines in the chart is formulated as an optimization problem which trades between the aesthetics and functionality of the chart. Using automatic person identification, we present StoryGraphs for 3 diverse TV series encompassing a total of 22 episodes. We define quantitative criteria to evaluate StoryGraphs and also compare them against episode summaries to evaluate their ability to provide an overview of the episode.
{"title":"StoryGraphs: Visualizing Character Interactions as a Timeline","authors":"Makarand Tapaswi, M. Bäuml, R. Stiefelhagen","doi":"10.1109/CVPR.2014.111","DOIUrl":"https://doi.org/10.1109/CVPR.2014.111","url":null,"abstract":"We present a novel way to automatically summarize and represent the storyline of a TV episode by visualizing character interactions as a chart. We also propose a scene detection method that lends itself well to generate over-segmented scenes which is used to partition the video. The positioning of character lines in the chart is formulated as an optimization problem which trades between the aesthetics and functionality of the chart. Using automatic person identification, we present StoryGraphs for 3 diverse TV series encompassing a total of 22 episodes. We define quantitative criteria to evaluate StoryGraphs and also compare them against episode summaries to evaluate their ability to provide an overview of the episode.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"289 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124165914","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}
The initial steps of many computer vision algorithms are interest point extraction and matching. In larger image sets the pairwise matching of interest point descriptors between images is an important bottleneck. For each descriptor in one image the (approximate) nearest neighbor in the other one has to be found and checked against the second-nearest neighbor to ensure the correspondence is unambiguous. Here, we asked the question how to best decimate the list of interest points without losing matches, i.e. we aim to speed up matching by filtering out, in advance, those points which would not survive the matching stage. It turns out that the best filtering criterion is not the response of the interest point detector, which in fact is not surprising: the goal of detection are repeatable and well-localized points, whereas the objective of the selection are points whose descriptors can be matched successfully. We show that one can in fact learn to predict which descriptors are matchable, and thus reduce the number of interest points significantly without losing too many matches. We show that this strategy, as simple as it is, greatly improves the matching success with the same number of points per image. Moreover, we embed the prediction in a state-of-the-art Structure-from-Motion pipeline and demonstrate that it also outperforms other selection methods at system level.
{"title":"Predicting Matchability","authors":"Wilfried Hartmann, M. Havlena, K. Schindler","doi":"10.1109/CVPR.2014.9","DOIUrl":"https://doi.org/10.1109/CVPR.2014.9","url":null,"abstract":"The initial steps of many computer vision algorithms are interest point extraction and matching. In larger image sets the pairwise matching of interest point descriptors between images is an important bottleneck. For each descriptor in one image the (approximate) nearest neighbor in the other one has to be found and checked against the second-nearest neighbor to ensure the correspondence is unambiguous. Here, we asked the question how to best decimate the list of interest points without losing matches, i.e. we aim to speed up matching by filtering out, in advance, those points which would not survive the matching stage. It turns out that the best filtering criterion is not the response of the interest point detector, which in fact is not surprising: the goal of detection are repeatable and well-localized points, whereas the objective of the selection are points whose descriptors can be matched successfully. We show that one can in fact learn to predict which descriptors are matchable, and thus reduce the number of interest points significantly without losing too many matches. We show that this strategy, as simple as it is, greatly improves the matching success with the same number of points per image. Moreover, we embed the prediction in a state-of-the-art Structure-from-Motion pipeline and demonstrate that it also outperforms other selection methods at system level.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127786627","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}
Several popular and effective object detectors separately model intra-class variations arising from deformations and appearance changes. This reduces model complexity while enabling the detection of objects across changes in view- point, object pose, etc. The Deformable Part Model (DPM) is perhaps the most successful such model to date. A common assumption is that the exponential number of templates enabled by a DPM is critical to its success. In this paper, we show the counter-intuitive result that it is possible to achieve similar accuracy using a small dictionary of deformations. Each component in our model is represented by a single HOG template and a dictionary of flow fields that determine the deformations the template may undergo. While the number of candidate deformations is dramatically fewer than that for a DPM, the deformed templates tend to be plausible and interpretable. In addition, we discover that the set of deformation bases is actually transferable across object categories and that learning shared bases across similar categories can boost accuracy.
{"title":"Detecting Objects Using Deformation Dictionaries","authors":"Bharath Hariharan, C. L. Zitnick, Piotr Dollár","doi":"10.1109/CVPR.2014.256","DOIUrl":"https://doi.org/10.1109/CVPR.2014.256","url":null,"abstract":"Several popular and effective object detectors separately model intra-class variations arising from deformations and appearance changes. This reduces model complexity while enabling the detection of objects across changes in view- point, object pose, etc. The Deformable Part Model (DPM) is perhaps the most successful such model to date. A common assumption is that the exponential number of templates enabled by a DPM is critical to its success. In this paper, we show the counter-intuitive result that it is possible to achieve similar accuracy using a small dictionary of deformations. Each component in our model is represented by a single HOG template and a dictionary of flow fields that determine the deformations the template may undergo. While the number of candidate deformations is dramatically fewer than that for a DPM, the deformed templates tend to be plausible and interpretable. In addition, we discover that the set of deformation bases is actually transferable across object categories and that learning shared bases across similar categories can boost accuracy.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126481568","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}
State-of-the-art general purpose Blind Image Quality Assessment (BIQA) models rely on examples of distorted images and corresponding human opinion scores to learn a regression function that maps image features to a quality score. These types of models are considered "opinion-aware" (OA) BIQA models. A large set of human scored training examples is usually required to train a reliable OA-BIQA model. However, obtaining human opinion scores through subjective testing is often expensive and time-consuming. It is therefore desirable to develop "opinion-free" (OF) BIQA models that do not require human opinion scores for training. This paper proposes BLISS (Blind Learning of Image Quality using Synthetic Scores). BLISS is a simple, yet effective method for extending OA-BIQA models to OF-BIQA models. Instead of training on human opinion scores, we propose to train BIQA models on synthetic scores derived from Full-Reference (FR) IQA measures. State-of-the-art FR measures yield high correlation with human opinion scores and can serve as approximations to human opinion scores. Unsupervised rank aggregation is applied to combine different FR measures to generate a synthetic score, which serves as a better "gold standard". Extensive experiments on standard IQA datasets show that BLISS significantly outperforms previous OF-BIQA methods and is comparable to state-of-the-art OA-BIQA methods.
最先进的通用盲图像质量评估(BIQA)模型依赖于扭曲图像的示例和相应的人类意见分数来学习将图像特征映射到质量分数的回归函数。这些类型的模型被认为是“意见感知”(OA) BIQA模型。为了训练一个可靠的OA-BIQA模型，通常需要大量的人类得分训练样本。然而，通过主观测试获得人类的意见得分往往是昂贵和耗时的。因此，开发“无意见”(OF) BIQA模型是可取的，这种模型不需要人类的意见分数来进行训练。本文提出了BLISS (Blind Learning of Image Quality using Synthetic Scores)。BLISS是将OA-BIQA模型扩展到OF-BIQA模型的一种简单而有效的方法。我们建议使用来自全参考(FR) IQA度量的合成分数来训练BIQA模型，而不是对人类意见分数进行训练。最先进的FR测量与人类意见得分具有高度相关性，可以作为人类意见得分的近似值。采用无监督秩聚合法，将不同的FR度量结合起来，生成一个综合分数，作为更好的“金标准”。在标准IQA数据集上进行的大量实验表明，BLISS显著优于以前的OF-BIQA方法，并可与最先进的OA-BIQA方法相媲美。
{"title":"Beyond Human Opinion Scores: Blind Image Quality Assessment Based on Synthetic Scores","authors":"Peng Ye, J. Kumar, D. Doermann","doi":"10.1109/CVPR.2014.540","DOIUrl":"https://doi.org/10.1109/CVPR.2014.540","url":null,"abstract":"State-of-the-art general purpose Blind Image Quality Assessment (BIQA) models rely on examples of distorted images and corresponding human opinion scores to learn a regression function that maps image features to a quality score. These types of models are considered \"opinion-aware\" (OA) BIQA models. A large set of human scored training examples is usually required to train a reliable OA-BIQA model. However, obtaining human opinion scores through subjective testing is often expensive and time-consuming. It is therefore desirable to develop \"opinion-free\" (OF) BIQA models that do not require human opinion scores for training. This paper proposes BLISS (Blind Learning of Image Quality using Synthetic Scores). BLISS is a simple, yet effective method for extending OA-BIQA models to OF-BIQA models. Instead of training on human opinion scores, we propose to train BIQA models on synthetic scores derived from Full-Reference (FR) IQA measures. State-of-the-art FR measures yield high correlation with human opinion scores and can serve as approximations to human opinion scores. Unsupervised rank aggregation is applied to combine different FR measures to generate a synthetic score, which serves as a better \"gold standard\". Extensive experiments on standard IQA datasets show that BLISS significantly outperforms previous OF-BIQA methods and is comparable to state-of-the-art OA-BIQA methods.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125482057","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}
S. Stein, Markus Schoeler, Jeremie Papon, F. Wörgötter
The problem of how to arrive at an appropriate 3D-segmentation of a scene remains difficult. While current state-of-the-art methods continue to gradually improve in benchmark performance, they also grow more and more complex, for example by incorporating chains of classifiers, which require training on large manually annotated data-sets. As an alternative to this, we present a new, efficient learning- and model-free approach for the segmentation of 3D point clouds into object parts. The algorithm begins by decomposing the scene into an adjacency-graph of surface patches based on a voxel grid. Edges in the graph are then classified as either convex or concave using a novel combination of simple criteria which operate on the local geometry of these patches. This way the graph is divided into locally convex connected subgraphs, which -- with high accuracy -- represent object parts. Additionally, we propose a novel depth dependent voxel grid to deal with the decreasing point-density at far distances in the point clouds. This improves segmentation, allowing the use of fixed parameters for vastly different scenes. The algorithm is straightforward to implement and requires no training data, while nevertheless producing results that are comparable to state-of-the-art methods which incorporate high-level concepts involving classification, learning and model fitting.
{"title":"Object Partitioning Using Local Convexity","authors":"S. Stein, Markus Schoeler, Jeremie Papon, F. Wörgötter","doi":"10.1109/CVPR.2014.46","DOIUrl":"https://doi.org/10.1109/CVPR.2014.46","url":null,"abstract":"The problem of how to arrive at an appropriate 3D-segmentation of a scene remains difficult. While current state-of-the-art methods continue to gradually improve in benchmark performance, they also grow more and more complex, for example by incorporating chains of classifiers, which require training on large manually annotated data-sets. As an alternative to this, we present a new, efficient learning- and model-free approach for the segmentation of 3D point clouds into object parts. The algorithm begins by decomposing the scene into an adjacency-graph of surface patches based on a voxel grid. Edges in the graph are then classified as either convex or concave using a novel combination of simple criteria which operate on the local geometry of these patches. This way the graph is divided into locally convex connected subgraphs, which -- with high accuracy -- represent object parts. Additionally, we propose a novel depth dependent voxel grid to deal with the decreasing point-density at far distances in the point clouds. This improves segmentation, allowing the use of fixed parameters for vastly different scenes. The algorithm is straightforward to implement and requires no training data, while nevertheless producing results that are comparable to state-of-the-art methods which incorporate high-level concepts involving classification, learning and model fitting.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127961245","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}
This paper presents a highly efficient, very accurate regression approach for face alignment. Our approach has two novel components: a set of local binary features, and a locality principle for learning those features. The locality principle guides us to learn a set of highly discriminative local binary features for each facial landmark independently. The obtained local binary features are used to jointly learn a linear regression for the final output. Our approach achieves the state-of-the-art results when tested on the current most challenging benchmarks. Furthermore, because extracting and regressing local binary features is computationally very cheap, our system is much faster than previous methods. It achieves over 3, 000 fps on a desktop or 300 fps on a mobile phone for locating a few dozens of landmarks.
{"title":"Face Alignment at 3000 FPS via Regressing Local Binary Features","authors":"Shaoqing Ren, Xudong Cao, Yichen Wei, Jian Sun","doi":"10.1109/CVPR.2014.218","DOIUrl":"https://doi.org/10.1109/CVPR.2014.218","url":null,"abstract":"This paper presents a highly efficient, very accurate regression approach for face alignment. Our approach has two novel components: a set of local binary features, and a locality principle for learning those features. The locality principle guides us to learn a set of highly discriminative local binary features for each facial landmark independently. The obtained local binary features are used to jointly learn a linear regression for the final output. Our approach achieves the state-of-the-art results when tested on the current most challenging benchmarks. Furthermore, because extracting and regressing local binary features is computationally very cheap, our system is much faster than previous methods. It achieves over 3, 000 fps on a desktop or 300 fps on a mobile phone for locating a few dozens of landmarks.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"251 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115843920","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}
Mattis Paulin, Jérôme Revaud, Zaïd Harchaoui, F. Perronnin, C. Schmid
A simple approach to learning invariances in image classification consists in augmenting the training set with transformed versions of the original images. However, given a large set of possible transformations, selecting a compact subset is challenging. Indeed, all transformations are not equally informative and adding uninformative transformations increases training time with no gain in accuracy. We propose a principled algorithm -- Image Transformation Pursuit (ITP) -- for the automatic selection of a compact set of transformations. ITP works in a greedy fashion, by selecting at each iteration the one that yields the highest accuracy gain. ITP also allows to efficiently explore complex transformations, that combine basic transformations. We report results on two public benchmarks: the CUB dataset of bird images and the ImageNet 2010 challenge. Using Fisher Vector representations, we achieve an improvement from 28.2% to 45.2% in top-1 accuracy on CUB, and an improvement from 70.1% to 74.9% in top-5 accuracy on ImageNet. We also show significant improvements for deep convnet features: from 47.3% to 55.4% on CUB and from 77.9% to 81.4% on ImageNet.
{"title":"Transformation Pursuit for Image Classification","authors":"Mattis Paulin, Jérôme Revaud, Zaïd Harchaoui, F. Perronnin, C. Schmid","doi":"10.1109/CVPR.2014.466","DOIUrl":"https://doi.org/10.1109/CVPR.2014.466","url":null,"abstract":"A simple approach to learning invariances in image classification consists in augmenting the training set with transformed versions of the original images. However, given a large set of possible transformations, selecting a compact subset is challenging. Indeed, all transformations are not equally informative and adding uninformative transformations increases training time with no gain in accuracy. We propose a principled algorithm -- Image Transformation Pursuit (ITP) -- for the automatic selection of a compact set of transformations. ITP works in a greedy fashion, by selecting at each iteration the one that yields the highest accuracy gain. ITP also allows to efficiently explore complex transformations, that combine basic transformations. We report results on two public benchmarks: the CUB dataset of bird images and the ImageNet 2010 challenge. Using Fisher Vector representations, we achieve an improvement from 28.2% to 45.2% in top-1 accuracy on CUB, and an improvement from 70.1% to 74.9% in top-5 accuracy on ImageNet. We also show significant improvements for deep convnet features: from 47.3% to 55.4% on CUB and from 77.9% to 81.4% on ImageNet.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129993651","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}
Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, S. Fidler, R. Urtasun, A. Yuille
In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of existing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.
{"title":"The Role of Context for Object Detection and Semantic Segmentation in the Wild","authors":"Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, S. Fidler, R. Urtasun, A. Yuille","doi":"10.1109/CVPR.2014.119","DOIUrl":"https://doi.org/10.1109/CVPR.2014.119","url":null,"abstract":"In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of existing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134428775","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：