Mengjiao MJ Wang, Yannis Panagakis, Patrick Snape, S. Zafeiriou
Statistical decomposition methods are of paramount importance in discovering the modes of variations of visual data. Probably the most prominent linear decomposition method is the Principal Component Analysis (PCA), which discovers a single mode of variation in the data. However, in practice, visual data exhibit several modes of variations. For instance, the appearance of faces varies in identity, expression, pose etc. To extract these modes of variations from visual data, several supervised methods, such as the TensorFaces, that rely on multilinear (tensor) decomposition (e.g., Higher Order SVD) have been developed. The main drawbacks of such methods is that they require both labels regarding the modes of variations and the same number of samples under all modes of variations (e.g., the same face under different expressions, poses etc.). Therefore, their applicability is limited to well-organised data, usually captured in well-controlled conditions. In this paper, we propose the first general multilinear method, to the best of our knowledge, that discovers the multilinear structure of visual data in unsupervised setting. That is, without the presence of labels. We demonstrate the applicability of the proposed method in two applications, namely Shape from Shading (SfS) and expression transfer.
{"title":"Learning the Multilinear Structure of Visual Data","authors":"Mengjiao MJ Wang, Yannis Panagakis, Patrick Snape, S. Zafeiriou","doi":"10.1109/CVPR.2017.641","DOIUrl":"https://doi.org/10.1109/CVPR.2017.641","url":null,"abstract":"Statistical decomposition methods are of paramount importance in discovering the modes of variations of visual data. Probably the most prominent linear decomposition method is the Principal Component Analysis (PCA), which discovers a single mode of variation in the data. However, in practice, visual data exhibit several modes of variations. For instance, the appearance of faces varies in identity, expression, pose etc. To extract these modes of variations from visual data, several supervised methods, such as the TensorFaces, that rely on multilinear (tensor) decomposition (e.g., Higher Order SVD) have been developed. The main drawbacks of such methods is that they require both labels regarding the modes of variations and the same number of samples under all modes of variations (e.g., the same face under different expressions, poses etc.). Therefore, their applicability is limited to well-organised data, usually captured in well-controlled conditions. In this paper, we propose the first general multilinear method, to the best of our knowledge, that discovers the multilinear structure of visual data in unsupervised setting. That is, without the presence of labels. We demonstrate the applicability of the proposed method in two applications, namely Shape from Shading (SfS) and expression transfer.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"5 1","pages":"6053-6061"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76382666","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 work addresses fine-grained image classification. Our work is based on the hypothesis that when dealing with subtle differences among object classes it is critical to identify and only account for a few informative image parts, as the remaining image context may not only be uninformative but may also hurt recognition. This motivates us to formulate our problem as a sequential search for informative parts over a deep feature map produced by a deep Convolutional Neural Network (CNN). A state of this search is a set of proposal bounding boxes in the image, whose informativeness is evaluated by the heuristic function (H), and used for generating new candidate states by the successor function (S). The two functions are unified via a Long Short-Term Memory network (LSTM) into a new deep recurrent architecture, called HSnet. Thus, HSnet (i) generates proposals of informative image parts and (ii) fuses all proposals toward final fine-grained recognition. We specify both supervised and weakly supervised training of HSnet depending on the availability of object part annotations. Evaluation on the benchmark Caltech-UCSD Birds 200-2011 and Cars-196 datasets demonstrate our competitive performance relative to the state of the art.
{"title":"Fine-Grained Recognition as HSnet Search for Informative Image Parts","authors":"Michael Lam, Behrooz Mahasseni, S. Todorovic","doi":"10.1109/CVPR.2017.688","DOIUrl":"https://doi.org/10.1109/CVPR.2017.688","url":null,"abstract":"This work addresses fine-grained image classification. Our work is based on the hypothesis that when dealing with subtle differences among object classes it is critical to identify and only account for a few informative image parts, as the remaining image context may not only be uninformative but may also hurt recognition. This motivates us to formulate our problem as a sequential search for informative parts over a deep feature map produced by a deep Convolutional Neural Network (CNN). A state of this search is a set of proposal bounding boxes in the image, whose informativeness is evaluated by the heuristic function (H), and used for generating new candidate states by the successor function (S). The two functions are unified via a Long Short-Term Memory network (LSTM) into a new deep recurrent architecture, called HSnet. Thus, HSnet (i) generates proposals of informative image parts and (ii) fuses all proposals toward final fine-grained recognition. We specify both supervised and weakly supervised training of HSnet depending on the availability of object part annotations. Evaluation on the benchmark Caltech-UCSD Birds 200-2011 and Cars-196 datasets demonstrate our competitive performance relative to the state of the art.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"15 1","pages":"6497-6506"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87117712","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 propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images. Key to our approach is the generation and scoring of a number of pose proposals per image, which allows us to predict 2D and 3D pose of multiple people simultaneously. Hence, our approach does not require an approximate localization of the humans for initialization. Our architecture, named LCR-Net, contains 3 main components: 1) the pose proposal generator that suggests potential poses at different locations in the image, 2) a classifier that scores the different pose proposals, and 3) a regressor that refines pose proposals both in 2D and 3D. All three stages share the convolutional feature layers and are trained jointly. The final pose estimation is obtained by integrating over neighboring pose hypotheses, which is shown to improve over a standard non maximum suppression algorithm. Our approach significantly outperforms the state of the art in 3D pose estimation on Human3.6M, a controlled environment. Moreover, it shows promising results on real images for both single and multi-person subsets of the MPII 2D pose benchmark.
{"title":"LCR-Net: Localization-Classification-Regression for Human Pose","authors":"Grégory Rogez, Philippe Weinzaepfel, C. Schmid","doi":"10.1109/CVPR.2017.134","DOIUrl":"https://doi.org/10.1109/CVPR.2017.134","url":null,"abstract":"We propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images. Key to our approach is the generation and scoring of a number of pose proposals per image, which allows us to predict 2D and 3D pose of multiple people simultaneously. Hence, our approach does not require an approximate localization of the humans for initialization. Our architecture, named LCR-Net, contains 3 main components: 1) the pose proposal generator that suggests potential poses at different locations in the image, 2) a classifier that scores the different pose proposals, and 3) a regressor that refines pose proposals both in 2D and 3D. All three stages share the convolutional feature layers and are trained jointly. The final pose estimation is obtained by integrating over neighboring pose hypotheses, which is shown to improve over a standard non maximum suppression algorithm. Our approach significantly outperforms the state of the art in 3D pose estimation on Human3.6M, a controlled environment. Moreover, it shows promising results on real images for both single and multi-person subsets of the MPII 2D pose benchmark.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"181 1","pages":"1216-1224"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85560699","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 method to track 3D models in color and depth data. To this end, we introduce approximations that accelerate the state-of-the-art in region-based tracking by an order of magnitude while retaining similar accuracy. Furthermore, we show how the method can be made more robust in the presence of depth data and consequently formulate a new joint contour and ICP tracking energy. We present better results than the state-of-the-art while being much faster then most other methods and achieving all of the above on a single CPU core.
{"title":"Real-Time 3D Model Tracking in Color and Depth on a Single CPU Core","authors":"Wadim Kehl, Federico Tombari, Slobodan Ilic, Nassir Navab","doi":"10.1109/CVPR.2017.57","DOIUrl":"https://doi.org/10.1109/CVPR.2017.57","url":null,"abstract":"We present a novel method to track 3D models in color and depth data. To this end, we introduce approximations that accelerate the state-of-the-art in region-based tracking by an order of magnitude while retaining similar accuracy. Furthermore, we show how the method can be made more robust in the presence of depth data and consequently formulate a new joint contour and ICP tracking energy. We present better results than the state-of-the-art while being much faster then most other methods and achieving all of the above on a single CPU core.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"73 1","pages":"465-473"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86373315","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}
Localizing functional regions of objects or affordances is an important aspect of scene understanding and relevant for many robotics applications. In this work, we introduce a pixel-wise annotated affordance dataset of 3090 images containing 9916 object instances. Since parts of an object can have multiple affordances, we address this by a convolutional neural network for multilabel affordance segmentation. We also propose an approach to train the network from very few keypoint annotations. Our approach achieves a higher affordance detection accuracy than other weakly supervised methods that also rely on keypoint annotations or image annotations as weak supervision.
{"title":"Weakly Supervised Affordance Detection","authors":"Johann Sawatzky, A. Srikantha, Juergen Gall","doi":"10.1109/CVPR.2017.552","DOIUrl":"https://doi.org/10.1109/CVPR.2017.552","url":null,"abstract":"Localizing functional regions of objects or affordances is an important aspect of scene understanding and relevant for many robotics applications. In this work, we introduce a pixel-wise annotated affordance dataset of 3090 images containing 9916 object instances. Since parts of an object can have multiple affordances, we address this by a convolutional neural network for multilabel affordance segmentation. We also propose an approach to train the network from very few keypoint annotations. Our approach achieves a higher affordance detection accuracy than other weakly supervised methods that also rely on keypoint annotations or image annotations as weak supervision.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"13 1","pages":"5197-5206"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90831863","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}
Deep Neural Networks (DNNs) have substantially improved the state-of-the-art in salient object detection. However, training DNNs requires costly pixel-level annotations. In this paper, we leverage the observation that image-level tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image-level tags only. The Foreground Inference Network (FIN) is introduced for this challenging task. In the first stage of our training method, FIN is jointly trained with a fully convolutional network (FCN) for image-level tag prediction. A global smooth pooling layer is proposed, enabling FCN to assign object category tags to corresponding object regions, while FIN is capable of capturing all potential foreground regions with the predicted saliency maps. In the second stage, FIN is fine-tuned with its predicted saliency maps as ground truth. For refinement of ground truth, an iterative Conditional Random Field is developed to enforce spatial label consistency and further boost performance. Our method alleviates annotation efforts and allows the usage of existing large scale training sets with image-level tags. Our model runs at 60 FPS, outperforms unsupervised ones with a large margin, and achieves comparable or even superior performance than fully supervised counterparts.
{"title":"Learning to Detect Salient Objects with Image-Level Supervision","authors":"Lijun Wang, Huchuan Lu, Yifan Wang, Mengyang Feng, D. Wang, Baocai Yin, Xiang Ruan","doi":"10.1109/CVPR.2017.404","DOIUrl":"https://doi.org/10.1109/CVPR.2017.404","url":null,"abstract":"Deep Neural Networks (DNNs) have substantially improved the state-of-the-art in salient object detection. However, training DNNs requires costly pixel-level annotations. In this paper, we leverage the observation that image-level tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image-level tags only. The Foreground Inference Network (FIN) is introduced for this challenging task. In the first stage of our training method, FIN is jointly trained with a fully convolutional network (FCN) for image-level tag prediction. A global smooth pooling layer is proposed, enabling FCN to assign object category tags to corresponding object regions, while FIN is capable of capturing all potential foreground regions with the predicted saliency maps. In the second stage, FIN is fine-tuned with its predicted saliency maps as ground truth. For refinement of ground truth, an iterative Conditional Random Field is developed to enforce spatial label consistency and further boost performance. Our method alleviates annotation efforts and allows the usage of existing large scale training sets with image-level tags. Our model runs at 60 FPS, outperforms unsupervised ones with a large margin, and achieves comparable or even superior performance than fully supervised counterparts.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"69 1","pages":"3796-3805"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90913385","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 the first snapshot hyperspectral light field imager in practice. Specifically, we design a novel hybrid camera system to obtain two complementary measurements that sample the angular and spectral dimensions respectively. To recover the full 5D hyperspectral light field from the severely undersampled measurements, we then propose an efficient computational reconstruction algorithm by exploiting the large correlations across the angular and spectral dimensions through self-learned dictionaries. Simulation on an elaborate hyperspectral light field dataset validates the effectiveness of the proposed approach. Hardware experimental results demonstrate that, for the first time to our knowledge, a 5D hyperspectral light field containing 9x9 angular views and 27 spectral bands can be acquired in a single shot.
{"title":"Snapshot Hyperspectral Light Field Imaging","authors":"Zhiwei Xiong, Lizhi Wang, Huiqun Li, Dong Liu, Feng Wu","doi":"10.1109/CVPR.2017.727","DOIUrl":"https://doi.org/10.1109/CVPR.2017.727","url":null,"abstract":"This paper presents the first snapshot hyperspectral light field imager in practice. Specifically, we design a novel hybrid camera system to obtain two complementary measurements that sample the angular and spectral dimensions respectively. To recover the full 5D hyperspectral light field from the severely undersampled measurements, we then propose an efficient computational reconstruction algorithm by exploiting the large correlations across the angular and spectral dimensions through self-learned dictionaries. Simulation on an elaborate hyperspectral light field dataset validates the effectiveness of the proposed approach. Hardware experimental results demonstrate that, for the first time to our knowledge, a 5D hyperspectral light field containing 9x9 angular views and 27 spectral bands can be acquired in a single shot.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"6873-6881"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74740411","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}
There is a significant interest in scene reconstruction from underwater images given its utility for oceanic research and for recreational image manipulation. In this paper we propose a novel algorithm for two view camera motion estimation for underwater imagery. Our method leverages the constraints provided by the attenuation properties of water and its effects on the appearance of the color to determine the depth difference of a point with respect to the two observing views of the underwater cameras. Additionally, we propose an algorithm, leveraging the depth differences of three such observed points, to estimate the relative pose of the cameras. Given the unknown underwater attenuation coefficients, our method estimates the relative motion up to scale. The results are represented as a generalized camera. We evaluate our method on both real data and simulated data.
{"title":"The Misty Three Point Algorithm for Relative Pose","authors":"Tobias Palmér, Kalle Åström, Jan-Michael Frahm","doi":"10.1109/CVPR.2017.484","DOIUrl":"https://doi.org/10.1109/CVPR.2017.484","url":null,"abstract":"There is a significant interest in scene reconstruction from underwater images given its utility for oceanic research and for recreational image manipulation. In this paper we propose a novel algorithm for two view camera motion estimation for underwater imagery. Our method leverages the constraints provided by the attenuation properties of water and its effects on the appearance of the color to determine the depth difference of a point with respect to the two observing views of the underwater cameras. Additionally, we propose an algorithm, leveraging the depth differences of three such observed points, to estimate the relative pose of the cameras. Given the unknown underwater attenuation coefficients, our method estimates the relative motion up to scale. The results are represented as a generalized camera. We evaluate our method on both real data and simulated data.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"26 1","pages":"4551-4559"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83166753","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 research focus of designing local patch descriptors has gradually shifted from handcrafted ones (e.g., SIFT) to learned ones. In this paper, we propose to learn high performance descriptor in Euclidean space via the Convolutional Neural Network (CNN). Our method is distinctive in four aspects: (i) We propose a progressive sampling strategy which enables the network to access billions of training samples in a few epochs. (ii) Derived from the basic concept of local patch matching problem, we empha-size the relative distance between descriptors. (iii) Extra supervision is imposed on the intermediate feature maps. (iv) Compactness of the descriptor is taken into account. The proposed network is named as L2-Net since the output descriptor can be matched in Euclidean space by L2 distance. L2-Net achieves state-of-the-art performance on the Brown datasets [16], Oxford dataset [18] and the newly proposed Hpatches dataset [11]. The good generalization ability shown by experiments indicates that L2-Net can serve as a direct substitution of the existing handcrafted descriptors. The pre-trained L2-Net is publicly available.
{"title":"L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space","authors":"Yurun Tian, Bin Fan, Fuchao Wu","doi":"10.1109/CVPR.2017.649","DOIUrl":"https://doi.org/10.1109/CVPR.2017.649","url":null,"abstract":"The research focus of designing local patch descriptors has gradually shifted from handcrafted ones (e.g., SIFT) to learned ones. In this paper, we propose to learn high performance descriptor in Euclidean space via the Convolutional Neural Network (CNN). Our method is distinctive in four aspects: (i) We propose a progressive sampling strategy which enables the network to access billions of training samples in a few epochs. (ii) Derived from the basic concept of local patch matching problem, we empha-size the relative distance between descriptors. (iii) Extra supervision is imposed on the intermediate feature maps. (iv) Compactness of the descriptor is taken into account. The proposed network is named as L2-Net since the output descriptor can be matched in Euclidean space by L2 distance. L2-Net achieves state-of-the-art performance on the Brown datasets [16], Oxford dataset [18] and the newly proposed Hpatches dataset [11]. The good generalization ability shown by experiments indicates that L2-Net can serve as a direct substitution of the existing handcrafted descriptors. The pre-trained L2-Net is publicly available.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"6128-6136"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83200304","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 address the problem of large scale image geo-localization where the location of an image is estimated by identifying geo-tagged reference images depicting the same place. We propose a novel model for learning image representations that integrates context-aware feature reweighting in order to effectively focus on regions that positively contribute to geo-localization. In particular, we introduce a Contextual Reweighting Network (CRN) that predicts the importance of each region in the feature map based on the image context. Our model is learned end-to-end for the image geo-localization task, and requires no annotation other than image geo-tags for training. In experimental results, the proposed approach significantly outperforms the previous state-of-the-art on the standard geo-localization benchmark datasets. We also demonstrate that our CRN discovers task-relevant contexts without any additional supervision.
{"title":"Learned Contextual Feature Reweighting for Image Geo-Localization","authors":"Hyo Jin Kim, Enrique Dunn, Jan-Michael Frahm","doi":"10.1109/CVPR.2017.346","DOIUrl":"https://doi.org/10.1109/CVPR.2017.346","url":null,"abstract":"We address the problem of large scale image geo-localization where the location of an image is estimated by identifying geo-tagged reference images depicting the same place. We propose a novel model for learning image representations that integrates context-aware feature reweighting in order to effectively focus on regions that positively contribute to geo-localization. In particular, we introduce a Contextual Reweighting Network (CRN) that predicts the importance of each region in the feature map based on the image context. Our model is learned end-to-end for the image geo-localization task, and requires no annotation other than image geo-tags for training. In experimental results, the proposed approach significantly outperforms the previous state-of-the-art on the standard geo-localization benchmark datasets. We also demonstrate that our CRN discovers task-relevant contexts without any additional supervision.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"64 2 1","pages":"3251-3260"},"PeriodicalIF":0.0,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83269225","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：