Haoxiang Li, Jonathan Brandt, Zhe L. Lin, Xiaohui Shen, G. Hua
In this work, we present a new framework for person recognition in photo albums that exploits contextual cues at multiple levels, spanning individual persons, individual photos, and photo groups. Through experiments, we show that the information available at each of these distinct contextual levels provides complementary cues as to person identities. At the person level, we leverage clothing and body appearance in addition to facial appearance, and to compensate for instances where the faces are not visible. At the photo level we leverage a learned prior on the joint distribution of identities on the same photo to guide the identity assignments. Going beyond a single photo, we are able to infer natural groupings of photos with shared context in an unsupervised manner. By exploiting this shared contextual information, we are able to reduce the identity search space and exploit higher intra-personal appearance consistency within photo groups. Our new framework enables efficient use of these complementary multi-level contextual cues to improve overall recognition rates on the photo album person recognition task, as demonstrated through state-of-theart results on a challenging public dataset. Our results outperform competing methods by a significant margin, while being computationally efficient and practical in a real world application.
{"title":"A Multi-level Contextual Model for Person Recognition in Photo Albums","authors":"Haoxiang Li, Jonathan Brandt, Zhe L. Lin, Xiaohui Shen, G. Hua","doi":"10.1109/CVPR.2016.145","DOIUrl":"https://doi.org/10.1109/CVPR.2016.145","url":null,"abstract":"In this work, we present a new framework for person recognition in photo albums that exploits contextual cues at multiple levels, spanning individual persons, individual photos, and photo groups. Through experiments, we show that the information available at each of these distinct contextual levels provides complementary cues as to person identities. At the person level, we leverage clothing and body appearance in addition to facial appearance, and to compensate for instances where the faces are not visible. At the photo level we leverage a learned prior on the joint distribution of identities on the same photo to guide the identity assignments. Going beyond a single photo, we are able to infer natural groupings of photos with shared context in an unsupervised manner. By exploiting this shared contextual information, we are able to reduce the identity search space and exploit higher intra-personal appearance consistency within photo groups. Our new framework enables efficient use of these complementary multi-level contextual cues to improve overall recognition rates on the photo album person recognition task, as demonstrated through state-of-theart results on a challenging public dataset. Our results outperform competing methods by a significant margin, while being computationally efficient and practical in a real world application.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"12 1","pages":"1297-1305"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91156869","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 DeepHand to estimate the 3D pose of a hand using depth data from commercial 3D sensors. We discriminatively train convolutional neural networks to output a low dimensional activation feature given a depth map. This activation feature vector is representative of the global or local joint angle parameters of a hand pose. We efficiently identify 'spatial' nearest neighbors to the activation feature, from a database of features corresponding to synthetic depth maps, and store some 'temporal' neighbors from previous frames. Our matrix completion algorithm uses these 'spatio-temporal' activation features and the corresponding known pose parameter values to estimate the unknown pose parameters of the input feature vector. Our database of activation features supplements large viewpoint coverage and our hierarchical estimation of pose parameters is robust to occlusions. We show that our approach compares favorably to state-of-the-art methods while achieving real time performance (≈ 32 FPS) on a standard computer.
{"title":"DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed with Deep Features","authors":"Ayan Sinha, Chiho Choi, K. Ramani","doi":"10.1109/CVPR.2016.450","DOIUrl":"https://doi.org/10.1109/CVPR.2016.450","url":null,"abstract":"We propose DeepHand to estimate the 3D pose of a hand using depth data from commercial 3D sensors. We discriminatively train convolutional neural networks to output a low dimensional activation feature given a depth map. This activation feature vector is representative of the global or local joint angle parameters of a hand pose. We efficiently identify 'spatial' nearest neighbors to the activation feature, from a database of features corresponding to synthetic depth maps, and store some 'temporal' neighbors from previous frames. Our matrix completion algorithm uses these 'spatio-temporal' activation features and the corresponding known pose parameter values to estimate the unknown pose parameters of the input feature vector. Our database of activation features supplements large viewpoint coverage and our hierarchical estimation of pose parameters is robust to occlusions. We show that our approach compares favorably to state-of-the-art methods while achieving real time performance (≈ 32 FPS) on a standard computer.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"30 1","pages":"4150-4158"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84267380","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}
Zheng Zhang, J. Girard, Yue Wu, Xing Zhang, Peng Liu, U. Ciftci, Shaun J. Canavan, M. Reale, Andy Horowitz, Huiyuan Yang, J. Cohn, Q. Ji, L. Yin
Emotion is expressed in multiple modalities, yet most research has considered at most one or two. This stems in part from the lack of large, diverse, well-annotated, multimodal databases with which to develop and test algorithms. We present a well-annotated, multimodal, multidimensional spontaneous emotion corpus of 140 participants. Emotion inductions were highly varied. Data were acquired from a variety of sensors of the face that included high-resolution 3D dynamic imaging, high-resolution 2D video, and thermal (infrared) sensing, and contact physiological sensors that included electrical conductivity of the skin, respiration, blood pressure, and heart rate. Facial expression was annotated for both the occurrence and intensity of facial action units from 2D video by experts in the Facial Action Coding System (FACS). The corpus further includes derived features from 3D, 2D, and IR (infrared) sensors and baseline results for facial expression and action unit detection. The entire corpus will be made available to the research community.
{"title":"Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis","authors":"Zheng Zhang, J. Girard, Yue Wu, Xing Zhang, Peng Liu, U. Ciftci, Shaun J. Canavan, M. Reale, Andy Horowitz, Huiyuan Yang, J. Cohn, Q. Ji, L. Yin","doi":"10.1109/CVPR.2016.374","DOIUrl":"https://doi.org/10.1109/CVPR.2016.374","url":null,"abstract":"Emotion is expressed in multiple modalities, yet most research has considered at most one or two. This stems in part from the lack of large, diverse, well-annotated, multimodal databases with which to develop and test algorithms. We present a well-annotated, multimodal, multidimensional spontaneous emotion corpus of 140 participants. Emotion inductions were highly varied. Data were acquired from a variety of sensors of the face that included high-resolution 3D dynamic imaging, high-resolution 2D video, and thermal (infrared) sensing, and contact physiological sensors that included electrical conductivity of the skin, respiration, blood pressure, and heart rate. Facial expression was annotated for both the occurrence and intensity of facial action units from 2D video by experts in the Facial Action Coding System (FACS). The corpus further includes derived features from 3D, 2D, and IR (infrared) sensors and baseline results for facial expression and action unit detection. The entire corpus will be made available to the research community.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"8 1","pages":"3438-3446"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79878887","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 consider the problem of camera pose estimation for a scenario where the camera may have continuous and unknown changes in its focal length. Understanding frame by frame changes in camera focal length is vital to accurately estimating camera pose and vital to accurately rendering virtual objects in a scene with the correct perspective. However, most approaches to camera calibration require geometric constraints from many frames or the observation of a 3D calibration object - both of which may not be feasible in augmented reality settings. This paper introduces a calibration object based on a flat lenticular array that creates a color coded light-field whose observed color changes depending on the angle from which it is viewed. We derive an approach to estimate the focal length of the camera and the relative pose of an object from a single image. We characterize the performance of camera calibration across various focal lengths and camera models, and we demonstrate the advantages of the focal length estimation in rendering a virtual object in a video with constant zooming.
{"title":"Single Image Camera Calibration with Lenticular Arrays for Augmented Reality","authors":"Ian Schillebeeckx, Robert Pless","doi":"10.1109/CVPR.2016.358","DOIUrl":"https://doi.org/10.1109/CVPR.2016.358","url":null,"abstract":"We consider the problem of camera pose estimation for a scenario where the camera may have continuous and unknown changes in its focal length. Understanding frame by frame changes in camera focal length is vital to accurately estimating camera pose and vital to accurately rendering virtual objects in a scene with the correct perspective. However, most approaches to camera calibration require geometric constraints from many frames or the observation of a 3D calibration object - both of which may not be feasible in augmented reality settings. This paper introduces a calibration object based on a flat lenticular array that creates a color coded light-field whose observed color changes depending on the angle from which it is viewed. We derive an approach to estimate the focal length of the camera and the relative pose of an object from a single image. We characterize the performance of camera calibration across various focal lengths and camera models, and we demonstrate the advantages of the focal length estimation in rendering a virtual object in a video with constant zooming.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"25 1","pages":"3290-3298"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87094779","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}
George Trigeorgis, Patrick Snape, M. Nicolaou, Epameinondas Antonakos, S. Zafeiriou
Cascaded regression has recently become the method of choice for solving non-linear least squares problems such as deformable image alignment. Given a sizeable training set, cascaded regression learns a set of generic rules that are sequentially applied to minimise the least squares problem. Despite the success of cascaded regression for problems such as face alignment and head pose estimation, there are several shortcomings arising in the strategies proposed thus far. Specifically, (a) the regressors are learnt independently, (b) the descent directions may cancel one another out and (c) handcrafted features (e.g., HoGs, SIFT etc.) are mainly used to drive the cascade, which may be sub-optimal for the task at hand. In this paper, we propose a combined and jointly trained convolutional recurrent neural network architecture that allows the training of an end-to-end to system that attempts to alleviate the aforementioned drawbacks. The recurrent module facilitates the joint optimisation of the regressors by assuming the cascades form a nonlinear dynamical system, in effect fully utilising the information between all cascade levels by introducing a memory unit that shares information across all levels. The convolutional module allows the network to extract features that are specialised for the task at hand and are experimentally shown to outperform hand-crafted features. We show that the application of the proposed architecture for the problem of face alignment results in a strong improvement over the current state-of-the-art.
{"title":"Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment","authors":"George Trigeorgis, Patrick Snape, M. Nicolaou, Epameinondas Antonakos, S. Zafeiriou","doi":"10.1109/CVPR.2016.453","DOIUrl":"https://doi.org/10.1109/CVPR.2016.453","url":null,"abstract":"Cascaded regression has recently become the method of choice for solving non-linear least squares problems such as deformable image alignment. Given a sizeable training set, cascaded regression learns a set of generic rules that are sequentially applied to minimise the least squares problem. Despite the success of cascaded regression for problems such as face alignment and head pose estimation, there are several shortcomings arising in the strategies proposed thus far. Specifically, (a) the regressors are learnt independently, (b) the descent directions may cancel one another out and (c) handcrafted features (e.g., HoGs, SIFT etc.) are mainly used to drive the cascade, which may be sub-optimal for the task at hand. In this paper, we propose a combined and jointly trained convolutional recurrent neural network architecture that allows the training of an end-to-end to system that attempts to alleviate the aforementioned drawbacks. The recurrent module facilitates the joint optimisation of the regressors by assuming the cascades form a nonlinear dynamical system, in effect fully utilising the information between all cascade levels by introducing a memory unit that shares information across all levels. The convolutional module allows the network to extract features that are specialised for the task at hand and are experimentally shown to outperform hand-crafted features. We show that the application of the proposed architecture for the problem of face alignment results in a strong improvement over the current state-of-the-art.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"47 1","pages":"4177-4187"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87349045","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}
While domain adaptation (DA) aims to associate the learning tasks across data domains, heterogeneous domain adaptation (HDA) particularly deals with learning from cross-domain data which are of different types of features. In other words, for HDA, data from source and target domains are observed in separate feature spaces and thus exhibit distinct distributions. In this paper, we propose a novel learning algorithm of Cross-Domain Landmark Selection (CDLS) for solving the above task. With the goal of deriving a domain-invariant feature subspace for HDA, our CDLS is able to identify representative cross-domain data, including the unlabeled ones in the target domain, for performing adaptation. In addition, the adaptation capabilities of such cross-domain landmarks can be determined accordingly. This is the reason why our CDLS is able to achieve promising HDA performance when comparing to state-of-the-art HDA methods. We conduct classification experiments using data across different features, domains, and modalities. The effectiveness of our proposed method can be successfully verified.
{"title":"Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation","authors":"Yao-Hung Hubert Tsai, Yi-Ren Yeh, Y. Wang","doi":"10.1109/CVPR.2016.549","DOIUrl":"https://doi.org/10.1109/CVPR.2016.549","url":null,"abstract":"While domain adaptation (DA) aims to associate the learning tasks across data domains, heterogeneous domain adaptation (HDA) particularly deals with learning from cross-domain data which are of different types of features. In other words, for HDA, data from source and target domains are observed in separate feature spaces and thus exhibit distinct distributions. In this paper, we propose a novel learning algorithm of Cross-Domain Landmark Selection (CDLS) for solving the above task. With the goal of deriving a domain-invariant feature subspace for HDA, our CDLS is able to identify representative cross-domain data, including the unlabeled ones in the target domain, for performing adaptation. In addition, the adaptation capabilities of such cross-domain landmarks can be determined accordingly. This is the reason why our CDLS is able to achieve promising HDA performance when comparing to state-of-the-art HDA methods. We conduct classification experiments using data across different features, domains, and modalities. The effectiveness of our proposed method can be successfully verified.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"93 1","pages":"5081-5090"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85697281","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}
Seoung Wug Oh, M. S. Brown, M. Pollefeys, Seon Joo Kim
Capturing hyperspectral images requires expensive and specialized hardware that is not readily accessible to most users. Digital cameras, on the other hand, are significantly cheaper in comparison and can be easily purchased and used. In this paper, we present a framework for reconstructing hyperspectral images by using multiple consumer-level digital cameras. Our approach works by exploiting the different spectral sensitivities of different camera sensors. In particular, due to the differences in spectral sensitivities of the cameras, different cameras yield different RGB measurements for the same spectral signal. We introduce an algorithm that is able to combine and convert these different RGB measurements into a single hyperspectral image for both indoor and outdoor scenes. This camera-based approach allows hyperspectral imaging at a fraction of the cost of most existing hyperspectral hardware. We validate the accuracy of our reconstruction against ground truth hyperspectral images (using both synthetic and real cases) and show its usage on relighting applications.
{"title":"Do It Yourself Hyperspectral Imaging with Everyday Digital Cameras","authors":"Seoung Wug Oh, M. S. Brown, M. Pollefeys, Seon Joo Kim","doi":"10.1109/CVPR.2016.270","DOIUrl":"https://doi.org/10.1109/CVPR.2016.270","url":null,"abstract":"Capturing hyperspectral images requires expensive and specialized hardware that is not readily accessible to most users. Digital cameras, on the other hand, are significantly cheaper in comparison and can be easily purchased and used. In this paper, we present a framework for reconstructing hyperspectral images by using multiple consumer-level digital cameras. Our approach works by exploiting the different spectral sensitivities of different camera sensors. In particular, due to the differences in spectral sensitivities of the cameras, different cameras yield different RGB measurements for the same spectral signal. We introduce an algorithm that is able to combine and convert these different RGB measurements into a single hyperspectral image for both indoor and outdoor scenes. This camera-based approach allows hyperspectral imaging at a fraction of the cost of most existing hyperspectral hardware. We validate the accuracy of our reconstruction against ground truth hyperspectral images (using both synthetic and real cases) and show its usage on relighting applications.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"96 3 1","pages":"2461-2469"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83358815","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}
Dynamic relocalization of 6D camera pose from single reference image is a costly and challenging task that requires delicate hand-eye calibration and precision positioning platform to do 3D mechanical rotation and translation. In this paper, we show that high-quality camera relocalization can be achieved in a much less expensive way. Based on inexpensive platform with unreliable absolute repositioning accuracy (ARA), we propose a hand-eye calibration free strategy to actively relocate camera into the same 6D pose that produces the input reference image, by sequentially correcting 3D relative rotation and translation. We theoretically prove that, by this strategy, both rotational and translational relative pose can be effectively reduced to zero, with bounded unknown hand-eye pose displacement. To conquer 3D rotation and translation ambiguity, this theoretical strategy is further revised to a practical relocalization algorithm with faster convergence rate and more reliability by jointly adjusting 3D relative rotation and translation. Extensive experiments validate the effectiveness and superior accuracy of the proposed approach on laboratory tests and challenging real-world applications.
{"title":"6D Dynamic Camera Relocalization from Single Reference Image","authors":"Wei Feng, Fei-Peng Tian, Qian Zhang, Ji-zhou Sun","doi":"10.1109/CVPR.2016.439","DOIUrl":"https://doi.org/10.1109/CVPR.2016.439","url":null,"abstract":"Dynamic relocalization of 6D camera pose from single reference image is a costly and challenging task that requires delicate hand-eye calibration and precision positioning platform to do 3D mechanical rotation and translation. In this paper, we show that high-quality camera relocalization can be achieved in a much less expensive way. Based on inexpensive platform with unreliable absolute repositioning accuracy (ARA), we propose a hand-eye calibration free strategy to actively relocate camera into the same 6D pose that produces the input reference image, by sequentially correcting 3D relative rotation and translation. We theoretically prove that, by this strategy, both rotational and translational relative pose can be effectively reduced to zero, with bounded unknown hand-eye pose displacement. To conquer 3D rotation and translation ambiguity, this theoretical strategy is further revised to a practical relocalization algorithm with faster convergence rate and more reliability by jointly adjusting 3D relative rotation and translation. Extensive experiments validate the effectiveness and superior accuracy of the proposed approach on laboratory tests and challenging real-world applications.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"32 1","pages":"4049-4057"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89429716","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}
Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be feasible for some application domains. Transfer learning can be one of the approaches to alleviate this problem by transferring data from data-rich source domain to data-scarce target domain. Existing transfer learning methods typically perform one-shot transfer learning and often ignore the specific properties that the transferred data must satisfy. To address these issues, we introduce a constrained deep transfer feature learning method to perform simultaneous transfer learning and feature learning by performing transfer learning in a progressively improving feature space iteratively in order to better narrow the gap between the target domain and the source domain for effective transfer of the data from source domain to target domain. Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain. To demonstrate the effectiveness of the proposed constrained deep transfer feature learning method, we apply it to thermal feature learning for eye detection by transferring from the visible domain. We also applied the proposed method for cross-view facial expression recognition as a second application. The experimental results demonstrate the effectiveness of the proposed method for both applications.
{"title":"Constrained Deep Transfer Feature Learning and Its Applications","authors":"Yue Wu, Q. Ji","doi":"10.1109/CVPR.2016.551","DOIUrl":"https://doi.org/10.1109/CVPR.2016.551","url":null,"abstract":"Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be feasible for some application domains. Transfer learning can be one of the approaches to alleviate this problem by transferring data from data-rich source domain to data-scarce target domain. Existing transfer learning methods typically perform one-shot transfer learning and often ignore the specific properties that the transferred data must satisfy. To address these issues, we introduce a constrained deep transfer feature learning method to perform simultaneous transfer learning and feature learning by performing transfer learning in a progressively improving feature space iteratively in order to better narrow the gap between the target domain and the source domain for effective transfer of the data from source domain to target domain. Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain. To demonstrate the effectiveness of the proposed constrained deep transfer feature learning method, we apply it to thermal feature learning for eye detection by transferring from the visible domain. We also applied the proposed method for cross-view facial expression recognition as a second application. The experimental results demonstrate the effectiveness of the proposed method for both applications.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"5101-5109"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89681627","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}
Traditional Feature Detectors and Trackers use information aggregation in 2D patches to detect and match discriminative patches. However, this information does not remain the same at object boundaries when there is object motion against a significantly varying background. In this paper, we propose a new approach for feature detection, tracking and re-detection that gives significantly improved results at the object boundaries. We utilize level lines or iso-intensity curves that often remain stable and can be reliably detected even at the object boundaries, which they often trace. Stable portions of long level lines are detected and points of high curvature are detected on such curves for corner detection. Further, this level line is used to separate the portions belonging to the two objects, which is then used for robust matching of such points. While such CoMaL (Corners on Maximally-stable Level Line Segments) points were found to be much more reliable at the object boundary regions, they perform comparably at the interior regions as well. This is illustrated in exhaustive experiments on realworld datasets.
{"title":"CoMaL: Good Features to Match on Object Boundaries","authors":"Swarna Kamlam Ravindran, Anurag Mittal","doi":"10.1109/CVPR.2016.43","DOIUrl":"https://doi.org/10.1109/CVPR.2016.43","url":null,"abstract":"Traditional Feature Detectors and Trackers use information aggregation in 2D patches to detect and match discriminative patches. However, this information does not remain the same at object boundaries when there is object motion against a significantly varying background. In this paper, we propose a new approach for feature detection, tracking and re-detection that gives significantly improved results at the object boundaries. We utilize level lines or iso-intensity curves that often remain stable and can be reliably detected even at the object boundaries, which they often trace. Stable portions of long level lines are detected and points of high curvature are detected on such curves for corner detection. Further, this level line is used to separate the portions belonging to the two objects, which is then used for robust matching of such points. While such CoMaL (Corners on Maximally-stable Level Line Segments) points were found to be much more reliable at the object boundary regions, they perform comparably at the interior regions as well. This is illustrated in exhaustive experiments on realworld datasets.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"108 1","pages":"336-345"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79377702","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：