The conventional sparse model relies on data representation in the form of vectors. It represents the vector-valued or vectorized one dimensional (1D) version of an signal as a highly sparse linear combination of basis atoms from a large dictionary. The 1D modeling, though simple, ignores the inherent structure and breaks the local correlation inside multidimensional (MD) signals. It also dramatically increases the demand of memory as well as computational resources especially when dealing with high dimensional signals. In this paper, we propose a new sparse model TenSR based on tensor for MD data representation along with the corresponding MD sparse coding and MD dictionary learning algorithms. The proposed TenSR model is able to well approximate the structure in each mode inherent in MD signals with a series of adaptive separable structure dictionaries via dictionary learning. The proposed MD sparse coding algorithm by proximal method further reduces the computational cost significantly. Experimental results with real world MD signals, i.e. 3D Multi-spectral images, show the proposed TenSR greatly reduces both the computational and memory costs with competitive performance in comparison with the state-of-the-art sparse representation methods. We believe our proposed TenSR model is a promising way to empower the sparse representation especially for large scale high order signals.
{"title":"TenSR: Multi-dimensional Tensor Sparse Representation","authors":"Na Qi, Yunhui Shi, Xiaoyan Sun, Baocai Yin","doi":"10.1109/CVPR.2016.637","DOIUrl":"https://doi.org/10.1109/CVPR.2016.637","url":null,"abstract":"The conventional sparse model relies on data representation in the form of vectors. It represents the vector-valued or vectorized one dimensional (1D) version of an signal as a highly sparse linear combination of basis atoms from a large dictionary. The 1D modeling, though simple, ignores the inherent structure and breaks the local correlation inside multidimensional (MD) signals. It also dramatically increases the demand of memory as well as computational resources especially when dealing with high dimensional signals. In this paper, we propose a new sparse model TenSR based on tensor for MD data representation along with the corresponding MD sparse coding and MD dictionary learning algorithms. The proposed TenSR model is able to well approximate the structure in each mode inherent in MD signals with a series of adaptive separable structure dictionaries via dictionary learning. The proposed MD sparse coding algorithm by proximal method further reduces the computational cost significantly. Experimental results with real world MD signals, i.e. 3D Multi-spectral images, show the proposed TenSR greatly reduces both the computational and memory costs with competitive performance in comparison with the state-of-the-art sparse representation methods. We believe our proposed TenSR model is a promising way to empower the sparse representation especially for large scale high order signals.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"17 1","pages":"5916-5925"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80197391","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 current approaches to action recognition on presegmented video clips already achieve high accuracies, temporal action detection is still far from comparably good results. Automatically locating and classifying the relevant action segments in videos of varying lengths proves to be a challenging task. We propose a novel method for temporal action detection including statistical length and language modeling to represent temporal and contextual structure. Our approach aims at globally optimizing the joint probability of three components, a length and language model and a discriminative action model, without making intermediate decisions. The problem of finding the most likely action sequence and the corresponding segment boundaries in an exponentially large search space is addressed by dynamic programming. We provide an extensive evaluation of each model component on Thumos 14, a large action detection dataset, and report state-of-the-art results on three datasets.
{"title":"Temporal Action Detection Using a Statistical Language Model","authors":"Alexander Richard, Juergen Gall","doi":"10.1109/CVPR.2016.341","DOIUrl":"https://doi.org/10.1109/CVPR.2016.341","url":null,"abstract":"While current approaches to action recognition on presegmented video clips already achieve high accuracies, temporal action detection is still far from comparably good results. Automatically locating and classifying the relevant action segments in videos of varying lengths proves to be a challenging task. We propose a novel method for temporal action detection including statistical length and language modeling to represent temporal and contextual structure. Our approach aims at globally optimizing the joint probability of three components, a length and language model and a discriminative action model, without making intermediate decisions. The problem of finding the most likely action sequence and the corresponding segment boundaries in an exponentially large search space is addressed by dynamic programming. We provide an extensive evaluation of each model component on Thumos 14, a large action detection dataset, and report state-of-the-art results on three datasets.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"3131-3140"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84331490","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}
J. Ning, Jimei Yang, Shaojie Jiang, Lei Zhang, Ming-Hsuan Yang
Structured support vector machine (SSVM) based methods have demonstrated encouraging performance in recent object tracking benchmarks. However, the complex and expensive optimization limits their deployment in real-world applications. In this paper, we present a simple yet efficient dual linear SSVM (DLSSVM) algorithm to enable fast learning and execution during tracking. By analyzing the dual variables, we propose a primal classifier update formula where the learning step size is computed in closed form. This online learning method significantly improves the robustness of the proposed linear SSVM with lower computational cost. Second, we approximate the intersection kernel for feature representations with an explicit feature map to further improve tracking performance. Finally, we extend the proposed DLSSVM tracker with multi-scale estimation to address the "drift" problem. Experimental results on large benchmark datasets with 50 and 100 video sequences show that the proposed DLSSVM tracking algorithm achieves state-of-the-art performance.
{"title":"Object Tracking via Dual Linear Structured SVM and Explicit Feature Map","authors":"J. Ning, Jimei Yang, Shaojie Jiang, Lei Zhang, Ming-Hsuan Yang","doi":"10.1109/CVPR.2016.462","DOIUrl":"https://doi.org/10.1109/CVPR.2016.462","url":null,"abstract":"Structured support vector machine (SSVM) based methods have demonstrated encouraging performance in recent object tracking benchmarks. However, the complex and expensive optimization limits their deployment in real-world applications. In this paper, we present a simple yet efficient dual linear SSVM (DLSSVM) algorithm to enable fast learning and execution during tracking. By analyzing the dual variables, we propose a primal classifier update formula where the learning step size is computed in closed form. This online learning method significantly improves the robustness of the proposed linear SSVM with lower computational cost. Second, we approximate the intersection kernel for feature representations with an explicit feature map to further improve tracking performance. Finally, we extend the proposed DLSSVM tracker with multi-scale estimation to address the \"drift\" problem. Experimental results on large benchmark datasets with 50 and 100 video sequences show that the proposed DLSSVM tracking algorithm achieves state-of-the-art performance.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"21 1","pages":"4266-4274"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85006706","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}
Recently, skeleton-based human action recognition has been receiving significant attention from various research communities due to the availability of depth sensors and real-time depth-based 3D skeleton estimation algorithms. In this work, we use rolling maps for recognizing human actions from 3D skeletal data. The rolling map is a well-defined mathematical concept that has not been explored much by the vision community. First, we represent each skeleton using the relative 3D rotations between various body parts. Since 3D rotations are members of the special orthogonal group SO3, our skeletal representation becomes a point in the Lie group SO3 × ... × SO3, which is also a Riemannian manifold. Then, using this representation, we model human actions as curves in this Lie group. Since classification of curves in this non-Euclidean space is a difficult task, we unwrap the action curves onto the Lie algebra so3 × ... × so3 (which is a vector space) by combining the logarithm map with rolling maps, and perform classification in the Lie algebra. Experimental results on three action datasets show that the proposed approach performs equally well or better when compared to state-of-the-art.
{"title":"Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data","authors":"Raviteja Vemulapalli, R. Chellappa","doi":"10.1109/CVPR.2016.484","DOIUrl":"https://doi.org/10.1109/CVPR.2016.484","url":null,"abstract":"Recently, skeleton-based human action recognition has been receiving significant attention from various research communities due to the availability of depth sensors and real-time depth-based 3D skeleton estimation algorithms. In this work, we use rolling maps for recognizing human actions from 3D skeletal data. The rolling map is a well-defined mathematical concept that has not been explored much by the vision community. First, we represent each skeleton using the relative 3D rotations between various body parts. Since 3D rotations are members of the special orthogonal group SO3, our skeletal representation becomes a point in the Lie group SO3 × ... × SO3, which is also a Riemannian manifold. Then, using this representation, we model human actions as curves in this Lie group. Since classification of curves in this non-Euclidean space is a difficult task, we unwrap the action curves onto the Lie algebra so3 × ... × so3 (which is a vector space) by combining the logarithm map with rolling maps, and perform classification in the Lie algebra. Experimental results on three action datasets show that the proposed approach performs equally well or better when compared to state-of-the-art.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"19 1","pages":"4471-4479"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78080726","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}
It is a challenging problem to accurately estimate gazes from low-resolution eye images that do not provide fine and detailed features for eyes. Existing methods attempt to establish the mapping between the visual appearance space to the gaze space. Different from the direct regression approach, the reconstruction-based approach represents appearance and gaze via local linear reconstruction in their own spaces. A common treatment is to use the same local reconstruction in the two spaces, i.e., the reconstruction weights in the appearance space are transferred to the gaze space for gaze reconstruction. However, this questionable treatment is taken for granted but has never been justified, leading to significant errors in gaze estimation. This paper is focused on the study of this fundamental issue. It shows that the distance metric in the appearance space needs to be adjusted, before the same reconstruction can be used. A novel method is proposed to learn the metric, such that the affinity structure of the appearance space under this new metric is as close as possible to the affinity structure of the gaze space under the normal Euclidean metric. Furthermore, the local affinity structure invariance is utilized to further regularize the solution to the reconstruction weights, so as to obtain a more robust and accurate solution. Effectiveness of the proposed method is validated and demonstrated through extensive experiments on different subjects.
{"title":"Learning Reconstruction-Based Remote Gaze Estimation","authors":"Pei Yu, Jiahuan Zhou, Ying Wu","doi":"10.1109/CVPR.2016.375","DOIUrl":"https://doi.org/10.1109/CVPR.2016.375","url":null,"abstract":"It is a challenging problem to accurately estimate gazes from low-resolution eye images that do not provide fine and detailed features for eyes. Existing methods attempt to establish the mapping between the visual appearance space to the gaze space. Different from the direct regression approach, the reconstruction-based approach represents appearance and gaze via local linear reconstruction in their own spaces. A common treatment is to use the same local reconstruction in the two spaces, i.e., the reconstruction weights in the appearance space are transferred to the gaze space for gaze reconstruction. However, this questionable treatment is taken for granted but has never been justified, leading to significant errors in gaze estimation. This paper is focused on the study of this fundamental issue. It shows that the distance metric in the appearance space needs to be adjusted, before the same reconstruction can be used. A novel method is proposed to learn the metric, such that the affinity structure of the appearance space under this new metric is as close as possible to the affinity structure of the gaze space under the normal Euclidean metric. Furthermore, the local affinity structure invariance is utilized to further regularize the solution to the reconstruction weights, so as to obtain a more robust and accurate solution. Effectiveness of the proposed method is validated and demonstrated through extensive experiments on different subjects.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"89 1","pages":"3447-3455"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72865592","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}
Multilinear models are widely used to represent the statistical variations of 3D human faces as they decouple shape changes due to identity and expression. Existing methods to learn a multilinear face model degrade if not every person is captured in every expression, if face scans are noisy or partially occluded, if expressions are erroneously labeled, or if the vertex correspondence is inaccurate. These limitations impose requirements on the training data that disqualify large amounts of available 3D face data from being usable to learn a multilinear model. To overcome this, we introduce the first framework to robustly learn a multilinear model from 3D face databases with missing data, corrupt data, wrong semantic correspondence, and inaccurate vertex correspondence. To achieve this robustness to erroneous training data, our framework jointly learns a multilinear model and fixes the data. We evaluate our framework on two publicly available 3D face databases, and show that our framework achieves a data completion accuracy that is comparable to state-of-the-art tensor completion methods. Our method reconstructs corrupt data more accurately than state-of-the-art methods, and improves the quality of the learned model significantly for erroneously labeled expressions.
{"title":"A Robust Multilinear Model Learning Framework for 3D Faces","authors":"Timo Bolkart, S. Wuhrer","doi":"10.1109/CVPR.2016.531","DOIUrl":"https://doi.org/10.1109/CVPR.2016.531","url":null,"abstract":"Multilinear models are widely used to represent the statistical variations of 3D human faces as they decouple shape changes due to identity and expression. Existing methods to learn a multilinear face model degrade if not every person is captured in every expression, if face scans are noisy or partially occluded, if expressions are erroneously labeled, or if the vertex correspondence is inaccurate. These limitations impose requirements on the training data that disqualify large amounts of available 3D face data from being usable to learn a multilinear model. To overcome this, we introduce the first framework to robustly learn a multilinear model from 3D face databases with missing data, corrupt data, wrong semantic correspondence, and inaccurate vertex correspondence. To achieve this robustness to erroneous training data, our framework jointly learns a multilinear model and fixes the data. We evaluate our framework on two publicly available 3D face databases, and show that our framework achieves a data completion accuracy that is comparable to state-of-the-art tensor completion methods. Our method reconstructs corrupt data more accurately than state-of-the-art methods, and improves the quality of the learned model significantly for erroneously labeled expressions.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"29 1","pages":"4911-4919"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73127906","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 explicitly discriminative and 'simple' approach to generate invariance to nuisance transformations modeled as unitary. In practice, the approach works well to handle non-unitary transformations as well. Our theoretical results extend the reach of a recent theory of invariance to discriminative and kernelized features based on unitary kernels. As a special case, a single common framework can be used to generate subject-specific pose-invariant features for face recognition and vice-versa for pose estimation. We show that our main proposed method (DIKF) can perform well under very challenging large-scale semisynthetic face matching and pose estimation protocols with unaligned faces using no landmarking whatsoever. We additionally benchmark on CMU MPIE and outperform previous work in almost all cases on off-angle face matching while we are on par with the previous state-of-the-art on the LFW unsupervised and image-restricted protocols, without any low-level image descriptors other than raw-pixels.
{"title":"Discriminative Invariant Kernel Features: A Bells-and-Whistles-Free Approach to Unsupervised Face Recognition and Pose Estimation","authors":"Dipan K. Pal, Felix Juefei-Xu, M. Savvides","doi":"10.1109/CVPR.2016.603","DOIUrl":"https://doi.org/10.1109/CVPR.2016.603","url":null,"abstract":"We propose an explicitly discriminative and 'simple' approach to generate invariance to nuisance transformations modeled as unitary. In practice, the approach works well to handle non-unitary transformations as well. Our theoretical results extend the reach of a recent theory of invariance to discriminative and kernelized features based on unitary kernels. As a special case, a single common framework can be used to generate subject-specific pose-invariant features for face recognition and vice-versa for pose estimation. We show that our main proposed method (DIKF) can perform well under very challenging large-scale semisynthetic face matching and pose estimation protocols with unaligned faces using no landmarking whatsoever. We additionally benchmark on CMU MPIE and outperform previous work in almost all cases on off-angle face matching while we are on par with the previous state-of-the-art on the LFW unsupervised and image-restricted protocols, without any low-level image descriptors other than raw-pixels.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"545 1","pages":"5590-5599"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76621960","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}
In this paper we propose a novel recurrent neural network architecture for video-based person re-identification. Given the video sequence of a person, features are extracted from each frame using a convolutional neural network that incorporates a recurrent final layer, which allows information to flow between time-steps. The features from all timesteps are then combined using temporal pooling to give an overall appearance feature for the complete sequence. The convolutional network, recurrent layer, and temporal pooling layer, are jointly trained to act as a feature extractor for video-based re-identification using a Siamese network architecture. Our approach makes use of colour and optical flow information in order to capture appearance and motion information which is useful for video re-identification. Experiments are conduced on the iLIDS-VID and PRID-2011 datasets to show that this approach outperforms existing methods of video-based re-identification.
{"title":"Recurrent Convolutional Network for Video-Based Person Re-identification","authors":"Niall McLaughlin, J. M. D. Rincón, P. Miller","doi":"10.1109/CVPR.2016.148","DOIUrl":"https://doi.org/10.1109/CVPR.2016.148","url":null,"abstract":"In this paper we propose a novel recurrent neural network architecture for video-based person re-identification. Given the video sequence of a person, features are extracted from each frame using a convolutional neural network that incorporates a recurrent final layer, which allows information to flow between time-steps. The features from all timesteps are then combined using temporal pooling to give an overall appearance feature for the complete sequence. The convolutional network, recurrent layer, and temporal pooling layer, are jointly trained to act as a feature extractor for video-based re-identification using a Siamese network architecture. Our approach makes use of colour and optical flow information in order to capture appearance and motion information which is useful for video re-identification. Experiments are conduced on the iLIDS-VID and PRID-2011 datasets to show that this approach outperforms existing methods of video-based re-identification.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"-1 1","pages":"1325-1334"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81329621","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 rule of perspectivity that 'straight-lines-mustremain-straight' is easily inflected in CMOS cameras by distortions introduced by motion. Lines can be rendered as curves due to the row-wise exposure mechanism known as rolling shutter (RS). We solve the problem of correcting distortions arising from handheld cameras due to RS effect from a single image free from motion blur with special relevance to urban scenes. We develop a procedure to extract prominent curves from the RS image since this is essential for deciphering the varying row-wise motion. We pose an optimization problem with line desirability costs based on straightness, angle, and length, to resolve the geometric ambiguities while estimating the camera motion based on a rotation-only model assuming known camera intrinsic matrix. Finally, we rectify the RS image based on the estimated camera trajectory using inverse mapping. We show rectification results for RS images captured using mobile phone cameras. We also compare our single image method against existing video and nonblind RS rectification methods that typically require multiple images.
{"title":"From Bows to Arrows: Rolling Shutter Rectification of Urban Scenes","authors":"Vijay Rengarajan, A. Rajagopalan, R. Aravind","doi":"10.1109/CVPR.2016.303","DOIUrl":"https://doi.org/10.1109/CVPR.2016.303","url":null,"abstract":"The rule of perspectivity that 'straight-lines-mustremain-straight' is easily inflected in CMOS cameras by distortions introduced by motion. Lines can be rendered as curves due to the row-wise exposure mechanism known as rolling shutter (RS). We solve the problem of correcting distortions arising from handheld cameras due to RS effect from a single image free from motion blur with special relevance to urban scenes. We develop a procedure to extract prominent curves from the RS image since this is essential for deciphering the varying row-wise motion. We pose an optimization problem with line desirability costs based on straightness, angle, and length, to resolve the geometric ambiguities while estimating the camera motion based on a rotation-only model assuming known camera intrinsic matrix. Finally, we rectify the RS image based on the estimated camera trajectory using inverse mapping. We show rectification results for RS images captured using mobile phone cameras. We also compare our single image method against existing video and nonblind RS rectification methods that typically require multiple images.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"74 1","pages":"2773-2781"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76169177","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}
Xikang Zhang, Yin Wang, Mengran Gou, M. Sznaier, O. Camps
In this paper we propose a new framework to compare and classify temporal sequences. The proposed approach captures the underlying dynamics of the data while avoiding expensive estimation procedures, making it suitable to process large numbers of sequences. The main idea is to first embed the sequences into a Riemannian manifold by using positive definite regularized Gram matrices of their Hankelets. The advantages of the this approach are: 1) it allows for using non-Euclidean similarity functions on the Positive Definite matrix manifold, which capture better the underlying geometry than directly comparing the sequences or their Hankel matrices, and 2) Gram matrices inherit desirable properties from the underlying Hankel matrices: their rank measure the complexity of the underlying dynamics, and the order and coefficients of the associated regressive models are invariant to affine transformations and varying initial conditions. The benefits of this approach are illustrated with extensive experiments in 3D action recognition using 3D joints sequences. In spite of its simplicity, the performance of this approach is competitive or better than using state-of-art approaches for this problem. Further, these results hold across a variety of metrics, supporting the idea that the improvement stems from the embedding itself, rather than from using one of these metrics.
{"title":"Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold","authors":"Xikang Zhang, Yin Wang, Mengran Gou, M. Sznaier, O. Camps","doi":"10.1109/CVPR.2016.487","DOIUrl":"https://doi.org/10.1109/CVPR.2016.487","url":null,"abstract":"In this paper we propose a new framework to compare and classify temporal sequences. The proposed approach captures the underlying dynamics of the data while avoiding expensive estimation procedures, making it suitable to process large numbers of sequences. The main idea is to first embed the sequences into a Riemannian manifold by using positive definite regularized Gram matrices of their Hankelets. The advantages of the this approach are: 1) it allows for using non-Euclidean similarity functions on the Positive Definite matrix manifold, which capture better the underlying geometry than directly comparing the sequences or their Hankel matrices, and 2) Gram matrices inherit desirable properties from the underlying Hankel matrices: their rank measure the complexity of the underlying dynamics, and the order and coefficients of the associated regressive models are invariant to affine transformations and varying initial conditions. The benefits of this approach are illustrated with extensive experiments in 3D action recognition using 3D joints sequences. In spite of its simplicity, the performance of this approach is competitive or better than using state-of-art approaches for this problem. Further, these results hold across a variety of metrics, supporting the idea that the improvement stems from the embedding itself, rather than from using one of these metrics.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"7 1","pages":"4498-4507"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87168567","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：