cvpr cvpr2013 cvpr2013-252 knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith
Abstract: This paper considers the person verification problem in modern surveillance and video retrieval systems. The problem is to identify whether a pair of face or human body images is about the same person, even if the person is not seen before. Traditional methods usually look for a distance (or similarity) measure between images (e.g., by metric learning algorithms), and make decisions based on a fixed threshold. We show that this is nevertheless insufficient and sub-optimal for the verification problem. This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule. We further formulate the inference on our decision function as a second-order large-margin regularization problem, and provide an efficient algorithm in its dual from. We evaluate our algorithm on both human body verification and face verification problems. Our method outperforms not only the classical metric learning algorithm including LMNN and ITML, but also the state-of-the-art in the computer vision community.
Reference: text
sentIndex sentText sentNum sentScore
1 Learning Locally-Adaptive Decision Functions for Person Verification Zhen Li ∗ Shiyu Chang ∗ Feng Liang UIUC UIUC UIUC zhenl i @ uiuc . [sent-1, score-0.406]
2 com Abstract This paper considers the person verification problem in modern surveillance and video retrieval systems. [sent-13, score-1.22]
3 The problem is to identify whether a pair of face or human body images is about the same person, even if the person is not seen before. [sent-14, score-0.678]
4 Traditional methods usually look for a distance (or similarity) measure between images (e. [sent-15, score-0.024]
5 , by metric learning algorithms), and make decisions based on a fixed threshold. [sent-17, score-0.101]
6 We show that this is nevertheless insufficient and sub-optimal for the verification problem. [sent-18, score-0.672]
7 This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule. [sent-19, score-0.927]
8 We further formulate the inference on our decision function as a second-order large-margin regularization problem, and provide an efficient algorithm in its dual from. [sent-20, score-0.17]
9 We evaluate our algorithm on both human body verification and face verification problems. [sent-21, score-1.373]
10 Our method outperforms not only the classical metric learning algorithm including LMNN and ITML, but also the state-of-the-art in the computer vision community. [sent-22, score-0.082]
11 Introduction Person verification, “Are you the person you claim to be,” is an important problem with many applications. [sent-24, score-0.414]
12 Modern image retrieval systems often want to verify whether photos contain the same person or the same object. [sent-25, score-0.675]
13 Person verification also gets more and more important for social network websites, where it is highly preferred to correctly assign personal photos to users. [sent-26, score-0.953]
14 More importantly, the huge amount of surveillance cameras - there are more than 30 million surveillance cameras in U. [sent-27, score-0.436]
15 recording about 4 billion hours of videos per week, calls for reliable systems which are able to identify the same person across differ∗ This research was supported in part by a research grant from Chongqing Institute of Green and Inteligent Technology, Chinese Academy of Sciences. [sent-29, score-0.77]
16 ent videos, a critical task that cannot merely rely on human labors. [sent-33, score-0.183]
17 So developing an automatic verification system is of great interest in practice. [sent-34, score-0.74]
18 There are two main visual clues for person verification: face images and human body figures. [sent-35, score-0.602]
19 Although our human vision system has the amazing ability of performing verification - we can judge whether two faces are about the same person without even seeing that person before, it is difficult to build a computer-based automatic system for this purpose. [sent-36, score-1.797]
20 For a given query image, the person in the image may not appear in the database or has only one or few images in the database. [sent-37, score-0.467]
21 Furthermore, the query image and the other images in the database are rarely collected in exactly the same environment, which leads to huge intra-person variations including viewpoint, lighting condition, image quality, resolution, etc. [sent-38, score-0.297]
22 Figure 1 provides some examples illustrating the difficulties with the person verification problem. [sent-39, score-1.062]
23 We can formally describe the verification problem as follows: for a pair of sample images represented by x, y ∈ Rd, respectively, iera cofh oafm wplheic imh corresponds t eod category ∈la Rbel c(x) and c(y), we aim to decide whether they are from the same category, i. [sent-40, score-0.991]
24 Given a set of training samples, our goal is to learn a decision function 333666001088 f(x, y) where f(x,y)? [sent-43, score-0.133]
wordName wordTfidf (topN-words)
[('verification', 0.6), ('uiuc', 0.406), ('person', 0.364), ('ibm', 0.225), ('decision', 0.11), ('surveillance', 0.103), ('photos', 0.099), ('smith', 0.096), ('amazing', 0.094), ('iangl', 0.094), ('cofh', 0.087), ('liangliang', 0.087), ('calls', 0.087), ('imh', 0.087), ('iang', 0.082), ('zhen', 0.082), ('itml', 0.078), ('billion', 0.078), ('huge', 0.078), ('modern', 0.076), ('whether', 0.073), ('body', 0.07), ('query', 0.069), ('websites', 0.068), ('lmnn', 0.068), ('clues', 0.065), ('thomas', 0.065), ('judge', 0.062), ('illustrating', 0.06), ('seeing', 0.058), ('personal', 0.055), ('face', 0.054), ('preferred', 0.054), ('academy', 0.054), ('cameras', 0.054), ('john', 0.053), ('liang', 0.053), ('decisions', 0.052), ('merely', 0.052), ('ent', 0.051), ('claim', 0.05), ('hours', 0.05), ('cao', 0.05), ('metric', 0.049), ('human', 0.049), ('recording', 0.048), ('decide', 0.048), ('videos', 0.047), ('huang', 0.047), ('social', 0.046), ('retrieval', 0.046), ('fp', 0.046), ('feng', 0.045), ('chinese', 0.044), ('million', 0.044), ('identify', 0.043), ('rarely', 0.042), ('developing', 0.041), ('gets', 0.041), ('category', 0.039), ('insufficient', 0.039), ('thresholding', 0.038), ('difficulties', 0.038), ('environment', 0.037), ('automatic', 0.037), ('verify', 0.036), ('network', 0.035), ('proposes', 0.035), ('dual', 0.035), ('database', 0.034), ('system', 0.034), ('la', 0.033), ('classical', 0.033), ('nevertheless', 0.033), ('formally', 0.032), ('considers', 0.031), ('importantly', 0.031), ('differ', 0.031), ('critical', 0.031), ('chang', 0.03), ('rd', 0.029), ('systems', 0.029), ('viewpoint', 0.029), ('faces', 0.028), ('great', 0.028), ('want', 0.028), ('lighting', 0.027), ('condition', 0.027), ('locally', 0.026), ('institute', 0.026), ('formulate', 0.025), ('pair', 0.025), ('look', 0.024), ('adaptive', 0.024), ('collected', 0.024), ('reliable', 0.024), ('assign', 0.023), ('exactly', 0.023), ('learn', 0.023), ('viewed', 0.022)]
simIndex simValue paperId paperTitle
same-paper 1 0.99999994 252 cvpr-2013-Learning Locally-Adaptive Decision Functions for Person Verification
Author: Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith
Abstract: This paper considers the person verification problem in modern surveillance and video retrieval systems. The problem is to identify whether a pair of face or human body images is about the same person, even if the person is not seen before. Traditional methods usually look for a distance (or similarity) measure between images (e.g., by metric learning algorithms), and make decisions based on a fixed threshold. We show that this is nevertheless insufficient and sub-optimal for the verification problem. This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule. We further formulate the inference on our decision function as a second-order large-margin regularization problem, and provide an efficient algorithm in its dual from. We evaluate our algorithm on both human body verification and face verification problems. Our method outperforms not only the classical metric learning algorithm including LMNN and ITML, but also the state-of-the-art in the computer vision community.
2 0.18523884 338 cvpr-2013-Probabilistic Elastic Matching for Pose Variant Face Verification
Author: Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, Jianchao Yang
Abstract: Pose variation remains to be a major challenge for realworld face recognition. We approach this problem through a probabilistic elastic matching method. We take a part based representation by extracting local features (e.g., LBP or SIFT) from densely sampled multi-scale image patches. By augmenting each feature with its location, a Gaussian mixture model (GMM) is trained to capture the spatialappearance distribution of all face images in the training corpus. Each mixture component of the GMM is confined to be a spherical Gaussian to balance the influence of the appearance and the location terms. Each Gaussian component builds correspondence of a pair of features to be matched between two faces/face tracks. For face verification, we train an SVM on the vector concatenating the difference vectors of all the feature pairs to decide if a pair of faces/face tracks is matched or not. We further propose a joint Bayesian adaptation algorithm to adapt the universally trained GMM to better model the pose variations between the target pair of faces/face tracks, which consistently improves face verification accuracy. Our experiments show that our method outperforms the state-ofthe-art in the most restricted protocol on Labeled Face in the Wild (LFW) and the YouTube video face database by a significant margin.
Author: Shoou-I Yu, Yi Yang, Alexander Hauptmann
Abstract: A device just like Harry Potter’s Marauder’s Map, which pinpoints the location ofeachperson-of-interest at all times, provides invaluable information for analysis of surveillance videos. To make this device real, a system would be required to perform robust person localization and tracking in real world surveillance scenarios, especially for complex indoor environments with many walls causing occlusion and long corridors with sparse surveillance camera coverage. We propose a tracking-by-detection approach with nonnegative discretization to tackle this problem. Given a set of person detection outputs, our framework takes advantage of all important cues such as color, person detection, face recognition and non-background information to perform tracking. Local learning approaches are used to uncover the manifold structure in the appearance space with spatio-temporal constraints. Nonnegative discretization is used to enforce the mutual exclusion constraint, which guarantees a person detection output to only belong to exactly one individual. Experiments show that our algorithm performs robust lo- calization and tracking of persons-of-interest not only in outdoor scenes, but also in a complex indoor real-world nursing home environment.
4 0.10705641 189 cvpr-2013-Graph-Based Discriminative Learning for Location Recognition
Author: Song Cao, Noah Snavely
Abstract: Recognizing the location of a query image by matching it to a database is an important problem in computer vision, and one for which the representation of the database is a key issue. We explore new ways for exploiting the structure of a database by representing it as a graph, and show how the rich information embedded in a graph can improve a bagof-words-based location recognition method. In particular, starting from a graph on a set of images based on visual connectivity, we propose a method for selecting a set of subgraphs and learning a local distance function for each using discriminative techniques. For a query image, each database image is ranked according to these local distance functions in order to place the image in the right part of the graph. In addition, we propose a probabilistic method for increasing the diversity of these ranked database images, again based on the structure of the image graph. We demonstrate that our methods improve performance over standard bag-of-words methods on several existing location recognition datasets.
5 0.10552134 270 cvpr-2013-Local Fisher Discriminant Analysis for Pedestrian Re-identification
Author: Sateesh Pedagadi, James Orwell, Sergio Velastin, Boghos Boghossian
Abstract: Metric learning methods, , forperson re-identification, estimate a scaling for distances in a vector space that is optimized for picking out observations of the same individual. This paper presents a novel approach to the pedestrian re-identification problem that uses metric learning to improve the state-of-the-art performance on standard public datasets. Very high dimensional features are extracted from the source color image. A first processing stage performs unsupervised PCA dimensionality reduction, constrained to maintain the redundancy in color-space representation. A second stage further reduces the dimensionality, using a Local Fisher Discriminant Analysis defined by a training set. A regularization step is introduced to avoid singular matrices during this stage. The experiments conducted on three publicly available datasets confirm that the proposed method outperforms the state-of-the-art performance, including all other known metric learning methods. Furthermore, the method is an effective way to process observations comprising multiple shots, and is non-iterative: the computation times are relatively modest. Finally, a novel statistic is derived to characterize the Match Characteris- tic: the normalized entropy reduction can be used to define the ’Proportion of Uncertainty Removed’ (PUR). This measure is invariant to test set size and provides an intuitive indication of performance.
6 0.10447728 451 cvpr-2013-Unsupervised Salience Learning for Person Re-identification
7 0.10234493 182 cvpr-2013-Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
8 0.097349085 271 cvpr-2013-Locally Aligned Feature Transforms across Views
9 0.086122632 160 cvpr-2013-Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-Based Classification
10 0.078039557 229 cvpr-2013-It's Not Polite to Point: Describing People with Uncertain Attributes
11 0.077557996 402 cvpr-2013-Social Role Discovery in Human Events
12 0.076080091 323 cvpr-2013-POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation
13 0.075202145 260 cvpr-2013-Learning and Calibrating Per-Location Classifiers for Visual Place Recognition
14 0.068515584 64 cvpr-2013-Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification
15 0.065474078 28 cvpr-2013-A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching
16 0.063440286 389 cvpr-2013-Semi-supervised Learning with Constraints for Person Identification in Multimedia Data
17 0.061350491 221 cvpr-2013-Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection
18 0.061152879 207 cvpr-2013-Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation
19 0.060650442 92 cvpr-2013-Constrained Clustering and Its Application to Face Clustering in Videos
20 0.059265658 335 cvpr-2013-Poselet Conditioned Pictorial Structures
topicId topicWeight
[(0, 0.104), (1, -0.051), (2, -0.03), (3, -0.03), (4, 0.029), (5, 0.009), (6, -0.037), (7, -0.048), (8, 0.08), (9, -0.063), (10, 0.024), (11, -0.0), (12, 0.061), (13, 0.038), (14, -0.014), (15, -0.011), (16, 0.02), (17, 0.007), (18, -0.016), (19, -0.105), (20, -0.007), (21, 0.07), (22, -0.05), (23, 0.033), (24, -0.016), (25, -0.064), (26, -0.03), (27, 0.035), (28, -0.06), (29, -0.102), (30, 0.015), (31, -0.023), (32, 0.061), (33, 0.046), (34, 0.072), (35, -0.0), (36, 0.013), (37, 0.148), (38, -0.046), (39, -0.071), (40, 0.04), (41, -0.007), (42, 0.127), (43, -0.015), (44, -0.026), (45, 0.009), (46, 0.035), (47, -0.024), (48, 0.019), (49, 0.114)]
simIndex simValue paperId paperTitle
same-paper 1 0.97678638 252 cvpr-2013-Learning Locally-Adaptive Decision Functions for Person Verification
Author: Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith
Abstract: This paper considers the person verification problem in modern surveillance and video retrieval systems. The problem is to identify whether a pair of face or human body images is about the same person, even if the person is not seen before. Traditional methods usually look for a distance (or similarity) measure between images (e.g., by metric learning algorithms), and make decisions based on a fixed threshold. We show that this is nevertheless insufficient and sub-optimal for the verification problem. This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule. We further formulate the inference on our decision function as a second-order large-margin regularization problem, and provide an efficient algorithm in its dual from. We evaluate our algorithm on both human body verification and face verification problems. Our method outperforms not only the classical metric learning algorithm including LMNN and ITML, but also the state-of-the-art in the computer vision community.
2 0.63910735 451 cvpr-2013-Unsupervised Salience Learning for Person Re-identification
Author: Rui Zhao, Wanli Ouyang, Xiaogang Wang
Abstract: Human eyes can recognize person identities based on some small salient regions. However, such valuable salient information is often hidden when computing similarities of images with existing approaches. Moreover, many existing approaches learn discriminative features and handle drastic viewpoint change in a supervised way and require labeling new training data for a different pair of camera views. In this paper, we propose a novel perspective for person re-identification based on unsupervised salience learning. Distinctive features are extracted without requiring identity labels in the training procedure. First, we apply adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations. Second, we learn human salience in an unsupervised manner. To improve the performance of person re-identification, human salience is incorporated in patch matching to find reliable and discriminative matched patches. The effectiveness of our approach is validated on the widely used VIPeR dataset and ETHZ dataset.
3 0.59019804 271 cvpr-2013-Locally Aligned Feature Transforms across Views
Author: Wei Li, Xiaogang Wang
Abstract: In this paper, we propose a new approach for matching images observed in different camera views with complex cross-view transforms and apply it to person reidentification. It jointly partitions the image spaces of two camera views into different configurations according to the similarity of cross-view transforms. The visual features of an image pair from different views are first locally aligned by being projected to a common feature space and then matched with softly assigned metrics which are locally optimized. The features optimal for recognizing identities are different from those for clustering cross-view transforms. They are jointly learned by utilizing sparsityinducing norm and information theoretical regularization. . cuhk . edu .hk (a) Camera view A (b) Camera view B This approach can be generalized to the settings where test images are from new camera views, not the same as those in the training set. Extensive experiments are conducted on public datasets and our own dataset. Comparisons with the state-of-the-art metric learning and person re-identification methods show the superior performance of our approach.
4 0.58501822 338 cvpr-2013-Probabilistic Elastic Matching for Pose Variant Face Verification
Author: Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, Jianchao Yang
Abstract: Pose variation remains to be a major challenge for realworld face recognition. We approach this problem through a probabilistic elastic matching method. We take a part based representation by extracting local features (e.g., LBP or SIFT) from densely sampled multi-scale image patches. By augmenting each feature with its location, a Gaussian mixture model (GMM) is trained to capture the spatialappearance distribution of all face images in the training corpus. Each mixture component of the GMM is confined to be a spherical Gaussian to balance the influence of the appearance and the location terms. Each Gaussian component builds correspondence of a pair of features to be matched between two faces/face tracks. For face verification, we train an SVM on the vector concatenating the difference vectors of all the feature pairs to decide if a pair of faces/face tracks is matched or not. We further propose a joint Bayesian adaptation algorithm to adapt the universally trained GMM to better model the pose variations between the target pair of faces/face tracks, which consistently improves face verification accuracy. Our experiments show that our method outperforms the state-ofthe-art in the most restricted protocol on Labeled Face in the Wild (LFW) and the YouTube video face database by a significant margin.
5 0.55966622 389 cvpr-2013-Semi-supervised Learning with Constraints for Person Identification in Multimedia Data
Author: Martin Bäuml, Makarand Tapaswi, Rainer Stiefelhagen
Abstract: We address the problem of person identification in TV series. We propose a unified learning framework for multiclass classification which incorporates labeled and unlabeled data, and constraints between pairs of features in the training. We apply the framework to train multinomial logistic regression classifiers for multi-class face recognition. The method is completely automatic, as the labeled data is obtained by tagging speaking faces using subtitles and fan transcripts of the videos. We demonstrate our approach on six episodes each of two diverse TV series and achieve state-of-the-art performance.
6 0.55744225 430 cvpr-2013-The SVM-Minus Similarity Score for Video Face Recognition
7 0.54148501 160 cvpr-2013-Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-Based Classification
8 0.53995174 182 cvpr-2013-Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
9 0.5387153 270 cvpr-2013-Local Fisher Discriminant Analysis for Pedestrian Re-identification
10 0.52860785 4 cvpr-2013-3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image
11 0.48997706 92 cvpr-2013-Constrained Clustering and Its Application to Face Clustering in Videos
13 0.45717239 120 cvpr-2013-Detecting and Naming Actors in Movies Using Generative Appearance Models
14 0.44838411 438 cvpr-2013-Towards Pose Robust Face Recognition
15 0.43799415 343 cvpr-2013-Query Adaptive Similarity for Large Scale Object Retrieval
16 0.4315688 119 cvpr-2013-Detecting and Aligning Faces by Image Retrieval
17 0.41162184 463 cvpr-2013-What's in a Name? First Names as Facial Attributes
18 0.38098788 272 cvpr-2013-Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery
19 0.38058814 82 cvpr-2013-Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories
20 0.36487043 229 cvpr-2013-It's Not Polite to Point: Describing People with Uncertain Attributes
topicId topicWeight
[(10, 0.018), (33, 0.811), (67, 0.031), (87, 0.019)]
simIndex simValue paperId paperTitle
same-paper 1 0.99879891 252 cvpr-2013-Learning Locally-Adaptive Decision Functions for Person Verification
Author: Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith
Abstract: This paper considers the person verification problem in modern surveillance and video retrieval systems. The problem is to identify whether a pair of face or human body images is about the same person, even if the person is not seen before. Traditional methods usually look for a distance (or similarity) measure between images (e.g., by metric learning algorithms), and make decisions based on a fixed threshold. We show that this is nevertheless insufficient and sub-optimal for the verification problem. This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule. We further formulate the inference on our decision function as a second-order large-margin regularization problem, and provide an efficient algorithm in its dual from. We evaluate our algorithm on both human body verification and face verification problems. Our method outperforms not only the classical metric learning algorithm including LMNN and ITML, but also the state-of-the-art in the computer vision community.
2 0.99763954 178 cvpr-2013-From Local Similarity to Global Coding: An Application to Image Classification
Author: Amirreza Shaban, Hamid R. Rabiee, Mehrdad Farajtabar, Marjan Ghazvininejad
Abstract: Bag of words models for feature extraction have demonstrated top-notch performance in image classification. These representations are usually accompanied by a coding method. Recently, methods that code a descriptor giving regard to its nearby bases have proved efficacious. These methods take into account the nonlinear structure of descriptors, since local similarities are a good approximation of global similarities. However, they confine their usage of the global similarities to nearby bases. In this paper, we propose a coding scheme that brings into focus the manifold structure of descriptors, and devise a method to compute the global similarities of descriptors to the bases. Given a local similarity measure between bases, a global measure is computed. Exploiting the local similarity of a descriptor and its nearby bases, a global measure of association of a descriptor to all the bases is computed. Unlike the locality-based and sparse coding methods, the proposed coding varies smoothly with respect to the underlying manifold. Experiments on benchmark image classification datasets substantiate the superiority oftheproposed method over its locality and sparsity based rivals.
3 0.99647361 357 cvpr-2013-Revisiting Depth Layers from Occlusions
Author: Adarsh Kowdle, Andrew Gallagher, Tsuhan Chen
Abstract: In this work, we consider images of a scene with a moving object captured by a static camera. As the object (human or otherwise) moves about the scene, it reveals pairwise depth-ordering or occlusion cues. The goal of this work is to use these sparse occlusion cues along with monocular depth occlusion cues to densely segment the scene into depth layers. We cast the problem of depth-layer segmentation as a discrete labeling problem on a spatiotemporal Markov Random Field (MRF) that uses the motion occlusion cues along with monocular cues and a smooth motion prior for the moving object. We quantitatively show that depth ordering produced by the proposed combination of the depth cues from object motion and monocular occlusion cues are superior to using either feature independently, and using a na¨ ıve combination of the features.
4 0.99600929 180 cvpr-2013-Fully-Connected CRFs with Non-Parametric Pairwise Potential
Author: Neill D.F. Campbell, Kartic Subr, Jan Kautz
Abstract: Conditional Random Fields (CRFs) are used for diverse tasks, ranging from image denoising to object recognition. For images, they are commonly defined as a graph with nodes corresponding to individual pixels and pairwise links that connect nodes to their immediate neighbors. Recent work has shown that fully-connected CRFs, where each node is connected to every other node, can be solved efficiently under the restriction that the pairwise term is a Gaussian kernel over a Euclidean feature space. In this paper, we generalize the pairwise terms to a non-linear dissimilarity measure that is not required to be a distance metric. To this end, we propose a density estimation technique to derive conditional pairwise potentials in a nonparametric manner. We then use an efficient embedding technique to estimate an approximate Euclidean feature space for these potentials, in which the pairwise term can still be expressed as a Gaussian kernel. We demonstrate that the use of non-parametric models for the pairwise interactions, conditioned on the input data, greatly increases expressive power whilst maintaining efficient inference.
5 0.99600494 93 cvpr-2013-Constraints as Features
Author: Shmuel Asafi, Daniel Cohen-Or
Abstract: In this paper, we introduce a new approach to constrained clustering which treats the constraints as features. Our method augments the original feature space with additional dimensions, each of which derived from a given Cannot-link constraints. The specified Cannot-link pair gets extreme coordinates values, and the rest of the points get coordinate values that express their spatial influence from the specified constrained pair. After augmenting all the new features, a standard unconstrained clustering algorithm can be performed, like k-means or spectral clustering. We demonstrate the efficacy of our method for active semi-supervised learning applied to image segmentation and compare it to alternative methods. We also evaluate the performance of our method on the four most commonly evaluated datasets from the UCI machine learning repository.
6 0.99575824 55 cvpr-2013-Background Modeling Based on Bidirectional Analysis
7 0.9952994 260 cvpr-2013-Learning and Calibrating Per-Location Classifiers for Visual Place Recognition
8 0.99472606 346 cvpr-2013-Real-Time No-Reference Image Quality Assessment Based on Filter Learning
9 0.99371517 137 cvpr-2013-Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis
10 0.99208933 113 cvpr-2013-Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video
11 0.991431 59 cvpr-2013-Better Exploiting Motion for Better Action Recognition
12 0.99120706 165 cvpr-2013-Fast Energy Minimization Using Learned State Filters
13 0.98692036 48 cvpr-2013-Attribute-Based Detection of Unfamiliar Classes with Humans in the Loop
14 0.9856196 301 cvpr-2013-Multi-target Tracking by Rank-1 Tensor Approximation
15 0.97736204 266 cvpr-2013-Learning without Human Scores for Blind Image Quality Assessment
16 0.97697693 189 cvpr-2013-Graph-Based Discriminative Learning for Location Recognition
17 0.97675389 379 cvpr-2013-Scalable Sparse Subspace Clustering
18 0.97439885 343 cvpr-2013-Query Adaptive Similarity for Large Scale Object Retrieval
19 0.97407913 148 cvpr-2013-Ensemble Video Object Cut in Highly Dynamic Scenes
20 0.97308075 378 cvpr-2013-Sampling Strategies for Real-Time Action Recognition