3,888 results match your criteria IEEE transactions on pattern analysis and machine intelligence[Journal]


A Novel Dynamic Model Capturing Spatial and Temporal Patterns for Facial Expression Analysis.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 17. Epub 2019 Apr 17.

Facial expression analysis could be greatly improved by incorporating spatial and temporal patterns present in facial behavior, but the patterns have not yet been utilized to their full advantage. We remedy this via a novel dynamic model - an interval temporal restricted Boltzmann machine (IT-RBM) - that is able to capture both universal spatial patterns and complicated temporal patterns in facial behavior for facial expression analysis. We regard a facial expression as a multifarious activity composed of sequential or overlapping primitive facial events. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2911937DOI Listing

Fine-grained Human-centric Tracklet Segmentation with Single Frame Supervision.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 17. Epub 2019 Apr 17.

In this paper, we target at the Fine-grAined human-Centric Tracklet Segmentation (FACTS) problem, where 12 human parts, e.g., face, pants, left-leg, are segmented. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2911936DOI Listing

Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 15. Epub 2019 Apr 15.

In this work we present a new approach to the field of weakly supervised learning in the video domain. Our method is relevant to sequence learning problems which can be split up into sub-problems that occur in parallel. Here, we experiment with sign language data. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2911077DOI Listing
April 2019
2 Reads

Significance of Softmax-based Features in Comparison to Distance Metric Learning-based Features.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 15. Epub 2019 Apr 15.

End-to-end distance metric learning (DML) has been applied to obtain features useful in many computer vision tasks. However, these DML studies have not provided equitable comparisons between features extracted from DML-based networks and softmax-based networks. In this paper, we present objective comparisons between these two approaches under the same network architecture. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2911075DOI Listing

Learning to Compose and Reason with Language Tree Structures for Visual Grounding.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 15. Epub 2019 Apr 15.

Grounding natural language in images, such as localizing "the black dog on the left of the tree", is one of the core problems in artificial intelligence, as it needs to comprehend the fine-grained and compositional language space. However, existing solutions rely on the association between the holistic language features and visual features, while neglect the nature of compositional reasoning implied in the language. In this paper, we propose a natural language grounding model that can automatically compose a binary tree structure for parsing the language and then perform visual reasoning along the tree in a bottom-up fashion. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2911066DOI Listing
April 2019
1 Read

Multilabel Deep Visual-Semantic Embedding.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 15. Epub 2019 Apr 15.

Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models for multilabel images. We propose a new learning paradigm for multilabel image classification, in which labels are ranked according to its relevance to the input image. In contrast to conventional CNN models that learn a latent vector representation (i. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2911065DOI Listing
April 2019
1 Read

Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 15. Epub 2019 Apr 15.

While numerous deep approaches to the problem of vision-aided localization have been recently proposed, systems operating in the real world will undoubtedly experience novel sensory states previously unseen even under the most prodigious training regimens. We address the localization problem with online error correction (OEC) modules that are trained to correct a vision-aided localization network's mistakes. We demonstrate the generalizability of the OEC modules and describe our unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2909895DOI Listing
April 2019
1 Read

Object Detection in Videos by High Quality Object Linking.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 11. Epub 2019 Apr 11.

Compared with object detection in static images, object detection in videos is more challenging due to degraded image qualities. An effective way to address this problem is to exploit temporal contexts by linking the same object across video to form tubelets and aggregating classification scores in the tubelets. In this paper, we focus on obtaining high quality object linking results for better classification. Read More

View Article

Download full-text PDF

Source
https://ieeexplore.ieee.org/document/8686124/
Publisher Site
http://dx.doi.org/10.1109/TPAMI.2019.2910529DOI Listing
April 2019
1 Read

A Comprehensive Analysis of Deep Regression.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 11. Epub 2019 Apr 11.

Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks. Vision tasks, such as human pose estimation, did not escape from this trend. There is a large number of deep models, where small changes in the network architecture, or in the data pre-processing, together with the stochastic nature of the optimization procedures, produce notably different results, making extremely difficult to sift methods that significantly outperform others. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2910523DOI Listing

Age from faces in the deep learning revolution.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 11. Epub 2019 Apr 11.

Face analysis includes a variety of specific problems as face detection, person identification, gender and ethnicity recognition; in the last two decades, significant research efforts have been devoted to the challenging task of age estimation from faces, as witnessed by the high number of published papers. The explosion of the deep learning paradigm, that is determining a spectacular increasing of the performance, is in the public eye; consequently, the number of approaches based on deep learning is impressively growing and this also happened for age estimation. The exciting results obtained have been recently surveyed on almost all the specific face analysis problems; the only exception stands for age estimation, whose last survey dates back to 2010 and does not include any deep learning based approach to the problem. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2910522DOI Listing
April 2019
2 Reads

Learning Complexity-Aware Cascades for Pedestrian Detection.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 11. Epub 2019 Apr 11.

The problem of pedestrian detection is considered. The design of complexity-aware cascaded pedestrian detectors, combining features of very different complexities, is investigated. A new cascade design procedure is introduced, by formulating cascade learning as the Lagrangian optimization of a risk that accounts for both accuracy and complexity. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2910514DOI Listing

Denoising Autoencoders for Overgeneralization in Neural Networks.

Authors:
Giacomo Spigler

IEEE Trans Pattern Anal Mach Intell 2019 Apr 9. Epub 2019 Apr 9.

Despite recent developments that allowed neural networks to achieve impressive performance on a variety of applications, these models are intrinsically affected by the problem of overgeneralization, due to their partitioning of the full input space into the fixed set of target classes used during training. Thus it is possible for novel inputs belonging to categories unknown during training or even completely unrecognizable to humans to fool the system into classifying them as one of the known classes, even with a high degree of confidence. This problem can lead to security problems in critical applications, and is closely linked to open set recognition and 1-class recognition. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2909876DOI Listing

Context-Aware Visual Policy Network for Fine-Grained Image Captioning.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 9. Epub 2019 Apr 9.

With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i.e., the task of image captioning. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2909864DOI Listing

Globally Optimal Inlier Set Maximization for Atlanta World Understanding.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 9. Epub 2019 Apr 9.

In this work, we describe man-made structures via an appropriate structure assumption, called Atlanta world, which contains a vertical direction (typically the gravity direction) and a set of horizontal directions orthogonal to the vertical direction. Contrary to the commonly used Manhattan world assumption, the horizontal directions in Atlanta world are not necessarily orthogonal to each other. While Atlanta world permits to encompass a wider range of scenes, this makes the solution space much larger and the problem more challenging. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2909863DOI Listing

Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 2. Epub 2019 Apr 2.

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First, for deterministic DNNs, either the IB functional is infinite for almost all values of network parameters, making the optimization problem ill-posed, or it is piecewise constant, hence not admitting gradient-based optimization methods. Second, the invariance of the IB functional under bijections prevents it from capturing properties of the learned representation that are desirable for classification, such as robustness and simplicity. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2909031DOI Listing
April 2019
1 Read

Aggregated Wasserstein Distance and State Registration for Hidden Markov Models.

IEEE Trans Pattern Anal Mach Intell 2019 Apr 1. Epub 2019 Apr 1.

We propose a framework, named Aggregated Wasserstein, for computing a distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time position follows a Gaussian mixture distribution, a fact exploited to softly match, aka register, the states in two HMMs. The registration of states is inspired by the intrinsic relationship of optimal transport and the Wasserstein metric between distributions. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2908635DOI Listing
April 2019
1 Read

Multi-Source Causal Feature Selection.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 29. Epub 2019 Mar 29.

Causal feature selection has attracted much attention in recent years, as the causal features selected imply the causal mechanism related to the class attribute, leading to more reliable prediction models built using them. Currently there is a need of developing multi-source feature selection methods, since in many applications data for studying the same problem has been collected from various sources, such as multiple gene expression datasets obtained from different experiments for studying the causes of the same disease. However, the state-of-the-art causal feature selection methods generally tackle a single dataset, and a direct application of the methods to multiple datasets will result in unreliable results as the datasets may have different distributions. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2908373DOI Listing
March 2019
1 Read

Generalized Feedback Loop for Joint Hand-Object Pose Estimation.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 27. Epub 2019 Mar 27.

We propose an approach to estimating the 3D pose of a hand, possibly handling an object, given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a feedback loop. The components of this feedback loop are also Deep Networks, optimized using training data. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2907951DOI Listing
March 2019
1 Read

Recognizing Material Properties from Images.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 27. Epub 2019 Mar 27.

Humans implicitly rely on the properties of materials to guide our interactions. Grasping smooth materials, for example, requires more care than rough ones. We may even visually infer non-visual properties (e. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2907850DOI Listing

Tensor Graphical Model: Non-convex Optimization and Statistical Inference.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 26. Epub 2019 Mar 26.

We consider estimation and inference of precision matrices in sparse tensor graphical models. To facilitate study, data is assumed to follow a tensor normal distribution whose covariance has a Kronecker product structure. A critical challenge in both estimation and inference of this model is that its penalized maximum likelihood estimation involves minimizing a non-convex objective function. Read More

View Article

Download full-text PDF

Source
https://ieeexplore.ieee.org/document/8674569/
Publisher Site
http://dx.doi.org/10.1109/TPAMI.2019.2907679DOI Listing
March 2019
4 Reads

Towards Efficient U-Nets: A Coupled and Quantized Approach.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 26. Epub 2019 Mar 26.

In this paper, we propose to couple stacked U-Nets for efficient visual landmark localization. The key idea is to globally reuse features of the same semantic meanings across the stacked U-Nets. The feature reuse makes each U-Net light-weighted. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2907634DOI Listing
March 2019
2 Reads

Learning of Gaussian Processes in Distributed and Communication Limited Systems.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 19. Epub 2019 Mar 19.

It is of fundamental importance to find algorithms obtaining optimal performance for learning of statistical models in distributed and communication limited systems. Aiming at characterizing the optimal strategies, we consider learning of Gaussian Processes (GP) in distributed systems as a pivotal example. We first address a very basic problem: how many bits are required to estimate the inner-products of some Gaussian vectors across distributed machines? Using information theoretic bounds, we obtain an optimal solution for the problem which is based on vector quantization. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2906207DOI Listing

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges.

Authors:
Olga Veksler

IEEE Trans Pattern Anal Mach Intell 2019 Mar 19. Epub 2019 Mar 19.

Fully connected pairwise Conditional Random Fields (Full-CRF) with Gaussian edge weights can achieve superior results compared to sparsely connected CRFs. However, traditional methods for Full-CRFs are too expensive. Previous work develops efficient approximate optimization based on mean field inference, which is a local optimization method can be far from the optimum. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2906204DOI Listing

Motion-Guided Cascaded Refinement Network for Video Object Segmentation.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 19. Epub 2019 Mar 19.

In this work, we propose a motion-guided cascaded refinement network for video object segmentation. By assuming the target object shows different motion patterns from the background, for each video frame we apply an active contour model on optical flow to coarsely segment the foreground. The proposed Cascaded Refinement Network (CRN) then takes as guidance the coarse segmentation to generate an accurate segmentation in full resolution. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2906175DOI Listing

Learning to Index for Nearest Neighbor Search.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 25. Epub 2019 Mar 25.

In this study, we present a novel ranking model based on learning neighborhood relationships embedded in the index space. Given a query point, conventional approximate nearest neighbor search calculates the distances to the cluster centroids, before ranking the clusters from near to far based on the distances. The data indexed in the top-ranked clusters are retrieved and treated as the nearest neighbor candidates for the query. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2907086DOI Listing

Social Anchor-Unit Graph Regularized Tensor Completion for Large-Scale Image Retagging.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 25. Epub 2019 Mar 25.

Image retagging aims to improve the tag quality of social images by completing the missing tags, recrifying the noise-corrupted tags, and assigning new high-quality tags. Recent approaches simultaneously explore visual, user and tag information to improve the performance of image retagging by mining the tag-image-user associations. However, such methods will become computationally infeasible with the rapidly increasing number of images, tags and users. Read More

View Article

Download full-text PDF

Source
https://ieeexplore.ieee.org/document/8673651/
Publisher Site
http://dx.doi.org/10.1109/TPAMI.2019.2906603DOI Listing
March 2019
5 Reads

Back To The Future: Radial Basis Function Network Revisited.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 25. Epub 2019 Mar 25.

Radial Basis Function (RBF) networks are a classical family of algorithms for supervised learning. The most popular approach for training RBF networks has relied on kernel methods using regularization based on a norm in a Reproducing Kernel Hilbert Space (RKHS), which is a principled and empirically successful framework. In this paper we aim to revisit some of the older approaches to training the RBF networks from a more modern perspective. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2906594DOI Listing

Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Network.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 25. Epub 2019 Mar 25.

Defocus blur detection (DBD) is aimed to estimate the probability of each pixel being in-focus or out-of-focus. This process has been paid considerable attention due to its remarkable potential applications. Accurate differentiation of homogeneous regions and detection of low-contrast focal regions, as well as suppression of background clutter, are challenges associated with DBD. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2906588DOI Listing
March 2019
1 Read

Inferring Salient Objects from Human Fixations.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 18. Epub 2019 Mar 18.

Previous research in visual saliency focused on two major types of models namely fixation prediction and salient object detection. The relationship between the two, however, has been less explored. We propose to employ the former model type to identify salient objects. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2905607DOI Listing
March 2019
1 Read

ROAM: a Rich Object Appearance Model with Application to Rotoscoping.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 13. Epub 2019 Mar 13.

Rotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping tools rely on parametric curves that offer the artists a much better interactive control on the definition, editing and manipulation of the segments of interest. Sticking to this prevalent rotoscoping paradigm, we propose a novel framework to capture and track the visual aspect of an arbitrary object in a scene, given an initial closed outline of this object. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2904963DOI Listing

On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 11. Epub 2019 Mar 11.

Parsimonious representations are ubiquitous in modeling and processing information. Motivated by the recent Multi-Layer Convolutional Sparse Coding (ML-CSC) model, we herein generalize the traditional Basis Pursuit problem to a multi-layer setting, introducing similar sparse enforcing penalties at different representation layers in a symbiotic relation between synthesis and analysis sparse priors. We explore different iterative methods to solve this new problem in practice, and we propose a new Multi-Layer Iterative Soft Thresholding Algorithm (ML-ISTA), as well as a fast version (ML-FISTA). Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2904255DOI Listing

Contactless Biometric Identification using 3D Finger Knuckle Patterns.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 11. Epub 2019 Mar 11.

Study on finger knuckle patterns has attracted increasing attention for the automated biometric identification. However, finger knuckle pattern is essentially a 3D biometric identifier and the usage or availability of only 2D finger knuckle databases in the literature is the key limitation to avail full potential from this biometric identifier. This paper therefore introduces (first) contactless 3D finger knuckle database in public domain, which is acquired from 130 different subjects in two-session imaging using photometric stereo approach. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2904232DOI Listing
March 2019
1 Read
1.614 Impact Factor

Approximate Sparse Multinomial Logistic Regression for Classification.

Authors:
Koray Kayabol

IEEE Trans Pattern Anal Mach Intell 2019 Mar 8. Epub 2019 Mar 8.

We propose a new learning rule for sparse multinomial logistic regression (SMLR). The new rule is the generalization of the one proposed in the pioneering work by Krishnapuram et al. In our proposed method, the parameters of SMLR are iteratively estimated from log-posterior by using some approximations. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2904062DOI Listing

A Simple and Fast Algorithm for L1-norm Kernel PCA.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 6. Epub 2019 Mar 6.

We present an algorithm for L1-norm kernel PCA and provide a convergence analysis for it. While an optimal solution of L2-norm kernel PCA can be obtained through matrix decomposition, finding that of L1-norm kernel PCA is not trivial due to its non-convexity and non-smoothness. We provide a novel reformulation through which an equivalent, geometrically interpretable problem is obtained. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903505DOI Listing

Estimation of Wetness and Color From A Single Multispectral Image.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 6. Epub 2019 Mar 6.

Recognizing wet surfaces and their degrees of wetness is essential for many computer vision applications. Surface wetness can inform us slippery spots on a road to autonomous vehicles, muddy areas of a trail to humanoid robots, and the freshness of groceries to us. In this paper, we show that color change, particularly in its spectral behavior, carries rich information about surface wetness. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903496DOI Listing

A Continuation Method for Graph Matching based Feature Correspondence.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 6. Epub 2019 Mar 6.

Feature correspondence lays the foundation for many computer vision and image processing tasks, which can be well formulated and solved by graph matching. Because of the high complexity, approximate methods are necessary for graph matching, and the continuous relaxation provides an efficient approximate scheme. But there are still many problems to be settled, such as the highly nonconvex objective function, the ignorance of the combinatorial nature of graph matching in the optimization process, and few attention to the outlier problem. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903483DOI Listing
March 2019
4 Reads

A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 6. Epub 2019 Mar 6.

During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving. However, to train CNNs requires a considerable amount of data, which is difficult to collect and laborious to annotate. Recent advances in computer graphics make it possible to train CNNs on photo-realistic synthetic imagery with computer-generated annotations. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903401DOI Listing

Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 5. Epub 2019 Mar 5.

The combination of spiking neural networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from the raw stimuli generated with an event-based camera. A novel adaptive neuron model and stable spike-timing-dependent plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903179DOI Listing

Learning Raw Image Reconstruction-Aware Deep Image Compressors.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 4. Epub 2019 Mar 4.

Deep learning-based image compressors are actively being explored in an effort to supersede conventional image compression algorithms, such as JPEG. Conventional and deep learning-based compression algorithms focus on minimizing image fidelity errors in the nonlinear standard RGB (sRGB) color space. However, for many computer vision tasks, the sensor's linear raw-RGB image is desirable. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903062DOI Listing

Unsupervised Tracklet Person Re-Identification.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 4. Epub 2019 Mar 4.

Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in a practical re-id deployment, due to the lack of exhaustive identity labelling of positive and negative image pairs for every camera-pair. In this work, we present an unsupervised re-id deep learning approach. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903058DOI Listing

Optimal Transport in Reproducing Kernel Hilbert Spaces: Theory and Applications.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 4. Epub 2019 Mar 4.

In this paper, we present a mathematical and computational framework for comparing and matching distributions in reproducing kernel Hilbert spaces (RKHS). This framework, called optimal transport in RKHS, is a generalization of the optimal transport problem in input spaces to (potentially) infinite-dimensional feature spaces. We provide a computable formulation of Kantorovich's optimal transport in RKHS. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903050DOI Listing

Computational Imaging on the Electric Grid.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 4. Epub 2019 Mar 4.

Night beats with alternating current (AC) illumination. By passively sensing this beat, we reveal new scene information which includes: the type of bulbs in the scene, the phases of the electric grid up to city scale, and the light transport matrix. This information yields unmixing of reflections and semi-reflections, nocturnal high dynamic range, and scene rendering with bulbs not observed during acquisition. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2903035DOI Listing
March 2019
1 Read

Side Information for Face Completion: a Robust PCA Approach.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 4. Epub 2019 Mar 4.

Robust principal component analysis (RPCA) is a powerful method for learning low-rank feature representation of various visual data. However, for certain types as well as significant amount of error corruption, it fails to yield satisfactory results; a drawback that can be alleviated by exploiting domain-dependent prior knowledge or information. In this paper, we propose two models for the RPCA that take into account such side information, even in the presence of missing values. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2902556DOI Listing
March 2019
2 Reads

Online Nearest Neighbor Search Using Hamming Weight Trees.

IEEE Trans Pattern Anal Mach Intell 2019 Mar 1. Epub 2019 Mar 1.

Nearest neighbor search is a basic and recurring proximity problem that has been studied for several decades. The goal is to preprocess a dataset of points so that we can quickly report the closet point(s) to any query point. Many recent applications of NNS involve datasets that are very large and dynamic, that is items of data items become available gradually. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2902391DOI Listing

Hiding Images Within Images.

Authors:
Shumeet Baluja

IEEE Trans Pattern Anal Mach Intell 2019 Feb 28. Epub 2019 Feb 28.

We present a system to hide a full color image inside another of the same size with minimal quality loss to either image. Deep neural networks are simultaneously trained to create the hiding and revealing processes and are designed to specifically work as a pair. The system is trained on images drawn randomly from the ImageNet database, and works well on natural images from a wide variety of sources. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2901877DOI Listing
February 2019
1 Read

Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization.

IEEE Trans Pattern Anal Mach Intell 2019 Feb 26. Epub 2019 Feb 26.

Landmark/pose estimation in single monocular images has received much effort in computer vision due to its important applications. It remains a challenging task when input images come with severe occlusions caused by, e.g. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2901875DOI Listing
February 2019
2 Reads

Logistic Regression Confined by Cardinality-Constrained Sample and Feature Selection.

IEEE Trans Pattern Anal Mach Intell 2019 Feb 26. Epub 2019 Feb 26.

Many vision-based applications rely on logistic regression for embedding classification within a probabilistic context, such as recognition in images and videos or identifying disease-specific image phenotypes from neuroimages. Logistic regression, however, often performs poorly when trained on data that is noisy, has irrelevant features, or when the samples are distributed across the classes in an imbalanced setting; a common occurrence in visual recognition tasks. To deal with those issues, researchers generally rely on ad-hoc regularization techniques or model a subset of these issues. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2901688DOI Listing
February 2019
2 Reads

Learning Multiple Local Metrics: Global Consideration Helps.

IEEE Trans Pattern Anal Mach Intell 2019 Feb 26. Epub 2019 Feb 26.

Learning distance metric between objects provides a better measurement for their relative comparison. Due to the complex properties inside or between heterogeneous objects, multiple local distance metrics become essential representation tools to depict various local perspectives of examples. Different from existing methods building more than one local metric directly, however, the global metric is emphasized when generating multiple local ones in this manuscript. Read More

View Article

Download full-text PDF

Source
https://ieeexplore.ieee.org/document/8653339/
Publisher Site
http://dx.doi.org/10.1109/TPAMI.2019.2901675DOI Listing
February 2019
4 Reads

Moments in Time Dataset: one million videos for event understanding.

IEEE Trans Pattern Anal Mach Intell 2019 Feb 25. Epub 2019 Feb 25.

We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical or not in time ("opening" means "closing" in reverse order), and transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2901464DOI Listing
February 2019
1 Read
1.614 Impact Factor

Ambiguity-Free Radiometric Calibration for Internet Photo Collections.

IEEE Trans Pattern Anal Mach Intell 2019 Feb 25. Epub 2019 Feb 25.

Radiometrically calibrating images from Internet photo collections makes photometric analysis applicable not only to lab data but also to big image data in the wild. However, conventional calibration methods cannot be directly applied to such photo collections. This paper presents a method to jointly perform radiometric calibration for a set of images in Internet photo collections. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2019.2901458DOI Listing
February 2019
2 Reads