Latest in

total 11596took 0.27s
Texture Segmentation Based Video Compression Using Convolutional Neural NetworksFeb 08 2018There has been a growing interest in using different approaches to improve the coding efficiency of modern video codec in recent years as demand for web-based video consumption increases. In this paper, we propose a model-based approach that uses texture ... More
A Generalization Method of Partitioned Activation Function for Complex NumberFeb 08 2018A method to convert real number partitioned activation function into complex number one is provided. The method has 4em variations; 1 has potential to get holomorphic activation, 2 has potential to conserve complex angle, and the last 1 guarantees interaction ... More
Practical Issues of Action-conditioned Next Image PredictionFeb 08 2018The problem of action-conditioned image prediction is to predict the expected next frame given the current camera frame the robot observes and an action selected by the robot. We provide the first comparison of two recent popular models, especially for ... More
TSViz: Demystification of Deep Learning Models for Time-Series AnalysisFeb 08 2018This paper presents a novel framework for demystification of convolutional deep learning models for time series analysis. This is a step towards making informed/explainable decisions in the domain of time series, powered by deep learning. There have been ... More
Rotate your Networks: Better Weight Consolidation and Less Catastrophic ForgettingFeb 08 2018In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. ... More
A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRIFeb 08 2018Mild traumatic brain injury (mTBI) is a growing public health problem with an estimated incidence of one million people annually in US. Neurocognitive tests have been used to both assess the patient condition and to monitor the patient progress. This ... More
Archetypal Analysis for Sparse Representation-based Hyperspectral Sub-pixel QuantificationFeb 08 2018The estimation of land cover fractions from remote sensing images is a frequently used indicator of the environmental quality. This paper focuses on the quantification of land cover fractions in an urban area of Berlin, Germany, using simulated hyperspectral ... More
Peekaboo - Where are the Objects? Structure Adjusting SuperpixelsFeb 08 2018This paper addresses the search for a fast and meaningful image segmentation in the context of $k$-means clustering. The proposed method builds on a widely-used local version of Lloyd's algorithm, called Simple Linear Iterative Clustering (SLIC). We propose ... More
Saliency-Enhanced Robust Visual TrackingFeb 08 2018Discrete correlation filter (DCF) based trackers have shown considerable success in visual object tracking. These trackers often make use of low to mid level features such as histogram of gradients (HoG) and mid-layer activations from convolution neural ... More
Learning to score and summarize figure skating sport videosFeb 08 2018This paper focuses on fully understanding the figure skating sport videos. In particular, we present a large-scale figure skating sport video dataset, which include 500 figure skating videos. On average, the length of each video is 2 minute and 50 seconds. ... More
From Hashing to CNNs: Training BinaryWeight Networks via HashingFeb 08 2018Deep convolutional neural networks (CNNs) have shown appealing performance on various computer vision tasks in recent years. This motivates people to deploy CNNs to realworld applications. However, most of state-of-art CNNs require large memory and computational ... More
Topologically Controlled Lossy CompressionFeb 08 2018This paper presents a new algorithm for the lossy compression of scalar data defined on 2D or 3D regular grids, with topological control. Certain techniques allow users to control the pointwise error induced by the compression. However, in many scenarios ... More
Deep Image Super Resolution via Natural Image PriorsFeb 08 2018Single image super-resolution (SR) via deep learning has recently gained significant attention in the literature. Convolutional neural networks (CNNs) are typically learned to represent the mapping between low-resolution (LR) and high-resolution (HR) ... More
Driver Gaze Zone Estimation using Convolutional Neural Networks: A General Framework and Ablative AnalysisFeb 08 2018Driver gaze has been shown to be an excellent surrogate for driver attention in intelligent vehicles. With the recent surge of highly autonomous vehicles, driver gaze can be useful for determining the handoff time to a human driver. While there has been ... More
A Semi-Supervised Two-Stage Approach to Learning from Noisy LabelsFeb 08 2018The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dateset. On the contrary, it is fairly convenient, fast, and cheap to collect ... More
PPFNet: Global Context Aware Local Features for Robust 3D Point MatchingFeb 07 2018We present PPFNet - Point Pair Feature NETwork for deeply learning a globally informed 3D local feature descriptor to find correspondences in unorganized point clouds. PPFNet learns local descriptors on pure geometry and is highly aware of the global ... More
Fine-Grained Land Use Classification at the City Scale Using Ground-Level ImagesFeb 07 2018We perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing ... More
SCK: A sparse coding based key-point detectorFeb 07 2018All current popular hand-crafted key-point detectors such as Harris corner, MSER, SIFT, SURF... rely on some specific pre-designed structures for the detection of corners, blobs, or junctions in an image. In this paper, a novel sparse coding based key ... More
Spatially adaptive image compression using a tiled deep networkFeb 07 2018Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant spatial bit rate ... More
Going Deeper in Spiking Neural Networks: VGG and Residual ArchitecturesFeb 07 2018Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network ... More
Effective Quantization Approaches for Recurrent Neural NetworksFeb 07 2018Deep learning, and in particular Recurrent Neural Networks (RNN) have shown superior accuracy in a large variety of tasks including machine translation, language understanding, and movie frame generation. However, these deep learning approaches are very ... More
Encoder-Decoder with Atrous Separable Convolution for Semantic Image SegmentationFeb 07 2018Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling ... More
Deep Versus Wide Convolutional Neural Networks for Object Recognition on Neuromorphic SystemFeb 07 2018In the last decade, special purpose computing systems, such as Neuromorphic computing, have become very popular in the field of computer vision and machine learning for classification tasks. In 2015, IBM's released the TrueNorth Neuromorphic system, kick-starting ... More
An Unsupervised Learning Model for Deformable Medical Image RegistrationFeb 07 2018We present an efficient learning-based algorithm for deformable, pairwise 3D medical image registration. Current registration methods optimize an energy function independently for each pair of images, which can be time-consuming for large data. We define ... More
Generating Triples with Adversarial Networks for Scene Graph ConstructionFeb 07 2018Driven by successes in deep learning, computer vision research has begun to move beyond object detection and image classification to more sophisticated tasks like image captioning or visual question answering. Motivating such endeavors is the desire for ... More
Unsupervised Typography TransferFeb 07 2018Traditional methods in Chinese typography synthesis view characters as an assembly of radicals and strokes, but they rely on manual definition of the key points, which is still time-costing. Some recent work on computer vision proposes a brand new approach: ... More
VISER: Visual Self-RegularizationFeb 07 2018In this work, we propose the use of large set of unlabeled images as a source of regularization data for learning robust visual representation. Given a visual model trained by a labeled dataset in a supervised fashion, we augment our training samples ... More
FixaTons: A collection of Human Fixations Datasets and Metrics for Scanpath SimilarityFeb 07 2018Feb 08 2018In the last three decades, human visual attention has been a topic of great interest in various disciplines. In computer vision, many models have been proposed to predict the distribution of human fixations on a visual input. Recently, thanks to the creation ... More
A Spatial Mapping Algorithm with Applications in Deep Learning-Based Structure ClassificationFeb 07 2018Convolutional Neural Network (CNN)-based machine learning systems have made breakthroughs in feature extraction and image recognition tasks in two dimensions (2D). Although there is significant ongoing work to apply CNN technology to domains involving ... More
Fair comparison of skin detection approaches on publicly available datasetsFeb 07 2018Skin detection is the process of discriminating skin and non-skin regions in a digital image and it is widely used in several applications ranging from hand gesture analysis to tracking body parts and face detection. Skin detection is a challenging problem ... More
Deep Reinforcement Learning for Image HashingFeb 07 2018Deep hashing methods have received much attention recently, which achieve promising results by taking advantage of the strong representation power of deep networks. However, most existing deep hashing methods learn a whole set of hashing functions independently ... More
SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial NetworkFeb 07 2018Cross-modal hashing aims to map heterogeneous multimedia data into a common Hamming space, which can realize fast and flexible retrieval across different modalities. Supervised cross-modal hashing methods have achieved considerable progress by incorporating ... More
Pixel-Level Alignment of Facial Images for High Accuracy Recognition Using Ensemble of PatchesFeb 07 2018The variation of pose, illumination and expression makes face recognition still a challenging problem. As a pre-processing in holistic approaches, faces are usually aligned by eyes. The proposed method tries to perform a pixel alignment rather than eye-alignment ... More
Stochastic Deconvolutional Neural Network Ensemble Training on Generative Pseudo-Adversarial NetworksFeb 07 2018The training of Generative Adversarial Networks is a difficult task mainly due to the nature of the networks. One such issue is when the generator and discriminator start oscillating, rather than converging to a fixed point. Another case can be when one ... More
Revisiting the Inverted Indices for Billion-Scale Approximate Nearest NeighborsFeb 07 2018This work addresses the problem of billion-scale nearest neighbor search. The state-of-the-art retrieval systems for billion-scale databases are currently based on the inverted multi-index, the recently proposed generalization of the inverted index structure. ... More
Super-resolution of spatiotemporal event-based imageFeb 07 2018Super-resolution (SR) is a useful technology to generate a high-resolution (HR) visual output from the low-resolution (LR) visual inputs overcoming the physical limitations of the sensors. However, SR has not been applied to enhance the resolution of ... More
From Selective Deep Convolutional Features to Compact Binary Representations for Image RetrievalFeb 07 2018Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors. Taking a different ... More
ShakeDrop regularizationFeb 07 2018This paper proposes a powerful regularization method named ShakeDrop regularization. ShakeDrop is inspired by Shake-Shake regularization that decreases error rates by disturbing learning. While Shake-Shake can be applied to only ResNeXt which has multiple ... More
SlideRunner - A Tool for Massive Cell Annotations in Whole Slide ImagesFeb 07 2018Large-scale image data such as digital whole-slide histology images pose a challenging task at annotation software solutions. Today, a number of good solutions with varying scopes exist. For cell annotation, however, we find that many do not match the ... More
Outlier Detection for Robust Multi-dimensional ScalingFeb 07 2018Multi-dimensional scaling (MDS) plays a central role in data-exploration, dimensionality reduction and visualization. State-of-the-art MDS algorithms are not robust to outliers, yielding significant errors in the embedding even when only a handful of ... More
MiMatrix: A Massively Distributed Deep Learning Framework on a Petascale High-density Heterogeneous ClusterFeb 07 2018In this paper, we present a co-designed petascale high-density GPU cluster to expedite distributed deep learning training with synchronous Stochastic Gradient Descent~(SSGD). This architecture of our heterogeneous cluster is inspired by Harvard architecture. ... More
Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial NetsFeb 07 2018Currently, Segmentation of bitewing radiograpy images is a very challenging task. The focus of the study is to segment it into caries, enamel, dentin, pulp, crowns, restoration and root canal treatments. The main method of semantic segmentation of bitewing ... More
Self-Supervised Video Hashing with Hierarchical Binary Auto-encoderFeb 07 2018Existing video hash functions are built on three isolated stages: frame pooling, relaxed learning, and binarization, which have not adequately explored the temporal order of video frames in a joint binary optimization model, resulting in severe information ... More
A comprehensive review of 3D point cloud descriptorsFeb 07 2018The introduction of inexpensive 3D data acquisition devices has promisingly facilitated the wide availability and popularity of 3D point cloud, which attracts more attention on the effective extraction of novel 3D point cloud descriptors for accurate ... More
Spectral Image Visualization Using Generative Adversarial NetworksFeb 07 2018Spectral images captured by satellites and radio-telescopes are analyzed to obtain information about geological compositions distributions, distant asters as well as undersea terrain. Spectral images usually contain tens to hundreds of continuous narrow ... More
Universal Deep Neural Network CompressionFeb 07 2018Compression of deep neural networks (DNNs) for memory- and computation-efficient compact feature representations becomes a critical problem particularly for deployment of DNNs on resource-limited platforms. In this paper, we investigate lossy compression ... More
Efficient Large-Scale Multi-Modal ClassificationFeb 06 2018While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality is discrete, e.g. text, and the other is continuous, e.g. visual representations ... More
Structural Recurrent Neural Network (SRNN) for Group Activity AnalysisFeb 06 2018A group of persons can be analyzed at various semantic levels such as individual actions, their interactions, and the activity of the entire group. In this paper, we propose a structural recurrent neural network (SRNN) that uses a series of interconnected ... More
A Log-Euclidean and Total Variation based Variational Framework for Computational SonographyFeb 06 2018We propose a spatial compounding technique and variational framework to improve 3D ultrasound image quality by compositing multiple ultrasound volumes acquired from different probe orientations. In the composite volume, instead of intensity values, we ... More
Multi-Temporal Land Cover Classification with Sequential Recurrent EncodersFeb 06 2018Earth observation (EO) sensors deliver data with daily or weekly temporal resolution. Most land use and land cover (LULC) approaches, however, expect cloud-free and mono-temporal observations. The increasing temporal capabilities of today's sensors enables ... More
Multispectral Compressive Imaging Strategies using Fabry-Pérot Filtered SensorsFeb 06 2018This paper introduces two acquisition device architectures for multispectral compressive imaging. Unlike most existing methods, the proposed computational imaging techniques do not include any dispersive element, as they use a dedicated sensor which integrates ... More
DeepTravel: a Neural Network Based Travel Time Estimation Model with Auxiliary SupervisionFeb 06 2018Estimating the travel time of a path is of great importance to smart urban mobility. Existing approaches are either based on estimating the time cost of each road segment which are not able to capture many cross-segment complex factors, or designed heuristically ... More
Orthogonally Regularized Deep Networks For Image Super-resolutionFeb 06 2018Deep learning methods, in particular trained Convolutional Neural Networks (CNNs) have recently been shown to produce compelling state-of-the-art results for single image Super-Resolution (SR). Invariably, a CNN is learned to map the low resolution (LR) ... More
Multimodal Image Captioning for Marketing AnalysisFeb 06 2018Automatically captioning images with natural language sentences is an important research topic. State of the art models are able to produce human-like sentences. These models typically describe the depicted scene as a whole and do not target specific ... More
Attribute-Guided Network for Cross-Modal Zero-Shot HashingFeb 06 2018Zero-Shot Hashing aims at learning a hashing model that is trained only by instances from seen categories but can generate well to those of unseen categories. Typically, it is achieved by utilizing a semantic embedding space to transfer knowledge from ... More
The steerable graph Laplacian and its application to filtering image data-setsFeb 06 2018In recent years, improvements in various scientific image acquisition techniques gave rise to the need for adaptive processing methods aimed for large data-sets corrupted by noise and deformations. In this work, we consider data-sets of images sampled ... More
Learning Image Representations by Completing Damaged Jigsaw PuzzlesFeb 06 2018In this paper, we explore methods of complicating self-supervised tasks for representation learning. That is, we do severe damage to data and encourage a network to recover them. First, we complicate each of three powerful self-supervised task candidates: ... More
Every Smile is Unique: Landmark-Guided Diverse Smile GenerationFeb 06 2018Each smile is unique: one person surely smiles in different ways (e.g., closing/opening the eyes or mouth). Given one input image of a neutral face, can we generate multiple smile videos with distinctive characteristics? To tackle this one-to-many video ... More
Fast Piecewise-Affine Motion Estimation Without SegmentationFeb 06 2018Current algorithmic approaches for piecewise affine motion estimation are based on alternating motion segmentation and estimation. We propose a new method to estimate piecewise affine motion fields directly without intermediate segmentation. To this end, ... More
Conformal Parametrisation of Loxodromes by Triples of CirclesFeb 06 2018We provide a parametrisation of a loxodrome by three specially arranged cycles. The parametrisation is covariant under fractional linear transformations of the complex plane and naturally encodes conformal properties of loxodromes. Selected geometrical ... More
An Occluded Stacked Hourglass Approach to Facial Landmark Localization and Occlusion EstimationFeb 05 2018A key step to driver safety is to observe the driver's activities with the face being a key step in this process to extracting information such as head pose, blink rate, yawns, talking to passenger which can then help derive higher level information such ... More
Regularized Evolution for Image Classifier Architecture SearchFeb 05 2018Feb 06 2018The effort devoted to hand-crafting image classifiers has motivated the use of architecture search to discover them automatically. Reinforcement learning and evolution have both shown promise for this purpose. This study employs a regularized version ... More
3D non-rigid registration using color: Color Coherent Point DriftFeb 05 2018Research into object deformations using computer vision techniques has been under intense study in recent years. A widely used technique is 3D non-rigid registration to estimate the transformation between two instances of a deforming structure. Despite ... More
Image restoration with generalized Gaussian mixture model patch priorsFeb 05 2018Patch priors have became an important component of image restoration. A powerful approach in this category of restoration algorithms is the popular Expected Patch Log-likelihood (EPLL) algorithm. EPLL uses a Gaussian mixture model (GMM) prior learned ... More
Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision SurfacesFeb 05 2018Both neural networks and decision trees are popular machine learning methods and are widely used to solve problems from diverse domains. These two classifiers are commonly used base classifiers in an ensemble framework. In this paper, we first present ... More
No Modes left behind: Capturing the data distribution effectively using GANsFeb 02 2018Generative adversarial networks (GANs) while being very versatile in realistic image synthesis, still are sensitive to the input distribution. Given a set of data that has an imbalance in the distribution, the networks are susceptible to missing modes ... More
Learning Attribute Representation for Human Activity RecognitionFeb 02 2018Attribute representations became relevant in image recognition and word spotting, providing support under the presence of unbalance and disjoint datasets. However, for human activity recognition using sequential data from on-body sensors, human-labeled ... More
Deep Convolutional Neural Networks for Breast Cancer Histology Image AnalysisFeb 02 2018Breast cancer is one of the main causes of cancer death worldwide. Early diagnostics significantly increases the chances of correct treatment and survival, but this process is tedious and often leads to a disagreement between pathologists. Computer-aided ... More
Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from VideosFeb 02 2018Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analysis such as in health care applications. Despite their importance, it is ... More
Convolutional neural network-based regression for depth prediction in digital holographyFeb 02 2018Digital holography enables us to reconstruct objects in three-dimensional space from holograms captured by an imaging device. For the reconstruction, we need to know the depth position of the recoded object in advance. In this study, we propose depth ... More
When can $l_p$-norm objective functions be minimized via graph cuts?Feb 02 2018Techniques based on minimal graph cuts have become a standard tool for solving combinatorial optimization problems arising in image processing and computer vision applications. These techniques can be used to minimize objective functions written as the ... More
A New Registration Approach for Dynamic Analysis of Calcium Signals in OrgansFeb 01 2018Wing disc pouches of fruit flies are a powerful genetic model for studying physiological intercellular calcium ($Ca^{2+}$) signals for dynamic analysis of cell signaling in organ development and disease studies. A key to analyzing spatial-temporal patterns ... More
HoloFace: Augmenting Human-to-Human Interactions on HoloLensFeb 01 2018We present HoloFace, an open-source framework for face alignment, head pose estimation and facial attribute retrieval for Microsoft HoloLens. HoloFace implements two state-of-the-art face alignment methods which can be used interchangeably: one running ... More
Improved Image Segmentation via Cost Minimization of Multiple HypothesesJan 31 2018Image segmentation is an important component of many image understanding systems. It aims to group pixels in a spatially and perceptually coherent manner. Typically, these algorithms have a collection of parameters that control the degree of over-segmentation ... More
Dynamics of Driver's Gaze: Explorations in Behavior Modeling & Maneuver PredictionJan 31 2018The study and modeling of driver's gaze dynamics is important because, if and how the driver is monitoring the driving environment is vital for driver assistance in manual mode, for take-over requests in highly automated mode and for semantic perception ... More
Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in Convolutional NetworksJan 31 2018While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this work we introduce a suite of tools that exploit sparsity in both the feature ... More
Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural NetworksJan 31 2018Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations. The key idea is to rank the filters based on a certain criterion (say, $l_1$-norm, average percentage ... More
An Iterative Spanning Forest Framework for Superpixel SegmentationJan 30 2018Superpixel segmentation has become an important research problem in image processing. In this paper, we propose an Iterative Spanning Forest (ISF) framework, based on sequences of Image Foresting Transforms, where one can choose i) a seed sampling strategy, ... More
Parallel Tracking and VerifyingJan 30 2018Being intensively studied, visual object tracking has witnessed great advances in either speed (e.g., with correlation filters) or accuracy (e.g., with deep features). Real-time and high accuracy tracking algorithms, however, remain scarce. In this paper ... More
Deep Learning based Retinal OCT SegmentationJan 29 2018Our objective is to evaluate the efficacy of methods that use deep learning (DL) for the automatic fine-grained segmentation of optical coherence tomography (OCT) images of the retina. OCT images from 10 patients with mild non-proliferative diabetic retinopathy ... More
Fekete-Szego Inequality for Analytic and Bi-univalent Functions Subordinate to Chebyshev PolynomialsJan 29 2018In the present paper, a new subclass of analytic and bi-univalent functions by means of Chebyshev polynomials is introduced. Certain coefficient bounds for functions belong to this subclass are obtained. Furthermore, the Fekete-Szego problem in this subclass ... More
TernaryNet: Faster Deep Model Inference without GPUs for Medical 3D Segmentation using Sparse and Binary ConvolutionsJan 29 2018Deep convolutional neural networks (DCNN) are currently ubiquitous in medical imaging. While their versatility and high quality results for common image analysis tasks including segmentation, localisation and prediction is astonishing, the large representational ... More
CosFace: Large Margin Cosine Loss for Deep Face RecognitionJan 29 2018Face recognition has achieved revolutionary advancement owing to the advancement of the deep convolutional neural network (CNN). The central task of face recognition, including face verification and identification, involves face feature discrimination. ... More
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional NetworksJan 29 2018It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent ... More
Square Sierpiński carpets and Lattès mapsJan 29 2018Jan 30 2018We prove that every quasisymmetric homeomorphism of a standard square Sierpi\'nski carpet $S_p$, $p\ge 3$ odd, is an isometry. This strengthens and completes earlier work by the authors. We also show that a similar conclusion holds for quasisymmetries ... More
Malaria Detection Using Image Processing and Machine LearningJan 28 2018Malaria is mosquito-borne blood disease caused by parasites of the genus Plasmodium. Conventional diagnostic tool for malaria is the examination of stained blood cell of patient in microscope. The blood to be tested is placed in a slide and is observed ... More
A Generative Approach to Zero-Shot and Few-Shot Action RecognitionJan 27 2018We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data. Our approach is based on modeling each action class using a probability distribution whose parameters are functions ... More
KRISM --- Krylov Subspace-based Optical Computing of Hyperspectral ImagesJan 26 2018Low-rank modeling of hyperspectral images has found extensive use in numerous inference tasks. In this paper, we present an adaptive imaging technique that optically computes a low-rank representation of the scene's hyperspectral image. We make significant ... More
Weakly Supervised Object Detection with Pointwise Mutual InformationJan 26 2018In this work a novel approach for weakly supervised object detection that incorporates pointwise mutual information is presented. A fully convolutional neural network architecture is applied in which the network learns one filter per object class. The ... More
Generative Adversarial Networks using Adaptive ConvolutionJan 25 2018Most existing GANs architectures that generate images use transposed convolution or resize-convolution as their upsampling algorithm from lower to higher resolution feature maps in the generator. We argue that this kind of fixed operation is problematic ... More
DeepPap: Deep Convolutional Networks for Cervical Cell ClassificationJan 25 2018Automation-assisted cervical screening via Pap smear or liquid-based cytology (LBC) is a highly effective cell imaging based cancer detection tool, where cells are partitioned into "abnormal" and "normal" categories. However, the success of most traditional ... More
Accurate Weakly Supervised Deep Lesion Segmentation on CT Scans: Self-Paced 3D Mask Generation from RECISTJan 25 2018Volumetric lesion segmentation via medical imaging is a powerful means to precisely assess multiple time-point lesion/tumor changes. Because manual 3D segmentation is prohibitively time consuming and requires radiological experience, current practices ... More
Deep LOGISMOS: Deep Learning Graph-based 3D Segmentation of Pancreatic Tumors on CT scansJan 25 2018This paper reports Deep LOGISMOS approach to 3D tumor segmentation by incorporating boundary information derived from deep contextual learning to LOGISMOS - layered optimal graph image segmentation of multiple objects and surfaces. Accurate and reliable ... More
Unmixing urban hyperspectral imagery with a Gaussian mixture model on endmember variabilityJan 25 2018In this paper, we model a pixel as a linear combination of endmembers sampled from probability distributions of Gaussian mixture models (GMM). The parameters of the GMM distributions are estimated using spectral libraries. Abundances are estimated based ... More
Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual AnnotationJan 25 2018Image segmentation is a fundamental problem in medical image analysis. In recent years, deep neural networks achieve impressive performances on many medical image segmentation tasks by supervised learning on large manually annotated data. However, expert ... More
Convolutional Invasion and Expansion Networks for Tumor Growth PredictionJan 25 2018Tumor growth is associated with cell invasion and mass-effect, which are traditionally formulated by mathematical models, namely reaction-diffusion equations and biomechanics. Such models can be personalized based on clinical measurements to build the ... More
Identifying Corresponding Patches in SAR and Optical Images with a Pseudo-Siamese CNNJan 25 2018In this letter, we propose a pseudo-siamese convolutional neural network (CNN) architecture that enables to solve the task of identifying corresponding patches in very-high-resolution (VHR) optical and synthetic aperture radar (SAR) remote sensing imagery. ... More
Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose OptimisationJan 25 2018Reconstructing dense, volumetric models of real-world 3D scenes is important for many tasks, but capturing large scenes can take significant time, and the risk of transient changes to the scene goes up as the capture time increases. These are good reasons ... More
A Tutorial on Modeling and Inference in Undirected Graphical Models for Hyperspectral Image AnalysisJan 25 2018Undirected graphical models have been successfully used to jointly model the spatial and the spectral dependencies in earth observing hyperspectral images. They produce less noisy, smooth, and spatially coherent land cover maps and give top accuracies ... More
When Vehicles See Pedestrians with Phones:A Multi-Cue Framework for Recognizing Phone-based Activities of PedestriansJan 24 2018The intelligent vehicle community has devoted considerable efforts to model driver behavior, and in particular to detect and overcome driver distraction in an effort to reduce accidents caused by driver negligence. However, as the domain increasingly ... More