Latest in

total 15584took 0.10s
Deep CNN-based Speech Balloon Detection and Segmentation for Comic BooksFeb 21 2019We develop a method for the automated detection and segmentation of speech balloons in comic books, including their carrier and tails. Our method is based on a deep convolutional neural network that was trained on annotated pages of the Graphic Narrative ... More
Domain Partitioning NetworkFeb 21 2019Standard adversarial training involves two agents, namely a generator and a discriminator, playing a mini-max game. However, even if the players converge to an equilibrium, the generator may only recover a part of the target data distribution, in a situation ... More
A Joint Deep Learning Approach for Automated Liver and Tumor SegmentationFeb 21 2019Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer in adults, and the most common cause of death of people suffering from cirrhosis. The segmentation of liver lesions in CT images allows assessment of tumor load, treatment ... More
Adversarial Augmentation for Enhancing Classification of Mammography ImagesFeb 20 2019Supervised deep learning relies on the assumption that enough training data is available, which presents a problem for its application to several fields, like medical imaging. On the example of a binary image classification task (breast cancer recognition), ... More
Knowledge-based Analysis for Mortality Prediction from CT ImagesFeb 20 2019Recent studies have highlighted the high correlation between cardiovascular diseases (CVD) and lung cancer, and both are associated with significant morbidity and mortality. Low-Dose CT (LCDT) scans have led to significant improvements in the accuracy ... More
On the effect of age perception biases for real age regressionFeb 20 2019Automatic age estimation from facial images represents an important task in computer vision. This paper analyses the effect of gender, age, ethnic, makeup and expression attributes of faces as sources of bias to improve deep apparent age prediction. Following ... More
Dynamic Cell Imaging in PET with Optimal Transport RegularizationFeb 20 2019We propose a novel dynamic image reconstruction method from PET listmode data that could be particularly suited to tracking single or small numbers of cells. In contrast to conventional PET reconstruction the proposed method combines the information from ... More
Dense 3D Visual Mapping via Semantic SimplificationFeb 20 2019Dense 3D visual mapping estimates as many as possible pixel depths, for each image. This results in very dense point clouds that often contain redundant and noisy information, especially for surfaces that are roughly planar, for instance, the ground or ... More
DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN AcceleratorsFeb 20 2019The convolutional neural network (CNN) has become a state-of-the-art method for several artificial intelligence domains in recent years. The increasingly complex CNN models are both computation-bound and I/O-bound. FPGA-based accelerators driven by custom ... More
Accurate Automatic Segmentation of Amygdala Subnuclei and Modeling of Uncertainty via Bayesian Fully Convolutional Neural NetworkFeb 19 2019Recent advances in deep learning have improved the segmentation accuracy of subcortical brain structures, which would be useful in neuroimaging studies of many neurological disorders. However, most of the previous deep learning work does not investigate ... More
Evaluating the Effectiveness of Automated Identity Masking (AIM) Methods with Human PerceptionFeb 19 2019Face de-identification algorithms have been developed in response to the prevalent use of public video recordings and surveillance cameras. Here, we evaluated the success of identity masking in the context of monitoring drivers as they actively operate ... More
WIDER Face and Pedestrian Challenge 2018: Methods and ResultsFeb 19 2019This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurate association of identities. It comprises of three tracks: (i) WIDER Face ... More
Democratisation of Usable Machine Learning in Computer VisionFeb 18 2019Many industries are now investing heavily in data science and automation to replace manual tasks and/or to help with decision making, especially in the realm of leveraging computer vision to automate many monitoring, inspection, and surveillance tasks. ... More
DIViS: Domain Invariant Visual Servoing for Collision-Free Goal ReachingFeb 18 2019Robots should understand both semantics and physics to be functional in the real world. While robot platforms provide means for interacting with the physical world they cannot autonomously acquire object-level semantics without needing human. In this ... More
Multi-layer Depth and Epipolar Feature Transformers for 3D Scene ReconstructionFeb 18 2019We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered, multi-layer ... More
HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image ClassificationFeb 18 2019Hyperspectral image (HSI) classification is widely used for the analysis of remotely sensed images. Hyperspectral imagery includes varying bands of images. Convolutional Neural Network (CNN) is one of the most frequently used deep learning based methods ... More
HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image ClassificationFeb 18 2019Feb 19 2019Hyperspectral image (HSI) classification is widely used for the analysis of remotely sensed images. Hyperspectral imagery includes varying bands of images. Convolutional Neural Network (CNN) is one of the most frequently used deep learning based methods ... More
Generative Adversarial Networks Synthesize Realistic OCT Images of the RetinaFeb 18 2019We report, to our knowledge, the first end-to-end application of Generative Adversarial Networks (GANs) towards the synthesis of Optical Coherence Tomography (OCT) images of the retina. Generative models have gained recent attention for the increasingly ... More
Contextual Encoder-Decoder Network for Visual Saliency PredictionFeb 18 2019Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted and augmented ... More
Object Recognition under Multifarious Conditions: A Reliability Analysis and A Feature Similarity-based Performance EstimationFeb 18 2019In this paper, we investigate the reliability of online recognition platforms, Amazon Rekognition and Microsoft Azure, with respect to changes in background, acquisition device, and object orientation. We focus on platforms that are commonly used by the ... More
Decomposing multispectral face images into diffuse and specular shading and biophysical parametersFeb 18 2019We propose a novel biophysical and dichromatic reflectance model that efficiently characterises spectral skin reflectance. We show how to fit the model to multispectral face images enabling high quality estimation of diffuse and specular shading as well ... More
MetaGrasp: Data Efficient Grasping by Affordance Interpreter NetworkFeb 18 2019Data-driven approach for grasping shows significant advance recently. But these approaches usually require much training data. To increase the efficiency of grasping data collection, this paper presents a novel grasp training system including the whole ... More
LocalNorm: Robust Image Classification through Dynamically Regularized NormalizationFeb 18 2019While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation. Here, we describe a variant of Batch Normalization, LocalNorm, that regularizes ... More
LocalNorm: Robust Image Classification through Dynamically Regularized NormalizationFeb 18 2019Feb 19 2019While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation. Here, we describe a variant of Batch Normalization, LocalNorm, that regularizes ... More
Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologyFeb 18 2019Stain variation is a phenomenon observed when distinct pathology laboratories stain tissue slides that exhibit similar but not identical color appearance. Due to this color shift between laboratories, convolutional neural networks (CNNs) trained with ... More
Structural Recurrent Neural Network for Traffic Speed PredictionFeb 18 2019Deep neural networks have recently demonstrated the traffic prediction capability with the time series data obtained by sensors mounted on road segments. However, capturing spatio-temporal features of the traffic data often requires a significant number ... More
Persistent entropy: a scale-invariant topological statistic for analyzing cell arrangementsFeb 18 2019In this work, we explain how to use computational topology for detecting differences in the geometrical distribution of cells forming epithelial tissues. In particular, we extract topological information from images using persistent homology and summarize ... More
SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI ReconstructionFeb 18 2019Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI). However most recent works lack exploration of structure information of MRI images that is crucial for clinical diagnosis. ... More
2017 Robotic Instrument Segmentation ChallengeFeb 18 2019Feb 21 2019In mainstream computer vision and machine learning, public datasets such as ImageNet, COCO and KITTI have helped drive enormous improvements by enabling researchers to understand the strengths and limitations of different algorithms via performance comparison. ... More
2017 Robotic Instrument Segmentation ChallengeFeb 18 2019In mainstream computer vision and machine learning, public datasets such as ImageNet, COCO and KITTI have helped drive enormous improvements by enabling researchers to understand the strengths and limitations of different algorithms via performance comparison. ... More
On the slit motion obeying chordal Komatu-Loewner equation with finite explosion timeFeb 18 2019This paper studies the behavior of solutions near the explosion time to the chordal Komatu-Loewner equation for slits, motivated by the preceding studies by Bauer and Friedrich (2008) and by Chen and Fukushima (2018). The solution to this equation represents ... More
Speeding up convolutional networks pruning with coarse rankingFeb 18 2019Channel-based pruning has achieved significant successes in accelerating deep convolutional neural network, whose pipeline is an iterative three-step procedure: ranking, pruning and fine-tuning. However, this iterative procedure is computationally expensive. ... More
Periocular Recognition in the Wild with Orthogonal Combination of Local Binary Coded Pattern in Dual-stream Convolutional Neural NetworkFeb 18 2019In spite of the advancements made in the periocular recognition, the dataset and periocular recognition in the wild remains a challenge. In this paper, we propose a multilayer fusion approach by means of a pair of shared parameters (dual-stream) convolutional ... More
Single-shot Channel Pruning Based on Alternating Direction Method of MultipliersFeb 18 2019Channel pruning has been identified as an effective approach to constructing efficient network structures. Its typical pipeline requires iterative pruning and fine-tuning. In this work, we propose a novel single-shot channel pruning approach based on ... More
PointIT: A Fast Tracking Framework Based on 3D Instance SegmentationFeb 18 2019Recently most popular tracking frameworks focus on 2D image sequences. They seldom track the 3D object in point clouds. In this paper, we propose PointIT, a fast, simple tracking method based on 3D on-road instance segmentation. Firstly, we transform ... More
Automatic Segmentation of Pulmonary Lobes Using a Progressive Dense V-NetworkFeb 18 2019Reliable and automatic segmentation of lung lobes is important for diagnosis, assessment, and quantification of pulmonary diseases. The existing techniques are prohibitively slow, undesirably rely on prior (airway/vessel) segmentation, and/or require ... More
Accurate Segmentation of Dermoscopic Images based on Local Binary Pattern ClusteringFeb 17 2019Feb 19 2019Segmentation is a key stage in dermoscopic image processing, where the accuracy of the border line that defines skin lesions is of utmost importance for subsequent algorithms (e.g., classification) and computer-aided early diagnosis of serious medical ... More
Accurate Segmentation of Dermoscopic Images based on Local Binary Pattern ClusteringFeb 17 2019Feb 20 2019Segmentation is a key stage in dermoscopic image processing, where the accuracy of the border line that defines skin lesions is of utmost importance for subsequent algorithms (e.g., classification) and computer-aided early diagnosis of serious medical ... More
Accurate Segmentation of Dermoscopic Images based on Local Binary Pattern ClusteringFeb 17 2019Segmentation is a key stage in dermoscopic image processing, where the accuracy of the border line that defines skin lesions is of utmost importance for subsequent algorithms (e.g., classification) and computer-aided early diagnosis of serious medical ... More
Semantically Interpretable and Controllable Filter SetsFeb 17 2019In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion. Each semantic filter learns a visually interpretable local structure in conjunction with other filters. ... More
Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted StacksFeb 17 2019Popular deep domain adaptation methods have mainly focused on learning discriminative and domain-invariant features of different domains. In this work, we present a novel approach inspired by human cognitive processes where receptive fields learned from ... More
PIXOR: Real-time 3D Object Detection from Point CloudsFeb 17 2019We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Computation speed is critical as detection is a necessary component for safety. Existing approaches are, however, expensive in computation ... More
Automated Detection of Regions of Interest for Brain Perfusion MR ImagesFeb 17 2019Images with abnormal brain anatomy produce problems for automatic segmentation techniques, and as a result poor ROI detection affects both quantitative measurements and visual assessment of perfusion data. This paper presents a new approach for fully ... More
Attention-Based Prototypical Learning Towards Interpretable, Confident and Robust Deep Neural NetworksFeb 17 2019We propose a new framework for prototypical learning that bases decision-making on few relevant examples that we call prototypes. Our framework utilizes an attention mechanism that relates the encoded representations to determine the prototypes. This ... More
Exploiting Unlabeled Data in CNNs by Self-supervised Learning to RankFeb 17 2019For many applications the collection of labeled data is expensive laborious. Exploitation of unlabeled data during training is thus a long pursued objective of machine learning. Self-supervised learning addresses this by positing an auxiliary task (different, ... More
Coefficient bounds for close-to-convex functions associated with vertical strip domainFeb 17 2019By considering a certain univalent function in the open unit disk U, that maps U onto a strip domain, we introduce a new class of analytic and close-to-convex functions by means of a certain non-homogeneous Cauchy-Euler-type differential equation. We ... More
Fully-Featured Attribute TransferFeb 17 2019Image attribute transfer aims to change an input image to a target one with expected attributes, which has received significant attention in recent years. However, most of the existing methods lack the ability to de-correlate the target attributes and ... More
Exploring Stereovision-Based 3-D Scene Reconstruction for Augmented RealityFeb 17 2019Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach ... More
Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good GeneralizationFeb 17 2019Image colorization achieves more and more realistic results with the increasing computation power of recent deep learning techniques. It becomes more difficult to identify the fake colorized images by human eyes. In this work, we propose a novel forensic ... More
LapEPI-Net: A Laplacian Pyramid EPI structure for Learning-based Dense Light Field ReconstructionFeb 17 2019For dense sampled light field (LF) reconstruction problem, existing approaches focus on a depth-free framework to achieve non-Lambertian performance. However, they trap in the trade-off "either aliasing or blurring" problem, i.e., pre-filtering the aliasing ... More
Fast Pedestrian Detection based on T-CENTRISTFeb 17 2019Pedestrian detection is a research hotspot and a difficult issue in the computer vision such as the Intelligent Surveillance System (ISS), the Intelligent Transport System (ITS), robotics, and automotive safety. However, the human body's position, angle, ... More
Using Persistent Homology to Quantify a Diurnal Cycle in Hurricane FelixFeb 17 2019The diurnal cycle of tropical cyclones (TCs) is a daily cycle in clouds that appears in satellite images and may have implications for TC structure and intensity. The diurnal pattern can be seen in infrared (IR) satellite imagery as cyclical pulses in ... More
Online PCB Defect Detector On A New PCB Defect DatasetFeb 17 2019Previous works for PCB defect detection based on image difference and image processing techniques have already achieved promising performance. However, they sometimes fall short because of the unaccounted defect patterns or over-sensitivity about some ... More
Structured Group Local Sparse TrackerFeb 17 2019Sparse representation is considered as a viable solution to visual tracking. In this paper, we propose a structured group local sparse tracker (SGLST), which exploits local patches inside target candidates in the particle filter framework. Unlike the ... More
Self-supervised Visual Feature Learning with Deep Neural Networks: A SurveyFeb 16 2019Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating ... More
Deep Convolutional Sum-Product Networks for Probabilistic Image RepresentationsFeb 16 2019Sum-Product Networks (SPNs) are hierarchical probabilistic graphical models capable of fast and exact inference. Applications of SPNs to real-world data such as large image datasets has been fairly limited in previous literature. We introduce Convolutional ... More
BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image UnderstandingFeb 16 2019This paper presents a new large-scale multi-label Sentinel-2 benchmark archive, named BigEarthNet. Our archive consists of 590,326 Sentinel-2 image patches, each of which has 10, 20 and 60 meter image bands associated to the pixel sizes of 120x120, 60x60 ... More
LISA: a MATLAB package for Longitudinal Image Sequence AnalysisFeb 16 2019Large sequences of images (or movies) can now be obtained on an unprecedented scale, which poses fundamental challenges to the existing image analysis techniques. The challenges include heterogeneity, (automatic) alignment, multiple comparisons, potential ... More
Atlas-based automated detection of swim bladder in Medaka embryoFeb 16 2019Fish embryo models are increasingly being used both for the assessment of chemicals efficacy and potential toxicity. This article proposes a methodology to automatically detect the swim bladder on 2D images of Medaka fish embryos seen either in dorsal ... More
Semi-supervised Learning on Graph with an Alternating Diffusion ProcessFeb 16 2019Graph-based semi-supervised learning usually involves two separate stages, constructing an affinity graph and then propagating labels for transductive inference on the graph. It is suboptimal to solve them independently, as the correlation between the ... More
DC-Al GAN: Pseudoprogression and True Tumor Progression of Glioblastoma multiform Image Classification Based On DCGAN and AlexnetFeb 16 2019Glioblastoma multiform (GBM) is a kind of head tumor with an extraordinarily complex treatment process. The survival period is typically 14-16 months, and the 2 year survival rate is approximately 26%-33%. The clinical treatment strategies for the pseudoprogression ... More
Local Fourier Slice PhotographyFeb 16 2019Light field cameras provide intriguing possibilities, such as post-capture refocus or the ability to look behind an object. This comes, however, at the price of significant storage requirements. Compression techniques can be used to reduce these but refocusing ... More
Deep Learning for Image Super-resolution: A SurveyFeb 16 2019Image Super-Resolution (SR) is an important class of image processing techniques to enhance the resolution of images and videos in computer vision. Recent years have witnessed remarkable progress of image super-resolution using deep learning techniques. ... More
RES-SE-NET: Boosting Performance of Resnets by Enhancing Bridge-connectionsFeb 16 2019One of the ways to train deep neural networks effectively is to use residual connections. Residual connections can be classified as being either identity connections or bridge-connections with a reshaping convolution. Empirical observations on CIFAR-10 ... More
Skin Lesion Segmentation and Classification with Deep Learning SystemFeb 16 2019Melanoma is one of the ten most common cancers in the US. Early detection is crucial for survival, but often the cancer is diagnosed in the fatal stage. Deep learning has the potential to improve cancer detection rates, but its applicability to melanoma ... More
Min-Entropy Latent Model for Weakly Supervised Object DetectionFeb 16 2019Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors. The inconsistency between the weak supervision and learning objectives ... More
$\mathcal{R}^2$-CNN: Fast Tiny Object Detection in Large-scale Remote Sensing ImagesFeb 16 2019Recently, convolutional neural network has brought impressive improvements for object detection. However, detecting tiny objects in large-scale remote sensing images still remains challenging. Firstly, the extreme large input size makes existing object ... More
GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face ReconstructionFeb 15 2019In the past few years, a lot of work has been done towards reconstructing the 3D facial structure from single images by capitalizing on the power of Deep Convolutional Neural Networks (DCNNs). In the most recent works, differentiable renderers were employed ... More
DeepFault: Fault Localization for Deep Neural NetworksFeb 15 2019Deep Neural Networks (DNNs) are increasingly deployed in safety-critical applications including autonomous vehicles and medical diagnostics. To reduce the residual risk for unexpected DNN behaviour and provide evidence for their trustworthy operation, ... More
One-box conditions for Carleson measures for the Dirichlet spaceFeb 15 2019We give a simple proof of the fact that a finite measure $\mu$ on the unit disk is a Carleson measure for the Dirichlet space if it satisfies the Carleson one-box condition $\mu(S(I))=O(\phi(|I|))$, where $\phi:(0,2\pi]\to(0,\infty)$ is an increasing ... More
Street Scene: A new dataset and evaluation protocol for video anomaly detectionFeb 15 2019Progress in video anomaly detection research is currently slowed by small datasets that lack a wide variety of activities as well as flawed evaluation criteria. This paper aims to help move this research effort forward by introducing a large and varied ... More
Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship DetectionFeb 15 2019Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply supervised ... More
Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning NetworkFeb 15 2019With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data. In this letter, we present a novel content-based remote sensing image retrieval method based ... More
Unsupervised shape and motion analysis of 3822 cardiac 4D MRIs of UK BiobankFeb 15 2019We perform unsupervised analysis of image-derived shape and motion features extracted from 3822 cardiac 4D MRIs of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 ... More
Network Offloading Policies for Cloud Robotics: a Learning-based ApproachFeb 15 2019Today's robotic systems are increasingly turning to computationally expensive models such as deep neural networks (DNNs) for tasks like localization, perception, planning, and object detection. However, resource-constrained robots, like low-power drones, ... More
Lightweight Feature Fusion Network for Single Image Super-ResolutionFeb 15 2019Single image super-resolution(SISR) has witnessed great progress as convolutional neural network(CNN) gets deeper and wider. However, enormous parameters hinder its application to real world problems. In this letter, We propose a lightweight feature fusion ... More
Lipschitz Generative Adversarial NetsFeb 15 2019In this paper we study the convergence of generative adversarial networks (GANs) from the perspective of the informativeness of the gradient of the optimal discriminative function. We show that GANs without restriction on the discriminative function space ... More
Breaking the Spatio-Angular Trade-off for Light Field Super-Resolution via LSTM Modelling on Epipolar Plane ImagesFeb 15 2019Light-field cameras (LFC) have received increasing attention due to their wide-spread applications. However, current LFCs suffer from the well-known spatio-angular trade-off, which is considered as an inherent and fundamental limit for LFC designs. In ... More
Cycle-Consistency for Robust Visual Question AnsweringFeb 15 2019Despite significant progress in Visual Question Answering over the years, robustness of today's VQA models leave much to be desired. We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that state-of-the-art VQA models ... More
Massively Parallel Benders Decomposition for Correlation ClusteringFeb 15 2019We tackle the problem of graph partitioning for image segmentation using correlation clustering (CC), which we treat as an integer linear program (ILP). We reformulate optimization in the ILP so as to admit efficient optimization via Benders decomposition, ... More
TMAV: Temporal Motionless Analysis of Video using CNN in MPSoCFeb 15 2019Feb 18 2019Analyzing video for traffic categorization is an important pillar of Intelligent Transport Systems. However, it is difficult to analyze and predict traffic based on image frames because the representation of each frame may vary significantly within a ... More
Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future DirectionsFeb 15 2019Medical Image Analysis is currently experiencing a paradigm shift due to Deep Learning. This technology has recently attracted so much interest of the Medical Imaging community that it led to a specialized conference in `Medical Imaging with Deep Learning' ... More
Improving Catheter Segmentation & Localization in 3D Cardiac Ultrasound Using Direction-Fused FCNFeb 14 2019Fast and accurate catheter detection in cardiac catheterization using harmless 3D ultrasound (US) can improve the efficiency and outcome of the intervention. However, the low image quality of US requires extra training for sonographers to localize the ... More
Learning to Control Self-Assembling Morphologies: A Study of Generalization via ModularityFeb 14 2019Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigates a modular co-evolution strategy: a collection of primitive agents learns ... More
Unsupervised Visuomotor Control through Distributional Planning NetworksFeb 14 2019While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of ... More
Deep Generative Endmember Modeling: An Application to Unsupervised Spectral UnmixingFeb 14 2019Endmember (EM) spectral variability can greatly impact the performance of standard hyperspectral image analysis algorithms. Extended parametric models have been successfully applied to account for the EM spectral variability. However, these models still ... More
MultiGrain: a unified image embedding for classes and instancesFeb 14 2019MultiGrain is a network architecture producing compact vector representations that are suited both for image classification and particular object retrieval. It builds on a standard classification trunk. The top of the network produces an embedding containing ... More
Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image ClassificationFeb 14 2019Zero-shot learning (ZSL) is one of the most extreme forms of learning from scarce labeled data. It enables predicting that images belong to classes for which no labeled training instances are available. In this paper, we present a new ZSL framework that ... More
Exploring Frame Segmentation Networks for Temporal Action LocalizationFeb 14 2019Temporal action localization is an important task of computer vision. Though many methods have been proposed, it still remains an open question how to predict the temporal location of action segments precisely. Most state-of-the-art works train action ... More
Sparse and noisy LiDAR completion with RGB guidance and uncertaintyFeb 14 2019This work proposes a new method to accurately complete sparse LiDAR maps guided by RGB images. For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions. A multitude of applications depend on ... More
Dynamical system based obstacle avoidance via manipulating orthogonal coordinatesFeb 14 2019In this paper, we consider the general problem of obstacle avoidance based on dynamical system. The modulation matrix is developed by introducing orthogonal coordinates, which makes the modulation matrix more reasonable. The new trajectory's direction ... More
Automatic Labeled LiDAR Data Generation based on Precise Human ModelFeb 14 2019Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. However, the performance of these networks strongly depends on the training data. An issue with collecting ... More
Breast Cancer: Model Reconstruction and Image Registration from Segmented Deformed Image using Visual and Force based AnalysisFeb 14 2019Breast lesion localization using tactile imaging is a new and developing direction in medical science. To achieve the goal, proper image reconstruction and image registration can be a valuable asset. In this paper, a new approach of the segmentation-based ... More
Deep HVS-IQA Net: Human Visual System Inspired Deep Image Quality Assessment NetworksFeb 14 2019In image quality enhancement processing, it is the most important to predict how humans perceive processed images since human observers are the ultimate receivers of the images. Thus, objective image quality assessment (IQA) methods based on human visual ... More
On instabilities of deep learning in image reconstruction - Does AI come at a cost?Feb 14 2019Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper we demonstrate a crucial phenomenon: deep learning typically yields ... More
Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian DetectionFeb 14 2019Effective fusion of complementary information captured by multi-modal sensors (visible and infrared cameras) enables robust pedestrian detection under various surveillance situations (e.g. daytime and nighttime). In this paper, we present a novel box-level ... More
Computed tomography data collection of the complete human mandible and valid clinical ground truth modelsFeb 14 2019Image-based algorithmic software segmentation is an increasingly important topic in many medical fields. Algorithmic segmentation is used for medical three-dimensional visualization, diagnosis or treatment support, especially in complex medical cases. ... More
3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance SegmentationFeb 14 2019This paper introduces a novel approach for 3D semantic instance segmentation on point clouds. A 3D convolutional neural network called submanifold sparse convolutional network is used to generate semantic predictions and instance embeddings simultaneously. ... More
Long and Short Memory Balancing in Visual Co-Tracking using Q-LearningFeb 14 2019Employing one or more additional classifiers to break the self-learning loop in tracing-by-detection has gained considerable attention. Most of such trackers merely utilize the redundancy to address the accumulating label error in the tracking loop, and ... More
Non-contact photoplethysmogram and instantaneous heart rate estimation from infrared face videoFeb 14 2019Extracting the instantaneous heart rate (iHR) from face videos has been well studied in recent years. It is well known that changes in skin color due to blood flow can be captured using conventional cameras. One of the main limitations of methods that ... More