Latest in

total 32095took 0.11s
Detecting Photoshopped Faces by Scripting PhotoshopJun 13 2019Most malicious photo manipulations are created using standard image editing tools, such as Adobe Photoshop. We present a method for detecting one very popular Photoshop manipulation -- image warping applied to human faces -- using a model trained entirely ... More
The Replica Dataset: A Digital Replica of Indoor SpacesJun 13 2019We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions at room and building scale. Each scene consists of a dense mesh, high-resolution high-dynamic-range (HDR) textures, per-primitive semantic class and instance ... More
Egocentric affordance detection with the one-shot geometry-driven Interaction TensorJun 13 2019In this abstract we describe recent [4,7] and latest work on the determination of affordances in visually perceived 3D scenes. Our method builds on the hypothesis that geometry on its own provides enough information to enable the detection of significant ... More
Unsupervised Image Noise Modeling with Self-Consistent GANJun 13 2019Noise modeling lies in the heart of many image processing tasks. However, existing deep learning methods for noise modeling generally require clean and noisy image pairs for model training; these image pairs are difficult to obtain in many realistic scenarios. ... More
Generating and Exploiting Probabilistic Monocular Depth EstimatesJun 13 2019Despite the remarkable success of modern monocular depth estimation methods, the accuracy achievable from a single image is limited, making it is practically useful to incorporate other sources of depth information. Currently, depth estimation from different ... More
2D Attentional Irregular Scene Text RecognizerJun 13 2019Irregular scene text, which has complex layout in 2D space, is challenging to most previous scene text recognizers. Recently, some irregular scene text recognizers either rectify the irregular text to regular text image with approximate 1D layout or transform ... More
Grid R-CNN Plus: Faster and BetterJun 13 2019Grid R-CNN is a well-performed objection detection framework. It transforms the traditional box offset regression problem into a grid point estimation problem. With the guidance of the grid points, it can obtain high-quality localization results. However, ... More
$c^+$GAN: Complementary Fashion Item RecommendationJun 13 2019We present a conditional generative adversarial model to draw realistic samples from paired fashion clothing distribution and provide real samples to pair with arbitrary fashion units. More concretely, given an image of a shirt, obtained from a fashion ... More
Amur Tiger Re-identification in the WildJun 13 2019Monitoring the population and movements of endangered species is an important task to wildlife conversation. Traditional tagging methods do not scale to large populations, while applying computer vision methods to camera sensor data requires re-identification ... More
An image-driven machine learning approach to kinetic modeling of a discontinuous precipitation reactionJun 13 2019Micrograph quantification is an essential component of several materials science studies. Machine learning methods, in particular convolutional neural networks, have previously demonstrated performance in image recognition tasks across several disciplines ... More
Robust and interpretable blind image denoising via bias-free convolutional neural networksJun 13 2019Deep convolutional networks often append additive constant ("bias") terms to their convolution operations, enabling a richer repertoire of functional mappings. Biases are also used to facilitate training, by subtracting mean response over batches of training ... More
CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training BudgetsJun 13 2019Deep networks are an integral part of the current machine learning paradigm. Their inherent ability to learn complex functional mappings between data and various target variables, while discovering hidden, task-driven features, makes them a powerful technology ... More
Copulas as High-Dimensional Generative Models: Vine Copula AutoencodersJun 12 2019We propose a vine copula autoencoder to construct flexible generative models for high-dimensional distributions in a straightforward three-step procedure. First, an autoencoder compresses the data using a lower dimensional representation. Second, the ... More
Eye Contact Correction using Deep Neural NetworksJun 12 2019In a typical video conferencing setup, it is hard to maintain eye contact during a call since it requires looking into the camera rather than the display. We propose an eye contact correction model that restores the eye contact regardless of the relative ... More
GANPOP: Generative Adversarial Network Prediction of Optical Properties from Single Snapshot Wide-field ImagesJun 12 2019We present a deep learning framework for wide-field, content-aware estimation of absorption and scattering coefficients of tissues, called Generative Adversarial Network Prediction of Optical Properties (GANPOP). Spatial frequency domain imaging is used ... More
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point CloudsJun 12 2019We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds. Inspired by Bilateral Convolutional Layers (BCL), we propose novel DownBCL, UpBCL, and CorrBCL operations that ... More
Presence-Only Geographical Priors for Fine-Grained Image ClassificationJun 12 2019Appearance information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Human experts make use of additional cues such as where, and when, a given image was taken in order to inform their final decision. ... More
Differential Imaging ForensicsJun 12 2019We introduce some new forensics based on differential imaging, where a novel category of visual evidence created via subtle interactions of light with a scene, such as dim reflections, can be computationally extracted and amplified from an image of interest ... More
Rouché's Theorem and the Geometry of Rational FunctionsJun 12 2019In this note, we use Rouch\'e's theorem and the pleasant properties of the arithmetic of the logarithmic derivative to establish several new results regarding the geometry of the zeros, poles, and critical points of a rational function. Included is an ... More
LAEO-Net: revisiting people Looking At Each Other in videosJun 12 2019Capturing the `mutual gaze' of people is essential for understanding and interpreting the social interactions between them. To this end, this paper addresses the problem of detecting people Looking At Each Other (LAEO) in video sequences. For this purpose, ... More
Image-Adaptive GAN based ReconstructionJun 12 2019In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of these methods ... More
Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural NetworkJun 12 2019We present a new handwritten text segmentation method by training a convolutional neural network (CNN) in an end-to-end manner. Many conventional methods addressed this problem by extracting connected components and then classifying them. However, this ... More
Continual and Multi-Task Architecture SearchJun 12 2019Architecture search is the process of automatically learning the neural model or cell structure that best suits the given task. Recently, this approach has shown promising performance improvements (on language modeling and image classification) with reasonable ... More
Towards Real-Time Head Pose Estimation: Exploring Parameter-Reduced Residual Networks on In-the-wild DatasetsJun 12 2019Head poses are a key component of human bodily communication and thus a decisive element of human-computer interaction. Real-time head pose estimation is crucial in the context of human-robot interaction or driver assistance systems. The most promising ... More
Manifold Graph with Learned Prototypes for Semi-Supervised Image ClassificationJun 12 2019Recent advances in semi-supervised learning methods rely on estimating categories for unlabeled data using a model trained on the labeled data (pseudo-labeling) and using the unlabeled data for various consistency-based regularization. In this work, we ... More
Tackling Partial Domain Adaptation with Self-SupervisionJun 12 2019Domain adaptation approaches have shown promising results in reducing the marginal distribution difference among visual domains. They allow to train reliable models that work over datasets of different nature (photos, paintings etc), but they still struggle ... More
Vispi: Automatic Visual Perception and Interpretation of Chest X-raysJun 12 2019Medical imaging contains the essential information for rendering diagnostic and treatment decisions. Inspecting (visual perception) and interpreting image to generate a report are tedious clinical routines for a radiologist where automation is expected ... More
Detection and Correction of Cardiac MR Motion Artefacts during Reconstruction from K-spaceJun 12 2019In fully sampled cardiac MR (CMR) acquisitions, motion can lead to corruption of k-space lines, which can result in artefacts in the reconstructed images. In this paper, we propose a method to automatically detect and correct motion-related artefacts ... More
Boosting Few-Shot Visual Learning with Self-SupervisionJun 12 2019Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns ... More
Stereoscopic Omnidirectional Image Quality Assessment Based on Predictive Coding TheoryJun 12 2019Objective quality assessment of stereoscopic omnidirectional images is a challenging problem since it is influenced by multiple aspects such as projection deformation, field of view (FoV) range, binocular vision, visual comfort, etc. Existing studies ... More
Evaluation of Dataflow through layers of Deep Neural Networks in Classification and Regression ProblemsJun 12 2019This paper introduces two straightforward, effective indices to evaluate the input data and the data flowing through layers of a feedforward deep neural network. For classification problems, the separation rate of target labels in the space of dataflow ... More
Recognizing Manipulation Actions from State-TransformationsJun 12 2019Manipulation actions transform objects from an initial state into a final state. In this paper, we report on the use of object state transitions as a mean for recognizing manipulation actions. Our method is inspired by the intuition that object states ... More
High Accuracy Classification of White Blood Cells using TSLDA Classifier and Covariance FeaturesJun 12 2019Creating automated processes in different areas of medical science with application of engineering tools is a highly growing field over recent decades. In this context, many medical image processing and analyzing researchers use worthwhile methods in ... More
LED2Net: Deep Illumination-aware Dehazing with Low-light and Detail EnhancementJun 12 2019We present a novel dehazing and low-light enhancement method based on an illumination map that is accurately estimated by a convolutional neural network (CNN). In this paper, the illumination map is used as a component for three different tasks, namely, ... More
Pose from Shape: Deep Pose Estimation for Arbitrary 3D ObjectsJun 12 2019Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on relevant categories, ... More
Locally Homogeneous Aspherical Sasaki ManifoldsJun 12 2019Let $G/H$ be a contractible homogeneous Sasaki manifold. A compact locally homogeneous aspherical Sasaki manifold $\Gamma\big\backslash G/H$ is by definition a quotient of $G/H$ by a discrete uniform subgroup $\Gamma\leq G$. We show that a compact locally ... More
Indoor image representation by high-level semantic featuresJun 12 2019Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, color, ... More
DeepSquare: Boosting the Learning Power of Deep Convolutional Neural Networks with Elementwise Square OperatorsJun 12 2019Modern neural network modules which can significantly enhance the learning power usually add too much computational complexity to the original neural networks. In this paper, we pursue very efficient neural network modules which can significantly boost ... More
CDPM: Convolutional Deformable Part Models for Person Re-identificationJun 12 2019Part-level representations are essential for robust person re-identification. Due to errors in pedestrian detection, there are usually severe mis-alignment problems for body parts, which degrade the quality of part representations. To handle this problem, ... More
Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object DetectionJun 12 2019Accurate computer-assisted diagnosis, relying on large-scale annotated pathological images, can alleviate the risk of overlooking the diagnosis. Unfortunately, in medical imaging, most available datasets are small/fragmented. To tackle this, as a Data ... More
Hand Orientation Estimation in Probability Density FormJun 12 2019Hand orientation is an essential feature required to understand hand behaviors and subsequently support human activities. In this paper, we present a new method for estimating hand orientation in probability density form. It can solve the cyclicity problem ... More
Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer LearningJun 12 2019We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transfer learning methods typically face the trade-off between training time ... More
Semi-Supervised Exploration in Image RetrievalJun 12 2019We present our solution to Landmark Image Retrieval Challenge 2019. This challenge was based on the large Google Landmarks Dataset V2[9]. The goal was to retrieve all database images containing the same landmark for every provided query image. Our solution ... More
Non-Parametric Calibration for ClassificationJun 12 2019Many applications for classification methods not only require high accuracy but also reliable estimation of predictive uncertainty. However, while many current classification frameworks, in particular deep neural network architectures, provide very good ... More
All-Weather Deep Outdoor Lighting EstimationJun 12 2019We present a neural network that predicts HDR outdoor illumination from a single LDR image. At the heart of our work is a method to accurately learn HDR lighting from LDR panoramas under any weather condition. We achieve this by training another CNN (on ... More
Compressive Hyperspherical Energy MinimizationJun 12 2019Recent work on minimum hyperspherical energy (MHE) has demonstrated its potential in regularizing neural networks and improving their generalization. MHE was inspired by the Thomson problem in physics, where the distribution of multiple propelling electrons ... More
Adaptive Navigation Scheme for Optimal Deep-Sea Localization Using Multimodal Perception CuesJun 12 2019Underwater robot interventions require a high level of safety and reliability. A major challenge to address is a robust and accurate acquisition of localization estimates, as it is a prerequisite to enable more complex tasks, e.g. floating manipulation ... More
Using Small Proxy Datasets to Accelerate Hyperparameter SearchJun 12 2019One of the biggest bottlenecks in a machine learning workflow is waiting for models to train. Depending on the available computing resources, it can take days to weeks to train a neural network on a large dataset with many classes such as ImageNet. For ... More
Visual Relationships as Functions: Enabling Few-Shot Scene Graph PredictionJun 12 2019Scene graph prediction --- classifying the set of objects and predicates in a visual scene --- requires substantial training data. The long-tailed distribution of relationships can be an obstacle for such approaches, however, as they can only be trained ... More
Task-Aware Deep Sampling for Feature GenerationJun 11 2019The human ability to imagine the variety of appearances of novel objects based on past experience is crucial for quickly learning novel visual concepts based on few examples. Endowing machines with a similar ability to generate feature distributions for ... More
Edge-Direct Visual OdometryJun 11 2019In this paper we propose an edge-direct visual odometry algorithm that efficiently utilizes edge pixels to find the relative pose that minimizes the photometric error between images. Prior work on exploiting edge pixels instead treats edges as features ... More
Weakly-supervised Compositional FeatureAggregation for Few-shot RecognitionJun 11 2019Learning from a few examples is a challenging task for machine learning. While recent progress has been made for this problem, most of the existing methods ignore the compositionality in visual concept representation (e.g. objects are built from parts ... More
Suppressing Model Overfitting for Image Super-Resolution NetworksJun 11 2019Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit undesirable ... More
Joint 3D Localization and Classification of Space Debris using a Multispectral Rotating Point Spread FunctionJun 11 2019We consider the problem of joint three-dimensional (3D) localization and material classification of unresolved space debris using a multispectral rotating point spread function (RPSF). The use of RPSF allows one to estimate the 3D locations of point sources ... More
Shapes and Context: In-the-Wild Image Synthesis & ManipulationJun 11 2019We introduce a data-driven approach for interactively synthesizing in-the-wild images from semantic label maps. Our approach is dramatically different from recent work in this space, in that we make use of no learning. Instead, our approach uses simple ... More
Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene LayoutsJun 11 2019We develop new representations and algorithms for three-dimensional (3D) object detection and spatial layout prediction in cluttered indoor scenes. We first propose a clouds of oriented gradient (COG) descriptor that links the 2D appearance and 3D pose ... More
Recurrent U-Net for Resource-Constrained SegmentationJun 11 2019State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs. In this paper, we introduce a novel recurrent U-Net architecture ... More
Data-Free Quantization through Weight Equalization and Bias CorrectionJun 11 2019We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit fixed-point quantization ... More
3-D Surface Segmentation Meets Conditional Random FieldsJun 11 2019Automated surface segmentation is important and challenging in many medical image analysis applications. Recent deep learning based methods have been developed for various object segmentation tasks. Most of them are a classification based approach, e.g. ... More
Automatic brain tissue segmentation in fetal MRI using convolutional neural networksJun 11 2019MR images of fetuses allow clinicians to detect brain abnormalities in an early stage of development. The cornerstone of volumetric and morphologic analysis in fetal MRI is segmentation of the fetal brain into different tissue classes. Manual segmentation ... More
Generative adversarial network for segmentation of motion affected neonatal brain MRIJun 11 2019Automatic neonatal brain tissue segmentation in preterm born infants is a prerequisite for evaluation of brain development. However, automatic segmentation is often hampered by motion artifacts caused by infant head movements during image acquisition. ... More
Rethinking Person Re-Identification with ConfidenceJun 11 2019A common challenge in person re-identification systems is to differentiate people with very similar appearances. The current learning frameworks based on cross-entropy minimization are not suited for this challenge. To tackle this issue, we propose to ... More
On Single Source Robustness in Deep Fusion ModelsJun 11 2019Algorithms that fuse multiple input sources benefit from both complementary and shared information. Shared information may provide robustness to faulty or noisy inputs, which is indispensable for safety-critical applications like self-driving cars. We ... More
Gated CRF Loss for Weakly Supervised Semantic Image SegmentationJun 11 2019State-of-the-art approaches for semantic segmentation rely on deep convolutional neural networks trained on fully annotated datasets, that have been shown to be notoriously expensive to collect, both in terms of time and money. To remedy this situation, ... More
`Project & Excite' Modules for Segmentation of Volumetric Medical ScansJun 11 2019Jun 12 2019Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for image segmentation in medical imaging. Recently, squeeze and excitation (SE) modules and variations thereof have been introduced to recalibrate feature maps channel- ... More
`Project & Excite' Modules for Segmentation of Volumetric Medical ScansJun 11 2019Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for image segmentation in medical imaging. Recently, squeeze and excitation (SE) modules and variations thereof have been introduced to recalibrate feature maps channel- ... More
Scale Invariant Fully Convolutional Network: Detecting Hands EfficientlyJun 11 2019Existing hand detection methods usually follow the pipeline of multiple stages with high computation cost, i.e., feature extraction, region proposal, bounding box regression, and additional layers for rotated region detection. In this paper, we propose ... More
On Stabilizing Generative Adversarial Training with NoiseJun 11 2019We present a novel method and analysis to train generative adversarial networks (GAN) in a stable manner. As shown in recent analysis, training is often undermined by the probability distribution of the data being zero on neighborhoods of the data space. ... More
Mimic and Fool: A Task Agnostic Adversarial AttackJun 11 2019At present, adversarial attacks are designed in a task-specific fashion. However, for downstream computer vision tasks such as image captioning, image segmentation etc., the current deep learning systems use an image classifier like VGG16, ResNet50, Inception-v3 ... More
Joint Subspace Recovery and Enhanced Locality Driven Robust Flexible Discriminative Dictionary LearningJun 11 2019We propose a joint subspace recovery and enhanced locality based robust flexible label consistent dictionary learning method called Robust Flexible Discriminative Dictionary Learning (RFDDL). RFDDL mainly improves the data representation and classification ... More
Challenges in Time-Stamp Aware Anomaly Detection in Traffic VideosJun 11 2019Time-stamp aware anomaly detection in traffic videos is an essential task for the advancement of the intelligent transportation system. Anomaly detection in videos is a challenging problem due to sparse occurrence of anomalous events, inconsistent behavior ... More
Anomaly Detection in High Performance Computers: A Vicinity PerspectiveJun 11 2019In response to the demand for higher computational power, the number of computing nodes in high performance computers (HPC) increases rapidly. Exascale HPC systems are expected to arrive by 2020. With drastic increase in the number of HPC system components, ... More
Learning robust visual representations using data augmentation invarianceJun 11 2019Deep convolutional neural networks trained for image object categorization have shown remarkable similarities with representations found across the primate ventral visual stream. Yet, artificial and biological networks still exhibit important differences. ... More
BasisConv: A method for compressed representation and learning in CNNsJun 11 2019It is well known that Convolutional Neural Networks (CNNs) have significant redundancy in their filter weights. Various methods have been proposed in the literature to compress trained CNNs. These include techniques like pruning weights, filter quantization ... More
Simultaneously Learning Architectures and Features of Deep Neural NetworksJun 11 2019This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explicitly enforces the optimizer to focus on promising candidate filters while ... More
Cross-Modal Relationship Inference for Grounding Referring ExpressionsJun 11 2019Grounding referring expressions is a fundamental yet challenging task facilitating human-machine communication in the physical world. It locates the target object in an image on the basis of the comprehension of the relationships between referring natural ... More
TW-SMNet: Deep Multitask Learning of Tele-Wide Stereo MatchingJun 11 2019In this paper, we introduce the problem of estimating the real world depth of elements in a scene captured by two cameras with different field of views, where the first field of view (FOV) is a Wide FOV (WFOV) captured by a wide angle lens, and the second ... More
Compressed Sensing MRI via a Multi-scale Dilated Residual Convolution NetworkJun 11 2019Magnetic resonance imaging (MRI) reconstruction is an active inverse problem which can be addressed by conventional compressed sensing (CS) MRI algorithms that exploit the sparse nature of MRI in an iterative optimization-based manner. However, two main ... More
Bag of Color Features For Color ConstancyJun 11 2019In this paper, we propose a novel color constancy approach, called Bag of Color Features (BoCF), building upon Bag-of-Features pooling. The proposed method substantially reduces the number of parameters needed for illumination estimation. At the same ... More
Single Image Blind Deblurring Using Multi-Scale Latent Structure PriorJun 11 2019Blind image deblurring is a challenging problem in computer vision, which aims to restore both the blur kernel and the latent sharp image from only a blurry observation. Inspired by the prevalent self-example prior in image super-resolution, in this paper, ... More
A Novel Cost Function for Despeckling using Convolutional Neural NetworksJun 11 2019Removing speckle noise from SAR images is still an open issue. It is well know that the interpretation of SAR images is very challenging and despeckling algorithms are necessary to improve the ability of extracting information. An urban environment makes ... More
On the Vector Space in Photoplethysmography ImagingJun 11 2019We study the vector space of visible wavelength intensities from face videos widely used as input features in Photoplethysmography Imaging (PPGI). Based upon theoretical principles of Group invariance in the Euclidean space we derive a change of the topology ... More
NAS-FCOS: Fast Neural Architecture Search for Object DetectionJun 11 2019Jun 12 2019The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal architectures, ... More
NAS-FCOS: Fast Neural Architecture Search for Object DetectionJun 11 2019The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal architectures, ... More
Deep learning analysis of cardiac CT angiography for detection of coronary arteries with functionally significant stenosisJun 11 2019In patients with obstructive coronary artery disease, the functional significance of a coronary artery stenosis needs to be determined to guide treatment. This is typically established through fractional flow reserve (FFR) measurement, performed during ... More
Few-Shot Point Cloud Region Annotation with Human in the LoopJun 11 2019We propose a point cloud annotation framework that employs human-in-loop learning to enable the creation of large point cloud datasets with per-point annotations. Sparse labels from a human annotator are iteratively propagated to generate a full segmentation ... More
iProStruct2D: Identifying protein structural classes by deep learning via 2D representationsJun 11 2019In this paper we address the problem of protein classification starting from a multi-view 2D representation of proteins. From each 3D protein structure, a large set of 2D projections is generated using the protein visualization software Jmol. This set ... More
Polysemous Visual-Semantic Embedding for Cross-Modal RetrievalJun 11 2019Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared space. Unfortunately, ... More
Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box AttacksJun 11 2019Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by issuing numerous ... More
Different Approaches for Human Activity Recognition: A SurveyJun 11 2019Human activity recognition has gained importance in recent years due to its applications in various fields such as health, security and surveillance, entertainment, and intelligent environments. A significant amount of work has been done on human activity ... More
Band Attention Convolutional Networks For Hyperspectral Image ClassificationJun 11 2019Redundancy and noise exist in the bands of hyperspectral images (HSIs). Thus, it is a good property to be able to select suitable parts from hundreds of input bands for HSIs classification methods. In this letter, a band attention module (BAM) is proposed ... More
PAN: Projective Adversarial Network for Medical Image SegmentationJun 11 2019Adversarial learning has been proven to be effective for capturing long-range and high-level label consistencies in semantic segmentation. Unique to medical imaging, capturing 3D semantics in an effective yet computationally efficient way remains an open ... More
Recognizing License Plates in Real-TimeJun 11 2019License plate detection and recognition (LPDR) is of growing importance for enabling intelligent transportation and ensuring the security and safety of the cities. However, LPDR faces a big challenge in a practical environment. The license plates can ... More
Object-aware Aggregation with Bidirectional Temporal Graph for Video CaptioningJun 11 2019Video captioning aims to automatically generate natural language descriptions of video content, which has drawn a lot of attention recent years. Generating accurate and fine-grained captions needs to not only understand the global content of video, but ... More
Hybrid Function Sparse Representation towards Image Super ResolutionJun 11 2019Sparse representation with training-based dictionary has been shown successful on super resolution(SR) but still have some limitations. Based on the idea of making the magnification of function curve without losing its fidelity, we proposed a function ... More
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain AdaptationJun 11 2019Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the source, and (b) aligning ... More
FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing NetworkJun 11 2019Single image dehazing is a critical image pre-processing step for subsequent high-level computer vision tasks. However, it remains challenging due to its ill-posed nature. Existing dehazing models tend to suffer from model overcomplexity and computational ... More
Multiscale Nakagami parametric imaging for improved liver tumor localizationJun 11 2019Effective ultrasound tissue characterization is usually hindered by complex tissue structures. The interlacing of speckle patterns complicates the correct estimation of backscatter distribution parameters. Nakagami parametric imaging based on localized ... More
Inferring 3D Shapes from Image Collections using Adversarial NetworksJun 11 2019We investigate the problem of learning a probabilistic distribution over three-dimensional shapes given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called projective generative adversarial network (PrGAN) trains ... More
Online Object Representations with Contrastive LearningJun 10 2019We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful in situated settings such as robotics. The main contributions of this paper are: 1) a self-supervising objective ... More