Results for "Luc Van Gool"

total 27115took 0.13s
Extremely Weak Supervised Image-to-Image Translation for Semantic SegmentationSep 18 2019Recent advances in generative models and adversarial training have led to a flourishing image-to-image (I2I) translation literature. The current I2I translation approaches require training images from the two domains that are either all paired (supervised) ... More
Failure Prediction for Autonomous DrivingMay 04 2018The primary focus of autonomous driving research is to improve driving accuracy. While great progress has been made, state-of-the-art algorithms still fail at times. Such failures may have catastrophic consequences. It therefore is important that automated ... More
End-to-End Learning of Driving Models with Surround-View Cameras and Route PlannersMar 27 2018Aug 06 2018For human drivers, having rear and side-view mirrors is vital for safe driving. They deliver a more complete view of what is happening around the car. Human drivers also heavily exploit their mental map for navigation. Nonetheless, several methods have ... More
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban ScenesNov 30 2017Apr 07 2018Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the learned model ... More
Semantic Foggy Scene Understanding with Synthetic DataAug 25 2017May 17 2019This work addresses the problem of semantic foggy scene understanding (SFSU). Although extensive research has been performed on image dehazing and on semantic scene understanding with clear-weather images, little attention has been paid to SFSU. Due to ... More
DARN: a Deep Adversial Residual Network for Intrinsic Image DecompositionDec 23 2016Mar 20 2018We present a new deep supervised learning method for intrinsic decomposition of a single image into its albedo and shading components. Our contributions are based on a new fully convolutional neural network that estimates absolute albedo and shading jointly. ... More
Seven ways to improve example-based single image super resolutionNov 06 2015In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2) use of large dictionaries with efficient search structures, 3) cascading, 4) image self-similarities, ... More
Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image SegmentationJan 17 2019Jul 26 2019Most progress in semantic segmentation reports on daytime images taken under favorable illumination conditions. We instead address the problem of semantic segmentation of nighttime images and improve the state-of-the-art, by adapting daytime models to ... More
Real-time 3D Traffic Cone Detection for Autonomous DrivingFeb 06 2019Jun 05 2019Considerable progress has been made in semantic scene understanding of road scenes with monocular cameras. It is, however, mainly related to certain classes such as cars and pedestrians. This work investigates traffic cones, an object class crucial for ... More
A Three-Player GAN: Generating Hard Samples To Improve Classification NetworksMar 08 2019We propose a Three-Player Generative Adversarial Network to improve classification networks. In addition to the game played between the discriminator and generator, a competition is introduced between the generator and the classifier. The generator's ... More
ComboGAN: Unrestrained Scalability for Image Domain TranslationDec 19 2017This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al. But experiments so far have been tailored to merely two domains at a time, and scaling them to more would require an quadratic ... More
Branched Multi-Task Networks: Deciding What Layers To ShareApr 05 2019In the context of deep learning, neural networks with multiple branches have been used that each solve different tasks. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence ... More
Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering BandwidthJun 26 2019Aug 02 2019Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high accuracy, they ... More
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene UnderstandingAug 03 2018This work addresses the problem of semantic scene understanding under dense fog. Although considerable progress has been made in semantic scene understanding, it is mainly related to clear-weather scenes. Extending recognition methods to adverse weather ... More
Appearance-and-Relation Networks for Video ClassificationNov 24 2017May 06 2018Spatiotemporal feature learning in videos is a fundamental problem in computer vision. This paper presents a new architecture, termed as Appearance-and-Relation Network (ARTNet), to learn video representation in an end-to-end manner. ARTNets are constructed ... More
Acquiring Common Sense Spatial Knowledge through Implicit Spatial TemplatesNov 18 2017Nov 21 2017Spatial understanding is a fundamental problem with wide-reaching real-world applications. The representation of spatial knowledge is often modeled with spatial templates, i.e., regions of acceptability of two objects under an explicit spatial relationship ... More
Query-adaptive Video Summarization via Quality-aware Relevance EstimationMay 01 2017Sep 28 2017Although the problem of automatic video summarization has recently received a lot of attention, the problem of creating a video summary that also highlights elements relevant to a search query has been less studied. We address this problem by posing query-relevant ... More
DeepCAMP: Deep Convolutional Action & Attribute Mid-Level PatternsAug 10 2016The recognition of human actions and the determination of human attributes are two tasks that call for fine-grained classification. Indeed, often rather small and inconspicuous objects and features have to be detected to tell their classes apart. In order ... 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
3D Appearance Super-Resolution with Deep LearningJun 03 2019Jun 04 2019We tackle the problem of retrieving high-resolution (HR) texture maps of objects that are captured from multiple view points. In the multi-view case, model-based super-resolution (SR) methods have been recently proved to recover high quality texture maps. ... More
Exemplar Guided Unsupervised Image-to-Image Translation with Semantic ConsistencyMay 28 2018Mar 13 2019Image-to-image translation has recently received significant attention due to advances in deep learning. Most works focus on learning either a one-to-one mapping in an unsupervised way or a many-to-many mapping in a supervised way. However, a more practical ... More
Holistic Large Scale Video UnderstandingApr 25 2019Action recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing on a highly specific video understanding task and thus leaving a significant ... More
Automatic Tool Landmark Detection for Stereo Vision in Robot-Assisted Retinal SurgerySep 17 2017Nov 20 2017Computer vision and robotics are being increasingly applied in medical interventions. Especially in interventions where extreme precision is required they could make a difference. One such application is robot-assisted retinal microsurgery. In recent ... More
Pose Guided Person Image GenerationMay 25 2017Jan 28 2018This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG$^2$ utilizes the pose information explicitly ... More
Learning a Curve Guardian for MotorcyclesJul 12 2019Up to 17% of all motorcycle accidents occur when the rider is maneuvering through a curve and the main cause of curve accidents can be attributed to inappropriate speed and wrong intra-lane position of the motorcycle. Existing curve warning systems lack ... More
Spatio-Temporal Channel Correlation Networks for Action ClassificationJun 19 2018Feb 07 2019The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models correlations ... More
Domain Adaptive Faster R-CNN for Object Detection in the WildMar 08 2018Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to ... More
Improving Video Generation for Multi-functional ApplicationsNov 30 2017Mar 14 2018In this paper, we aim to improve the state-of-the-art video generative adversarial networks (GANs) with a view towards multi-functional applications. Our improved video GAN model does not separate foreground from background nor dynamic from static patterns, ... More
DSLR-Quality Photos on Mobile Devices with Deep Convolutional NetworksApr 08 2017Sep 05 2017Despite a rapid rise in the quality of built-in smartphone cameras, their physical limitations - small sensor size, compact lenses and the lack of specific hardware, - impede them to achieve the quality results of DSLR cameras. In this work we present ... More
Fast Perceptual Image EnhancementDec 31 2018The vast majority of photos taken today are by mobile phones. While their quality is rapidly growing, due to physical limitations and cost constraints, mobile phone cameras struggle to compare in quality with DSLR cameras. This motivates us to computationally ... More
AI Benchmark: Running Deep Neural Networks on Android SmartphonesOct 02 2018Oct 15 2018Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there ... More
Temporal 3D ConvNets: New Architecture and Transfer Learning for Video ClassificationNov 22 2017The work in this paper is driven by the question how to exploit the temporal cues available in videos for their accurate classification, and for human action recognition in particular? Thus far, the vision community has focused on spatio-temporal approaches ... More
WebVision Challenge: Visual Learning and Understanding With Web DataMay 16 2017We present the 2017 WebVision Challenge, a public image recognition challenge designed for deep learning based on web images without instance-level human annotation. Following the spirit of previous vision challenges, such as ILSVRC, Places2 and PASCAL ... More
A Riemannian Network for SPD Matrix LearningAug 15 2016Symmetric Positive Definite (SPD) matrix learning methods have become popular in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting the Riemannian geometry of the underlying ... More
Unsupervised High-level Feature Learning by Ensemble Projection for Semi-supervised Image Classification and Image ClusteringFeb 02 2016Feb 04 2016This paper investigates the problem of image classification with limited or no annotations, but abundant unlabeled data. The setting exists in many tasks such as semi-supervised image classification, image clustering, and image retrieval. Unlike previous ... More
Does V-NIR based Image Enhancement Come with Better Features?Aug 23 2016Aug 24 2016Image enhancement using the visible (V) and near-infrared (NIR) usually enhances useful image details. The enhanced images are evaluated by observers perception, instead of quantitative feature evaluation. Thus, can we say that these enhanced images using ... More
A Riemannian Network for SPD Matrix LearningAug 15 2016Dec 22 2016Symmetric Positive Definite (SPD) matrix learning methods have become popular in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting Riemannian geometry of underlying SPD manifolds. ... More
Dark Model Adaptation: Semantic Image Segmentation from Daytime to NighttimeOct 05 2018This work addresses the problem of semantic image segmentation of nighttime scenes. Although considerable progress has been made in semantic image segmentation, it is mainly related to daytime scenarios. This paper proposes a novel method to progressive ... More
Image-level Classification in Hyperspectral Images using Feature Descriptors, with Application to Face RecognitionMay 11 2016In this paper, we proposed a novel pipeline for image-level classification in the hyperspectral images. By doing this, we show that the discriminative spectral information at image-level features lead to significantly improved performance in a face recognition ... More
Quantum filtering: a reference probability approachAug 01 2005Jan 30 2006These notes are intended as an introduction to noncommutative (quantum) filtering theory. An introduction to quantum probability theory is given, focusing on the spectral theorem and the conditional expectation as the least squares estimate, and culminating ... More
On the separation principle of quantum controlNov 05 2005Aug 22 2006It is well known that quantum continuous observations and nonlinear filtering can be developed within the framework of the quantum stochastic calculus of Hudson-Parthasarathy. The addition of real-time feedback control has been discussed by many authors, ... More
Discrete Approximation of Quantum Stochastic ModelsMar 31 2008Sep 25 2008We develop a general technique for proving convergence of repeated quantum interactions to the solution of a quantum stochastic differential equation. The wide applicability of the method is illustrated in a variety of examples. Our main theorem, which ... More
Semantic Nighttime Image Segmentation with Synthetic Stylized Data, Gradual Adaptation and Uncertainty-Aware EvaluationJan 17 2019This work addresses the problem of semantic segmentation of nighttime images. The main direction of recent progress in semantic segmentation pertains to daytime scenes with favorable illumination conditions. We focus on improving the performance of state-of-the-art ... More
Unsupervised Deep Single-Image Intrinsic Decomposition using Illumination-Varying Image SequencesMar 02 2018Sep 03 2018Machine learning based Single Image Intrinsic Decomposition (SIID) methods decompose a captured scene into its albedo and shading images by using the knowledge of a large set of known and realistic ground truth decompositions. Collecting and annotating ... More
Deep Temporal Linear Encoding NetworksNov 21 2016The CNN-encoding of features from entire videos for the representation of human actions has rarely been addressed. Instead, CNN work has focused on approaches to fuse spatial and temporal networks, but these were typically limited to processing shorter ... More
Semi-Supervised Learning by Augmented Distribution AlignmentMay 20 2019Aug 18 2019In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled samples, which ... More
Real-time 3D Traffic Cone Detection for Autonomous DrivingFeb 06 2019Considerable progress has been made in semantic scene understanding of road scenes with monocular cameras. It is, however, mainly related to certain classes such as cars and pedestrians. This work investigates traffic cones, an object class crucial for ... More
Comment on "Ensemble Projection for Semi-supervised Image Classification"Aug 29 2014In a series of papers by Dai and colleagues [1,2], a feature map (or kernel) was introduced for semi- and unsupervised learning. This feature map is build from the output of an ensemble of classifiers trained without using the ground-truth class labels. ... More
Multi-bin Trainable Linear Unit for Fast Image Restoration NetworksJul 30 2018Tremendous advances in image restoration tasks such as denoising and super-resolution have been achieved using neural networks. Such approaches generally employ very deep architectures, large number of parameters, large receptive fields and high nonlinear ... More
Generic 3D Convolutional Fusion for image restorationJul 26 2016Also recently, exciting strides forward have been made in the area of image restoration, particularly for image denoising and single image super-resolution. Deep learning techniques contributed to this significantly. The top methods differ in their formulations ... More
Semi-Supervised Learning by Augmented Distribution AlignmentMay 20 2019In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited amount of labeled samples, which ... More
Random Binary Mappings for Kernel Learning and Efficient SVMJul 19 2013Mar 28 2014Support Vector Machines (SVMs) are powerful learners that have led to state-of-the-art results in various computer vision problems. SVMs suffer from various drawbacks in terms of selecting the right kernel, which depends on the image descriptors, as well ... More
AENet: Learning Deep Audio Features for Video AnalysisJan 03 2017Jan 04 2017We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period ... More
Failure Detection for Facial Landmark DetectorsAug 23 2016Most face applications depend heavily on the accuracy of the face and facial landmarks detectors employed. Prediction of attributes such as gender, age, and identity usually completely fail when the faces are badly aligned due to inaccurate facial landmark ... More
k2-means for fast and accurate large scale clusteringMay 30 2016We propose k^2-means, a new clustering method which efficiently copes with large numbers of clusters and achieves low energy solutions. k^2-means builds upon the standard k-means (Lloyd's algorithm) and combines a new strategy to accelerate the convergence ... More
Some like it hot - visual guidance for preference predictionOct 27 2015Mar 10 2016For people first impressions of someone are of determining importance. They are hard to alter through further information. This begs the question if a computer can reach the same judgement. Earlier research has already pointed out that age, gender, and ... More
Semantic Foggy Scene Understanding with Synthetic DataAug 25 2017Sep 05 2017This work addresses the problem of semantic foggy scene understanding (SFSU). Although extensive research has been performed on image dehazing and on semantic scene understanding with weather-clear images, little attention has been paid to SFSU. Due to ... More
Direction matters: hand pose estimation from local surface normalsApr 10 2016We present a hierarchical regression framework for estimating hand joint positions from single depth images based on local surface normals. The hierarchical regression follows the tree structured topology of hand from wrist to finger tips. We propose ... More
Progressive Structure from MotionMar 20 2018Jul 10 2018Structure from Motion or the sparse 3D reconstruction out of individual photos is a long studied topic in computer vision. Yet none of the existing reconstruction pipelines fully addresses a progressive scenario where images are only getting available ... More
Manifold-valued Image Generation with Wasserstein Generative Adversarial NetsDec 05 2017Jan 03 2019Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently ... More
Building Deep Networks on Grassmann ManifoldsNov 17 2016Jan 29 2018Learning representations on Grassmann manifolds is popular in quite a few visual recognition tasks. In order to enable deep learning on Grassmann manifolds, this paper proposes a deep network architecture by generalizing the Euclidean network paradigm ... More
Building Deep Networks on Grassmann ManifoldsNov 17 2016Representing the data on Grassmann manifolds is popular in quite a few image and video recognition tasks. In order to enable deep learning on Grassmann manifolds, this paper proposes a deep network architecture which generalizes the Euclidean network ... More
Learning Accurate, Comfortable and Human-like DrivingMar 26 2019Autonomous vehicles are more likely to be accepted if they drive accurately, comfortably, but also similar to how human drivers would. This is especially true when autonomous and human-driven vehicles need to share the same road. The main research focus ... More
Approximation and limit theorems for quantum stochastic models with unbounded coefficientsDec 14 2007We prove a limit theorem for quantum stochastic differential equations with unbounded coefficients which extends the Trotter-Kato theorem for contraction semigroups. From this theorem, general results on the convergence of approximations and singular ... More
Observing the fine structure of loops through high resolution spectroscopic observations of coronal rain with the CRISP instrument at the Swedish Solar TelescopeDec 03 2011We present here one of the first high resolution spectroscopic observations of coronal rain, performed with the CRISP instrument at the Swedish Solar Telescope. This work constitutes the first attempt to assess the importance of coronal rain in the understanding ... More
An introduction to quantum filteringJan 30 2006This paper provides an introduction to quantum filtering theory. An introduction to quantum probability theory is given, focusing on the spectral theorem and the conditional expectation as a least squares estimate, and culminating in the construction ... More
Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event DetectionApr 25 2016We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due ... More
Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene UnderstandingJan 05 2019This work addresses the problem of semantic scene understanding under fog. Although marked progress has been made in semantic scene understanding, it is mainly concentrated on clear-weather scenes. Extending semantic segmentation methods to adverse weather ... More
Efficient Two-Stream Motion and Appearance 3D CNNs for Video ClassificationAug 31 2016Sep 02 2016The video and action classification have extremely evolved by deep neural networks specially with two stream CNN using RGB and optical flow as inputs and they present outstanding performance in terms of video analysis. One of the shortcoming of these ... More
Dilemma First Search for Effortless Optimization of NP-Hard ProblemsSep 12 2016To tackle the exponentiality associated with NP-hard problems, two paradigms have been proposed. First, Branch & Bound, like Dynamic Programming, achieve efficient exact inference but requires extensive information and analysis about the problem at hand. ... More
Efficient Volumetric Fusion of Airborne and Street-Side Data for Urban ReconstructionSep 05 2016Airborne acquisition and on-road mobile mapping provide complementary 3D information of an urban landscape: the former acquires roof structures, ground, and vegetation at a large scale, but lacks the facade and street-side details, while the latter is ... 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
Ensemble Manifold Segmentation for Model Distillation and Semi-supervised LearningApr 06 2018Manifold theory has been the central concept of many learning methods. However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the architecture of the ... More
Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation ApproachDec 12 2018Jan 13 2019Recently, increasing attention has been drawn to training semantic segmentation models using synthetic data and computer-generated annotation. However, domain gap remains a major barrier and prevents models learned from synthetic data from generalizing ... More
Semantically-Guided Video Object SegmentationApr 06 2017Jul 17 2018This paper tackles the problem of semi-supervised video object segmentation, that is, segmenting an object in a sequence given its mask in the first frame. One of the main challenges in this scenario is the change of appearance of the objects of interest. ... More
DynamoNet: Dynamic Action and Motion NetworkApr 25 2019In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action recognition in particular. Thus far, the vision community has focused ... More
Learning Filter Basis for Convolutional Neural Network CompressionAug 23 2019Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost of millions ... More
Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering BandwidthJun 26 2019Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high accuracy, they ... More
Object Referring in Videos with Language and Human GazeJan 04 2018Apr 04 2018We investigate the problem of object referring (OR) i.e. to localize a target object in a visual scene coming with a language description. Humans perceive the world more as continued video snippets than as static images, and describe objects not only ... More
Object Referring in Visual Scene with Spoken LanguageNov 10 2017Dec 05 2017Object referring has important applications, especially for human-machine interaction. While having received great attention, the task is mainly attacked with written language (text) as input rather than spoken language (speech), which is more natural. ... More
UntrimmedNets for Weakly Supervised Action Recognition and DetectionMar 09 2017May 22 2017Current action recognition methods heavily rely on trimmed videos for model training. However, it is expensive and time-consuming to acquire a large-scale trimmed video dataset. This paper presents a new weakly supervised architecture, called UntrimmedNet, ... More
PathTrack: Fast Trajectory Annotation with Path SupervisionMar 07 2017Mar 22 2017Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use it to produce a MOT dataset of unprecedented size. In our novel path supervision ... More
Covariance Pooling For Facial Expression RecognitionMay 13 2018Classifying facial expressions into different categories requires capturing regional distortions of facial landmarks. We believe that second-order statistics such as covariance is better able to capture such distortions in regional facial fea- tures. ... More
Model-free Consensus Maximization for Non-Rigid ShapesJul 05 2018Aug 13 2018Many computer vision methods use consensus maximization to relate measurements containing outliers with the correct transformation model. In the context of rigid shapes, this is typically done using Random Sampling and Consensus (RANSAC) by estimating ... More
Deep Learning on Lie Groups for Skeleton-based Action RecognitionDec 18 2016Apr 11 2017In recent years, skeleton-based action recognition has become a popular 3D classification problem. State-of-the-art methods typically first represent each motion sequence as a high-dimensional trajectory on a Lie group with an additional dynamic time ... More
DLOW: Domain Flow for Adaptation and GeneralizationDec 13 2018May 13 2019In this work, we present a domain flow generation(DLOW) model to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other. The benefits of our DLOW model are two-fold. First, it is able ... More
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric LearningApr 09 2018This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same object instance ... More
SMIT: Stochastic Multi-Label Image-to-Image TranslationDec 10 2018Cross-domain mapping has been a very active topic in recent years. Given one image, its main purpose is to translate it to the desired target domain, or multiple domains in the case of multiple labels. This problem is highly challenging due to three main ... More
DLOW: Domain Flow for Adaptation and GeneralizationDec 13 2018In this work, we propose a domain flow generation(DLOW) approach to model the domain shift between two domains by generating a continuous sequence of intermediate domains flowing from one domain to the other. The benefits of our DLOW model are two-fold. ... More
SMIT: Stochastic Multi-Label Image-to-Image TranslationDec 10 2018Apr 01 2019Cross-domain mapping has been a very active topic in recent years. Given one image, its main purpose is to translate it to the desired target domain, or multiple domains in the case of multiple labels. This problem is highly challenging due to three main ... More
Logo Synthesis and Manipulation with Clustered Generative Adversarial NetworksDec 12 2017Designing a logo for a new brand is a lengthy and tedious back-and-forth process between a designer and a client. In this paper we explore to what extent machine learning can solve the creative task of the designer. For this, we build a dataset -- LLD ... More
Optimal transport maps for distribution preserving operations on latent spaces of Generative ModelsNov 06 2017Jan 24 2018Generative models such as Variational Auto Encoders (VAEs) and Generative Adversarial Networks (GANs) are typically trained for a fixed prior distribution in the latent space, such as uniform or Gaussian. After a trained model is obtained, one can sample ... More
Fast Optical Flow using Dense Inverse SearchMar 11 2016Most recent works in optical flow extraction focus on the accuracy and neglect the time complexity. However, in real-life visual applications, such as tracking, activity detection and recognition, the time complexity is critical. We propose a solution ... More
Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANsOct 04 2018Dec 06 2018The extension of image generation to video generation turns out to be a very difficult task, since the temporal dimension of videos introduces an extra challenge during the generation process. Besides, due to the limitation of memory and training stability, ... More
Actionness Estimation Using Hybrid Fully Convolutional NetworksApr 25 2016Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location. Accurate and efficient estimation of actionness is important in video analysis and may benefit other relevant tasks such as action recognition ... More
Oracle MCG: A first peek into COCO Detection ChallengesAug 14 2015The recently presented COCO detection challenge will most probably be the reference benchmark in object detection in the next years. COCO is two orders of magnitude larger than Pascal and has four times the number of categories; so in all likelihood researchers ... More
On the Relation between Color Image Denoising and ClassificationApr 05 2017Large amount of image denoising literature focuses on single channel images and often experimentally validates the proposed methods on tens of images at most. In this paper, we investigate the interaction between denoising and classification on large ... More
A Novel BiLevel Paradigm for Image-to-Image TranslationApr 18 2019Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong category bias in image scenes. In order to tackle these problems, we propose ... More
SMIT: Stochastic Multi-Label Image-to-Image TranslationDec 10 2018Sep 05 2019Cross-domain mapping has been a very active topic in recent years. Given one image, its main purpose is to translate it to the desired target domain, or multiple domains in the case of multiple labels. This problem is highly challenging due to three main ... More
Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene UnderstandingJan 05 2019May 01 2019This work addresses the problem of semantic scene understanding under fog. Although marked progress has been made in semantic scene understanding, it is mainly concentrated on clear-weather scenes. Extending semantic segmentation methods to adverse weather ... More