no code implementations • CVPR 2013 • Rodrigo Benenson, Markus Mathias, Tinne Tuytelaars, Luc van Gool
The current state of the art solutions for object detection describe each class by a set of models trained on discovered sub-classes (so called "components"), with each model itself composed of collections of interrelated parts (deformable models).
no code implementations • CVPR 2013 • Andelo Martinovic, Luc van Gool
Given a set of labeled positive examples, we induce a grammar which can be sampled to create novel instances of the same building style.
no code implementations • CVPR 2013 • Julien Weissenberg, Hayko Riemenschneider, Mukta Prasad, Luc van Gool
Urban models are key to navigation, architecture and entertainment.
no code implementations • CVPR 2013 • Matthieu Guillaumin, Luc van Gool, Vittorio Ferrari
However, when the graph is fully connected and the pairwise potentials are arbitrary, the complexity of even approximate minimization algorithms such as TRW-S grows quadratically both in the number of nodes and in the number of states a node can take.
no code implementations • CVPR 2013 • Matthias Dantone, Juergen Gall, Christian Leistner, Luc van Gool
The second layer takes the estimated class distributions of the first one into account and is thereby able to predict joint locations by modeling the interdependence and co-occurrence of the parts.
no code implementations • CVPR 2013 • Xavier Boix, Michael Gygli, Gemma Roig, Luc van Gool
We demonstrate the capabilities of our formulation for both keypoint matching and image classification.
no code implementations • CVPR 2013 • Danfeng Qin, Christian Wengert, Luc van Gool
Furthermore, we propose a function to score the individual contributions into an image to image similarity within the probabilistic framework.
no code implementations • 19 Jul 2013 • Gemma Roig, Xavier Boix, Luc van Gool
SVMs suffer from various drawbacks in terms of selecting the right kernel, which depends on the image descriptors, as well as computational and memory efficiency.
1 code implementation • 16 Sep 2013 • Michael Van den Bergh, Xavier Boix, Gemma Roig, Luc van Gool
We define a robust and fast to evaluate energy function, based on enforcing color similarity between the bound- aries and the superpixel color histogram.
no code implementations • ECCV 2014 • Michael Gygli, Helmut Grabner, Hayko Riemenschneider, Luc van Gool
Thereby we focus on user videos, which are raw videos containing a set of interesting events.
no code implementations • CVPR 2014 • Dengxin Dai, Hayko Riemenschneider, Luc van Gool
This work is the first attempt to quantify this image property, and we find that texture synthesizability can be learned and predicted.
no code implementations • CVPR 2014 • Meng Yang, Dengxin Dai, Lilin Shen, Luc van Gool
Each dictionary atom is jointly learned with a latent vector, which associates this atom to the representation of different classes.
no code implementations • CVPR 2014 • Hakan Bilen, Marco Pedersoli, Vinay P. Namboodiri, Tinne Tuytelaars, Luc van Gool
In classification of objects substantial work has gone into improving the low level representation of an image by considering various aspects such as different features, a number of feature pooling and coding techniques and considering different kernels.
no code implementations • CVPR 2014 • Marko Ristin, Matthieu Guillaumin, Juergen Gall, Luc van Gool
NCMFs not only outperform conventional random forests, but are also well suited for integrating new classes.
no code implementations • CVPR 2014 • Andras Bodis-Szomoru, Hayko Riemenschneider, Luc van Gool
State-of-the-art Multi-View Stereo (MVS) algorithms deliver dense depth maps or complex meshes with very high detail, and redundancy over regular surfaces.
no code implementations • CVPR 2014 • Ralf Dragon, Luc van Gool
We focus on the problem of estimating the ground plane orientation and location in monocular video sequences from a moving observer.
no code implementations • CVPR 2014 • Angela Yao, Luc van Gool, Pushmeet Kohli
Human gestures, similar to speech and handwriting, are often unique to the individual.
no code implementations • CVPR 2014 • Marco Pedersoli, Tinne Tuytelaars, Luc van Gool
Additionally, without any facial point annotation at the level of individual training images, our method can localize facial points with an accuracy similar to fully supervised approaches.
no code implementations • 29 Aug 2014 • Xavier Boix, Gemma Roig, Luc van Gool
In a series of papers by Dai and colleagues [1, 2], a feature map (or kernel) was introduced for semi- and unsupervised learning.
no code implementations • CVPR 2015 • Marko Ristin, Juergen Gall, Matthieu Guillaumin, Luc van Gool
Compared to approaches that disregard the extra coarse labeled data, we achieve a relative improvement in subcategory classification accuracy of up to 22% in our large-scale image classification experiments.
no code implementations • CVPR 2015 • Michael Gygli, Helmut Grabner, Luc van Gool
We present a novel method for summarizing raw, casually captured videos.
no code implementations • CVPR 2015 • Andelo Martinovic, Jan Knopp, Hayko Riemenschneider, Luc van Gool
We propose a new approach for semantic segmentation of 3D city models.
no code implementations • CVPR 2015 • Andras Bodis-Szomoru, Hayko Riemenschneider, Luc van Gool
Multi-View-Stereo (MVS) methods aim for the highest detail possible, however, such detail is often not required.
no code implementations • CVPR 2015 • Till Kroeger, Dengxin Dai, Luc van Gool
Although the method is designed for unknown camera poses, it is also helpful in scenarios with known poses, since a multi-frame approach in VP detection helps to regularize in frames with weak VP line support.
no code implementations • CVPR 2015 • Dengxin Dai, Till Kroeger, Radu Timofte, Luc van Gool
In particular, MI consists of: 1) quantifying the properties of source metrics as manifold geometry, 2) transferring the manifold from source domain to target domain, and 3) learning a mapping of TFs so that the manifold is approximated as well as possible in the mapped feature domain.
no code implementations • 14 Aug 2015 • Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool
The recently presented COCO detection challenge will most probably be the reference benchmark in object detection in the next years.
no code implementations • 23 Sep 2015 • Dengxin Dai, Yujian Wang, Yuhua Chen, Luc van Gool
In this paper, we present the first comprehensive study and analysis of the usefulness of ISR for other vision applications.
1 code implementation • ICCV 2015 • Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc van Gool
We generate hypotheses in a sliding-window fashion over different activation layers and show that the final convolutional layers can find the object of interest with high recall but poor localization due to the coarseness of the feature maps.
no code implementations • CVPR 2016 • Rasmus Rothe, Radu Timofte, Luc van Gool
Our computational pipeline comprises a face detector, convolutional neural networks for the extraction of deep features, standard support vector regression for gender, age and facial beauty, and - as the main novelties - visual regularized collaborative filtering to infer inter-person preferences as well as a novel regression technique for handling visual queries without rating history.
no code implementations • CVPR 2016 • Radu Timofte, Rasmus Rothe, Luc van Gool
In 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, 5) back projection refinement, 6) enhanced prediction by consistency check, and 7) context reasoning.
Ranked #45 on Image Super-Resolution on BSD100 - 4x upscaling
no code implementations • ICCV 2015 • Jordi Pont-Tuset, Luc van Gool
Computer vision in general, and object proposals in particular, are nowadays strongly influenced by the databases on which researchers evaluate the performance of their algorithms.
no code implementations • ICCV 2015 • Stamatios Georgoulis, Vincent Vanweddingen, Marc Proesmans, Luc van Gool
Although inferring higher dimensional BRDFs from such modest training is not a trivial problem, our method performs better than state-of-the-art parametric, semi-parametric and non-parametric approaches.
no code implementations • 2 Feb 2016 • Dengxin Dai, Luc van Gool
Hence, in the spirit of ensemble learning we create a set of such training sets which are all diverse, leading to diverse classifiers.
no code implementations • 11 Mar 2016 • Till Kroeger, Radu Timofte, Dengxin Dai, Luc van Gool
Most recent works in optical flow extraction focus on the accuracy and neglect the time complexity.
no code implementations • 22 Mar 2016 • Bert Moons, Bert de Brabandere, Luc van Gool, Marian Verhelst
Recently ConvNets or convolutional neural networks (CNN) have come up as state-of-the-art classification and detection algorithms, achieving near-human performance in visual detection.
no code implementations • 27 Mar 2016 • Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Luc van Gool, Tinne Tuytelaars
In this paper we are extracting surface reflectance and natural environmental illumination from a reflectance map, i. e. from a single 2D image of a sphere of one material under one illumination.
no code implementations • 10 Apr 2016 • Chengde Wan, Angela Yao, Luc van Gool
We present a hierarchical regression framework for estimating hand joint positions from single depth images based on local surface normals.
no code implementations • 25 Apr 2016 • Naoya Takahashi, Michael Gygli, Beat Pfister, Luc van Gool
We propose a novel method for Acoustic Event Detection (AED).
Sound Multimedia
no code implementations • CVPR 2016 • Limin Wang, Yu Qiao, Xiaoou Tang, Luc van Gool
Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location.
Ranked #11 on Action Detection on J-HMDB
no code implementations • 11 May 2016 • Vivek Sharma, Luc van Gool
In this paper, we proposed a novel pipeline for image-level classification in the hyperspectral images.
no code implementations • 26 May 2016 • Vivek Sharma, Sule Yildirim-Yayilgan, Luc van Gool
We propose a low cost and effective way to combine a free simulation software and free CAD models for modeling human-object interaction in order to improve human & object segmentation.
no code implementations • 30 May 2016 • Eirikur Agustsson, Radu Timofte, Luc van Gool
k^2-means builds upon the standard k-means (Lloyd's algorithm) and combines a new strategy to accelerate the convergence with a new low time complexity divisive initialization.
1 code implementation • NeurIPS 2016 • Bert De Brabandere, Xu Jia, Tinne Tuytelaars, Luc van Gool
In a traditional convolutional layer, the learned filters stay fixed after training.
Ranked #1 on Video Prediction on KTH (Cond metric)
1 code implementation • CVPR 2016 • Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams, Luc van Gool, Markus Gross, Alexander Sorkine-Hornung
The dataset, named DAVIS (Densely Annotated VIdeo Segmentation), consists of fifty high quality, Full HD video sequences, spanning multiple occurrences of common video object segmentation challenges such as occlusions, motion-blur and appearance changes.
1 code implementation • CVPR 2016 • Alex Locher, Michal Perdoch, Luc van Gool
This work proposes a progressive patch based multi-view stereo algorithm able to deliver a dense point cloud at any time.
1 code implementation • CVPR 2016 • Yuhua Chen, Dengxin Dai, Jordi Pont-Tuset, Luc van Gool
To demonstrate the power of our method, we perform comprehensive experiments, which show that our method, as a post-processing step, can significantly improve the quality of the hierarchical segmentation representations, and ease the usage of hierarchical image segmentation to high-level vision tasks such as object segmentation.
no code implementations • CVPR 2016 • Wen Li, Dengxin Dai, Mingkui Tan, Dong Xu, Luc van Gool
The SVM+ approach has shown excellent performance in visual recognition tasks for exploiting privileged information in the training data.
1 code implementation • 15 Jun 2016 • Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc van Gool
In this paper, a new method for generating object and action proposals in images and videos is proposed.
no code implementations • 26 Jul 2016 • Jiqing Wu, Radu Timofte, Luc van Gool
Unlike other methods adapted to different tasks, our method uses the exact same convolutional network architecture to address both image denois- ing and single image super-resolution.
1 code implementation • 2 Aug 2016 • Yuanjun Xiong, Li-Min Wang, Zhe Wang, Bo-Wen Zhang, Hang Song, Wei Li, Dahua Lin, Yu Qiao, Luc van Gool, Xiaoou Tang
This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016.
19 code implementations • 2 Aug 2016 • Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc van Gool
The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
Ranked #3 on Multimodal Activity Recognition on EV-Action
1 code implementation • 9 Aug 2016 • Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool
We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs).
no code implementations • IJCV 2016 • Rasmus Rothe, Radu Timofte, Luc van Gool
In this paper we propose a deep learning solution to age estimation from a single face image without the use of facial landmarks and introduce the IMDB-WIKI dataset, the largest public dataset of face images with age and gender labels.
Ranked #3 on Age Estimation on ChaLearn 2015
no code implementations • CVPR 2016 • Ali Diba, Ali Mohammad Pazandeh, Hamed Pirsiavash, Luc van Gool
On the other hand, we let an iteration of feature learning and patch clustering purify the set of dedicated patches that we use.
no code implementations • 15 Aug 2016 • Zhiwu Huang, Luc van Gool
Symmetric 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.
no code implementations • 15 Aug 2016 • Zhiwu Huang, Ruiping Wang, Shiguang Shan, Luc van Gool, Xilin Chen
With this mapping, the problem of learning a cross-view metric between the two source heterogeneous spaces can be expressed as learning a single-view Euclidean distance metric in the target common Euclidean space.
no code implementations • 17 Aug 2016 • Zhiwu Huang, Ruiping Wang, Xianqiu Li, Wenxian Liu, Shiguang Shan, Luc van Gool, Xilin Chen
Specifically, by exploiting the Riemannian geometry of the manifold of fixed-rank Positive Semidefinite (PSD) matrices, we present a new solution to reduce optimizing over the space of column full-rank transformation matrices to optimizing on the PSD manifold which has a well-established Riemannian structure.
no code implementations • 23 Aug 2016 • Vivek Sharma, Luc van Gool
Image enhancement using the visible (V) and near-infrared (NIR) usually enhances useful image details.
no code implementations • 23 Aug 2016 • Andreas Steger, Radu Timofte, Luc van Gool
Most face applications depend heavily on the accuracy of the face and facial landmarks detectors employed.
no code implementations • 31 Aug 2016 • Ali Diba, Ali Mohammad Pazandeh, Luc van Gool
The 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.
no code implementations • 1 Sep 2016 • Limin Wang, Zhe Wang, Yu Qiao, Luc van Gool
These newly designed transferring techniques exploit multi-task learning frameworks to incorporate extra knowledge from other networks and additional datasets into the training procedure of event CNNs.
1 code implementation • 5 Sep 2016 • Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool
This paper presents Deep Retinal Image Understanding (DRIU), a unified framework of retinal image analysis that provides both retinal vessel and optic disc segmentation.
no code implementations • 5 Sep 2016 • András Bódis-Szomorú, Hayko Riemenschneider, Luc van Gool
Airborne 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 incomplete for higher floors and often totally misses out on pedestrian-only areas or undriven districts.
no code implementations • 12 Sep 2016 • Julien Weissenberg, Hayko Riemenschneider, Ralf Dragon, Luc van Gool
We evaluate DFS on two problems: First, the Knapsack problem, for which efficient algorithms exist, serves as a toy example.
8 code implementations • CVPR 2017 • Sergi Caelles, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Laura Leal-Taixé, Daniel Cremers, Luc van Gool
This paper tackles the task of semi-supervised video object segmentation, i. e., the separation of an object from the background in a video, given the mask of the first frame.
no code implementations • 17 Nov 2016 • Zhiwu Huang, Jiqing Wu, Luc van Gool
Learning representations on Grassmann manifolds is popular in quite a few visual recognition tasks.
2 code implementations • CVPR 2017 • Ali Diba, Vivek Sharma, Luc van Gool
Advantages of TLEs are: (a) they encode the entire video into a compact feature representation, learning the semantics and a discriminative feature space; (b) they are applicable to all kinds of networks like 2D and 3D CNNs for video classification; and (c) they model feature interactions in a more expressive way and without loss of information.
no code implementations • CVPR 2017 • Ali Diba, Vivek Sharma, Ali Pazandeh, Hamed Pirsiavash, Luc van Gool
The final stage of both architectures is a part of a convolutional neural network that performs multiple instance learning on proposals extracted in the previous stage(s).
Ranked #2 on Weakly Supervised Object Detection on ImageNet
no code implementations • ICCV 2017 • Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Tinne Tuytelaars, Luc van Gool
How much does a single image reveal about the environment it was taken in?
no code implementations • WS 2016 • Shurong Sheng, Luc van Gool, Marie-Francine Moens
In this paper, we introduce the construction of a golden standard dataset that will aid research of multimodal question answering in the cultural heritage domain.
no code implementations • CVPR 2017 • Zhiwu Huang, Chengde Wan, Thomas Probst, Luc van Gool
In recent years, skeleton-based action recognition has become a popular 3D classification problem.
no code implementations • 23 Dec 2016 • Louis Lettry, Kenneth Vanhoey, Luc van Gool
We present a new deep supervised learning method for intrinsic decomposition of a single image into its albedo and shading components.
1 code implementation • 3 Jan 2017 • Naoya Takahashi, Michael Gygli, Luc van Gool
Instead, combining visual features with our AENet features, which can be computed efficiently on a GPU, leads to significant performance improvements on action recognition and video highlight detection.
2 code implementations • 17 Jan 2017 • Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool
We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs).
no code implementations • CVPR 2017 • Chengde Wan, Thomas Probst, Luc van Gool, Angela Yao
Regressing the hand pose can then be done by learning a discriminator to estimate the posterior of the latent pose given some depth maps.
1 code implementation • 27 Feb 2017 • Joachim D. Curtó, Irene C. Zarza, Feng Yang, Alexander J. Smola, Fernando de la Torre, Chong-Wah Ngo, Luc van Gool
The algorithm requires to compute the product of Walsh Hadamard Transform (WHT) matrices.
no code implementations • ICCV 2017 • Santiago Manen, Michael Gygli, Dengxin Dai, Luc van Gool
We further validate our approach by crowdsourcing the PathTrack dataset, with more than 15, 000 person trajectories in 720 sequences.
2 code implementations • CVPR 2017 • Limin Wang, Yuanjun Xiong, Dahua Lin, Luc van Gool
We exploit the learned models for action recognition (WSR) and detection (WSD) on the untrimmed video datasets of THUMOS14 and ActivityNet.
Ranked #3 on Action Classification on ActivityNet-1.2
Weakly Supervised Action Localization Weakly-Supervised Action Recognition
1 code implementation • IEEE Winter Conference on Applications of Computer Vision (WACV) 2017 • Louis Lettry, Michal Perdoch, Kenneth Vanhoey, Luc van Gool
We propose a new approach for detecting repeated patterns on a grid in a single image.
1 code implementation • ICCV 2017 • Wilfried Hartmann, Silvano Galliani, Michal Havlena, Luc van Gool, Konrad Schindler
Estimating a depth map from multiple views of a scene is a fundamental task in computer vision.
no code implementations • CVPR 2017 • Jie Song, Li-Min Wang, Luc van Gool, Otmar Hilliges
Temporal information can provide additional cues about the location of body joints and help to alleviate these issues.
Ranked #4 on Pose Estimation on UPenn Action
no code implementations • 3 Apr 2017 • Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbeláez, Alex Sorkine-Hornung, Luc van Gool
The DAVIS Challenge follows up on the recent publication of DAVIS (Densely-Annotated VIdeo Segmentation), which has fostered the development of several novel state-of-the-art video object segmentation techniques.
no code implementations • NeurIPS 2017 • Eirikur Agustsson, Fabian Mentzer, Michael Tschannen, Lukas Cavigelli, Radu Timofte, Luca Benini, Luc van Gool
We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy.
no code implementations • 5 Apr 2017 • Jiqing Wu, Radu Timofte, Zhiwu Huang, Luc van Gool
Inspired by classification models, we propose a novel deep learning architecture for color (multichannel) image denoising and report on thousands of images from ImageNet dataset as well as commonly used imagery.
no code implementations • 6 Apr 2017 • Sergi Caelles, Yu-Hua Chen, Jordi Pont-Tuset, Luc van Gool
This 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.
3 code implementations • ICCV 2017 • Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Kenneth Vanhoey, Luc van Gool
Despite 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.
1 code implementation • 1 May 2017 • Arun Balajee Vasudevan, Michael Gygli, Anna Volokitin, Luc van Gool
Although 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.
1 code implementation • 1 May 2017 • Ted Zhang, Dengxin Dai, Tinne Tuytelaars, Marie-Francine Moens, Luc van Gool
This paper introduces speech-based visual question answering (VQA), the task of generating an answer given an image and a spoken question.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
11 code implementations • 8 May 2017 • Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc van Gool
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
Ranked #5 on Video Classification on COIN
no code implementations • 16 May 2017 • Wen Li, Li-Min Wang, Wei Li, Eirikur Agustsson, Jesse Berent, Abhinav Gupta, Rahul Sukthankar, Luc van Gool
The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset.
2 code implementations • NeurIPS 2017 • Liqian Ma, Xu Jia, Qianru Sun, Bernt Schiele, Tinne Tuytelaars, Luc van Gool
This 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.
Ranked #3 on Gesture-to-Gesture Translation on Senz3D
1 code implementation • 8 Jun 2017 • Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc van Gool
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
no code implementations • CVPR 2017 • Pablo Speciale, Danda Pani Paudel, Martin R. Oswald, Till Kroeger, Luc van Gool, Marc Pollefeys
While randomized methods like RANSAC are fast, they do not guarantee global optimality and fail to manage large amounts of outliers.
2 code implementations • 10 Jul 2017 • Kaili Wang, Yu-Hui Huang, Jose Oramas, Luc van Gool, Tinne Tuytelaars
Experiments on the Fashion 144k and a Pinterest-based dataset show that the automatic methods succeed at this task to a reasonable extent.
no code implementations • 13 Jul 2017 • Yifei Wang, Wen Li, Dengxin Dai, Luc van Gool
Our work builds on the recently proposed Deep CORAL method, which proposed to train a convolutional neural network and simultaneously minimize the Euclidean distance of convariance matrices between the source and target domains.
no code implementations • 28 Jul 2017 • Tatjana Chavdarova, Pierre Baqué, Stéphane Bouquet, Andrii Maksai, Cijo Jose, Louis Lettry, Pascal Fua, Luc van Gool, François Fleuret
People detection methods are highly sensitive to the perpetual occlusions among the targets.
1 code implementation • 8 Aug 2017 • Davy Neven, Bert de Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc van Gool
Most approaches for instance-aware semantic labeling traditionally focus on accuracy.
8 code implementations • 8 Aug 2017 • Bert De Brabandere, Davy Neven, Luc van Gool
In this work we propose to tackle the problem with a discriminative loss function, operating at the pixel level, that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step.
Ranked #4 on Multi-Human Parsing on MHP v1.0
no code implementations • 9 Aug 2017 • Wen Li, Li-Min Wang, Wei Li, Eirikur Agustsson, Luc van Gool
Our new WebVision database and relevant studies in this work would benefit the advance of learning state-of-the-art visual models with minimum supervision based on web data.
no code implementations • 25 Aug 2017 • Christos Sakaridis, Dengxin Dai, Luc van Gool
Due to the difficulty of collecting and annotating foggy images, we choose to generate synthetic fog on real images that depict clear-weather outdoor scenes, and then leverage these partially synthetic data for SFSU by employing state-of-the-art convolutional neural networks (CNN).
3 code implementations • 4 Sep 2017 • Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Kenneth Vanhoey, Luc van Gool
Low-end and compact mobile cameras demonstrate limited photo quality mainly due to space, hardware and budget constraints.
no code implementations • 17 Sep 2017 • Thomas Probst, Kevis-Kokitsi Maninis, Ajad Chhatkuli, Mouloud Ourak, Emmanuel Vander Poorten, Luc van Gool
In recent works, such interventions are conducted under a stereo-microscope, and with a robot-controlled surgical tool.
no code implementations • 18 Sep 2017 • Kevis-Kokitsi Maninis, Sergi Caelles, Yu-Hua Chen, Jordi Pont-Tuset, Laura Leal-Taixé, Daniel Cremers, Luc van Gool
Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames.
no code implementations • ICCV 2017 • Eirikur Agustsson, Radu Timofte, Luc van Gool
We propose the Anchored Regression Network (ARN), a nonlinear regression network which can be seamlessly integrated into various networks or can be used stand-alone when the features have already been fixed.
no code implementations • ICCV 2017 • Danda Pani Paudel, Adlane Habed, Luc van Gool
This paper addresses the problem of estimating the geometric transformation relating two distinct visual modalities (e. g. an image and a map, or a projective structure and a Euclidean 3D model) while relying only on semantic cues, such as semantically segmented regions or object bounding boxes.
no code implementations • 20 Oct 2017 • Vivek Sharma, Ali Diba, Davy Neven, Michael S. Brown, Luc van Gool, Rainer Stiefelhagen
In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception.
no code implementations • ICLR 2018 • Eirikur Agustsson, Alexander Sage, Radu Timofte, Luc van Gool
Generative 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.
no code implementations • 10 Nov 2017 • Arun Balajee Vasudevan, Dengxin Dai, Luc van Gool
This paper investigates Object Referring with Spoken Language (ORSpoken) by presenting two datasets and one novel approach.
1 code implementation • 18 Nov 2017 • Guillem Collell, Luc van Gool, Marie-Francine Moens
In contrast with prior work that restricts spatial templates to explicit spatial prepositions (e. g., "glass on table"), here we extend this concept to implicit spatial language, i. e., those relationships (generally actions) for which the spatial arrangement of the objects is only implicitly implied (e. g., "man riding horse").
no code implementations • 22 Nov 2017 • Ali Diba, Vivek Sharma, Rainer Stiefelhagen, Luc van Gool
We approach GANs with a novel training method and learning objective, to discover multiple object instances for three cases: 1) synthesizing a picture of a specific object within a cluttered scene; 2) localizing different categories in images for weakly supervised object detection; and 3) improving object discov- ery in object detection pipelines.
Ranked #2 on Weakly Supervised Object Detection on COCO test-dev
3 code implementations • 22 Nov 2017 • Ali Diba, Mohsen Fayyaz, Vivek Sharma, Amir Hossein Karami, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Luc van Gool
Thus, by finetuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e. g. Sports-1M, and finetuned on the target datasets, e. g. HMDB51/UCF101.
1 code implementation • CVPR 2018 • Chengde Wan, Thomas Probst, Luc van Gool, Angela Yao
Specifically, we decompose the pose parameters into a set of per-pixel estimations, i. e., 2D heat maps, 3D heat maps and unit 3D directional vector fields.
Ranked #4 on Hand Pose Estimation on MSRA Hands
2 code implementations • CVPR 2018 • Kevis-Kokitsi Maninis, Sergi Caelles, Jordi Pont-Tuset, Luc van Gool
This paper explores the use of extreme points in an object (left-most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos.
1 code implementation • CVPR 2018 • Limin Wang, Wei Li, Wen Li, Luc van Gool
Specifically, SMART blocks decouple the spatiotemporal learning module into an appearance branch for spatial modeling and a relation branch for temporal modeling.
Ranked #51 on Action Recognition on UCF101
no code implementations • CVPR 2018 • Qianru Sun, Liqian Ma, Seong Joon Oh, Luc van Gool, Bernt Schiele, Mario Fritz
As more and more personal photos are shared online, being able to obfuscate identities in such photos is becoming a necessity for privacy protection.
2 code implementations • 29 Nov 2017 • Miriam Bellver, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Xavier Giro-i-Nieto, Jordi Torres, Luc van Gool
A fully automatic technique for segmenting the liver and localizing its unhealthy tissues is a convenient tool in order to diagnose hepatic diseases and assess the response to the according treatments.
1 code implementation • 30 Nov 2017 • Bernhard Kratzwald, Zhiwu Huang, Danda Pani Paudel, Acharya Dinesh, Luc van Gool
In this paper, we aim to improve the state-of-the-art video generative adversarial networks (GANs) with a view towards multi-functional applications.
no code implementations • CVPR 2018 • Yuhua Chen, Wen Li, Luc van Gool
To this end, we propose a new reality oriented adaptation approach for urban scene semantic segmentation by learning from synthetic data.
1 code implementation • ECCV 2018 • Jiqing Wu, Zhiwu Huang, Janine Thoma, Dinesh Acharya, Luc van Gool
In many domains of computer vision, generative adversarial networks (GANs) have achieved great success, among which the family of Wasserstein GANs (WGANs) is considered to be state-of-the-art due to the theoretical contributions and competitive qualitative performance.
no code implementations • 4 Dec 2017 • Zhiwu Huang, Bernhard Kratzwald, Danda Pani Paudel, Jiqing Wu, Luc van Gool
This paper presents a new problem of unpaired face translation between images and videos, which can be applied to facial video prediction and enhancement.
no code implementations • 4 Dec 2017 • Carles Ventura, Jordi Pont-Tuset, Sergi Caelles, Kevis-Kokitsi Maninis, Luc van Gool
This paper tackles the task of estimating the topology of filamentary networks such as retinal vessels and road networks.
no code implementations • 5 Dec 2017 • Zhiwu Huang, Jiqing Wu, Luc van Gool
In addition, we recommend three benchmark datasets that are CIFAR-10 HSV/CB color images, ImageNet HSV/CB color images, UCL DT image datasets.
1 code implementation • CVPR 2018 • Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc van Gool, Bernt Schiele, Mario Fritz
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information.
Ranked #2 on Gesture-to-Gesture Translation on Senz3D
no code implementations • 11 Dec 2017 • Yu-Hui Huang, Xu Jia, Stamatios Georgoulis, Tinne Tuytelaars, Luc van Gool
Pixelwise semantic image labeling is an important, yet challenging, task with many applications.
no code implementations • CVPR 2018 • Alexander Sage, Eirikur Agustsson, Radu Timofte, Luc van Gool
We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training.
1 code implementation • 19 Dec 2017 • Asha Anoosheh, Eirikur Agustsson, Radu Timofte, Luc Van Gool
This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al.
Ranked #6 on Facial Expression Translation on CelebA
no code implementations • CVPR 2018 • Arun Balajee Vasudevan, Dengxin Dai, Luc van Gool
To that end, we present a new video dataset for OR, with 30, 000 objects over 5, 000 stereo video sequences annotated for their descriptions and gaze.
1 code implementation • CVPR 2018 • Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc van Gool
During training, the auto-encoder makes use of the context model to estimate the entropy of its representation, and the context model is concurrently updated to learn the dependencies between the symbols in the latent representation.
22 code implementations • 15 Feb 2018 • Davy Neven, Bert de Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc van Gool
By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation.
Ranked #15 on Lane Detection on TuSimple
no code implementations • 1 Mar 2018 • Sergi Caelles, Alberto Montes, Kevis-Kokitsi Maninis, Yu-Hua Chen, Luc van Gool, Federico Perazzi, Jordi Pont-Tuset
Motivated by the analysis of the results of the 2017 edition, the main track of the competition will be the same than in the previous edition (segmentation given the full mask of the objects in the first frame -- semi-supervised scenario).
no code implementations • 2 Mar 2018 • Louis Lettry, Kenneth Vanhoey, Luc van Gool
Machine 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.
8 code implementations • CVPR 2018 • Yuhua Chen, Wen Li, Christos Sakaridis, Dengxin Dai, Luc van Gool
The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
1 code implementation • ICLR 2018 • Robert Torfason, Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc van Gool
Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as classification and segmentation directly on the compressed representations produced by these compression methods.
no code implementations • ECCV 2018 • Alex Locher, Michal Havlena, Luc van Gool
Structure from Motion or the sparse 3D reconstruction out of individual photos is a long studied topic in computer vision.
no code implementations • ECCV 2018 • Simon Hecker, Dengxin Dai, Luc van Gool
In particular, we develop a sensor setup that provides data for a 360-degree view of the area surrounding the vehicle, the driving route to the destination, and low-level driving maneuvers (e. g. steering angle and speed) by human drivers.
no code implementations • 29 Mar 2018 • Zheng Liu, Jie Qin, Annan Li, Yunhong Wang, Luc van Gool
Specifically, instead of learning explicit projections or adding fully-connected mapping layers, the proposed Adversarial Binary Coding (ABC) framework guides the extraction of binary codes implicitly and effectively.
no code implementations • 6 Apr 2018 • Dengxin Dai, Wen Li, Till Kroeger, Luc van Gool
We mitigate this by introducing ensemble manifold segmentation (EMS).
no code implementations • CVPR 2018 • Yuhua Chen, Jordi Pont-Tuset, Alberto Montes, Luc van Gool
This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest.
Ranked #66 on Semi-Supervised Video Object Segmentation on DAVIS 2016
no code implementations • CVPR 2018 • Atsushi Kanehira, Luc van Gool, Yoshitaka Ushiku, Tatsuya Harada
To satisfy these requirements (A)-(C) simultaneously, we proposed a novel video summarization method from multiple groups of videos.
1 code implementation • ICCV 2019 • Eirikur Agustsson, Michael Tschannen, Fabian Mentzer, Radu Timofte, Luc van Gool
We present a learned image compression system based on GANs, operating at extremely low bitrates.
no code implementations • 4 May 2018 • Simon Hecker, Dengxin Dai, Luc van Gool
This work presents a method to learn to predict the occurrence of these failures, i. e. to assess how difficult a scene is to a given driving model and to possibly give the human driver an early headsup.
1 code implementation • 13 May 2018 • Dinesh Acharya, Zhiwu Huang, Danda Paudel, Luc van Gool
In this work, we explore the benefits of using a man- ifold network structure for covariance pooling to improve facial expression recognition.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • ICLR 2019 • Liqian Ma, Xu Jia, Stamatios Georgoulis, Tinne Tuytelaars, Luc van Gool
Experimental results on various datasets show that EGSC-IT does not only translate the source image to diverse instances in the target domain, but also preserves the semantic consistency during the process.
no code implementations • CVPR 2018 • Vivek Sharma, Ali Diba, Davy Neven, Michael S. Brown, Luc van Gool, Rainer Stiefelhagen
In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception.
no code implementations • CVPR 2018 • Tatjana Chavdarova, Pierre Baqué, Stéphane Bouquet, Andrii Maksai, Cijo Jose, Timur Bagautdinov, Louis Lettry, Pascal Fua, Luc van Gool, François Fleuret
People detection methods are highly sensitive to occlusions between pedestrians, which are extremely frequent in many situations where cameras have to be mounted at a limited height.
no code implementations • CVPR 2018 • Pablo Speciale, Danda P. Paudel, Martin R. Oswald, Hayko Riemenschneider, Luc van Gool, Marc Pollefeys
We propose a novel method for the geometric registration of semantically labeled regions.
no code implementations • ECCV 2018 • Ali Diba, Mohsen Fayyaz, Vivek Sharma, M. Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc van Gool
Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets.
no code implementations • ECCV 2018 • Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc van Gool
In this paper, we formulate the model-free consensus maximization as an Integer Program in a graph using `rules' on measurements.
no code implementations • 30 Jul 2018 • Shuhang Gu, Radu Timofte, Luc van Gool
Tremendous advances in image restoration tasks such as denoising and super-resolution have been achieved using neural networks.
no code implementations • ECCV 2018 • Christos Sakaridis, Dengxin Dai, Simon Hecker, Luc van Gool
In addition, we present three other main stand-alone contributions: 1) a novel method to add synthetic fog to real, clear-weather scenes using semantic input; 2) a new fog density estimator; 3) the Foggy Zurich dataset comprising $3808$ real foggy images, with pixel-level semantic annotations for $16$ images with dense fog.
no code implementations • ECCV 2018 • Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
In this paper we present a method for incremental Non-Rigid Structure-from-Motion (NRSfM) with the perspective camera model and the isometric surface prior with unknown focal length.
1 code implementation • 28 Aug 2018 • Carles Ventura, Jordi Pont-Tuset, Sergi Caelles, Kevis-Kokitsi Maninis, Luc van Gool
This paper tackles the task of estimating the topology of road networks from aerial images.
no code implementations • ECCV 2018 • Danda Pani Paudel, Luc van Gool
This paper addresses the problem of robustly autocalibrating a moving camera with constant intrinsics.
1 code implementation • ECCV 2018 • Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen, Luc van Gool
The generative model learns a mapping that the distributions of sketches can be indistinguishable from the distribution of natural images using an adversarial loss, and simultaneously learns an inverse mapping based on the cycle consistency loss in order to enhance the indistinguishability.
no code implementations • ECCV 2018 • Mengshi Qi, Jie Qin, Annan Li, Yunhong Wang, Jiebo Luo, Luc van Gool
Group activity recognition plays a fundamental role in a variety of applications, e. g. sports video analysis and intelligent surveillance.
1 code implementation • 26 Sep 2018 • Asha Anoosheh, Torsten Sattler, Radu Timofte, Marc Pollefeys, Luc van Gool
We then compare the daytime and translated night images to obtain a pose estimate for the night image using the known 6-DOF position of the closest day image.
1 code implementation • 2 Oct 2018 • Andrey Ignatov, Radu Timofte, William Chou, Ke Wang, Max Wu, Tim Hartley, Luc van Gool
Over 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.
no code implementations • 3 Oct 2018 • Andrey Ignatov, Radu Timofte, Thang Van Vu, Tung Minh Luu, Trung X. Pham, Cao Van Nguyen, Yongwoo Kim, Jae-Seok Choi, Munchurl Kim, Jie Huang, Jiewen Ran, Chen Xing, Xingguang Zhou, Pengfei Zhu, Mingrui Geng, Yawei Li, Eirikur Agustsson, Shuhang Gu, Luc van Gool, Etienne de Stoutz, Nikolay Kobyshev, Kehui Nie, Yan Zhao, Gen Li, Tong Tong, Qinquan Gao, Liu Hanwen, Pablo Navarrete Michelini, Zhu Dan, Hu Fengshuo, Zheng Hui, Xiumei Wang, Lirui Deng, Rang Meng, Jinghui Qin, Yukai Shi, Wushao Wen, Liang Lin, Ruicheng Feng, Shixiang Wu, Chao Dong, Yu Qiao, Subeesh Vasu, Nimisha Thekke Madam, Praveen Kandula, A. N. Rajagopalan, Jie Liu, Cheolkon Jung
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
1 code implementation • 4 Oct 2018 • Dinesh Acharya, Zhiwu Huang, Danda Pani Paudel, Luc van Gool
Furthermore, we introduce a sliced version of Wasserstein GAN (SWGAN) loss to improve the distribution learning on the video data of high-dimension and mixed-spatiotemporal distribution.
no code implementations • 5 Oct 2018 • Dengxin Dai, Luc van Gool
This work addresses the problem of semantic image segmentation of nighttime scenes.
Ranked #12 on Semantic Segmentation on Nighttime Driving
3 code implementations • CVPR 2019 • Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc van Gool
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000.
Ranked #3 on Image Compression on ImageNet32
no code implementations • 5 Dec 2018 • Kaili Wang, Liqian Ma, Jose Oramas, Luc van Gool, Tinne Tuytelaars
We address the problem of unpaired geometric image-to-image translation.
1 code implementation • 10 Dec 2018 • Andrés Romero, Pablo Arbeláez, Luc van Gool, Radu Timofte
This problem is highly challenging due to three main reasons: (i) unpaired datasets, (ii) multiple attributes, and (iii) the multimodality (e. g., style) associated with the translation.
no code implementations • CVPR 2019 • Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Thomas Probst, Luc van Gool
The problem of localization often arises as part of a navigation process.
no code implementations • CVPR 2019 • Yuhua Chen, Wen Li, Xiaoran Chen, Luc van Gool
In this work, we take the advantage of additional geometric information from synthetic data, a powerful yet largely neglected cue, to bridge the domain gap.
1 code implementation • CVPR 2019 • Rui Gong, Wen Li, Yu-Hua Chen, Luc van Gool
In 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.
1 code implementation • 31 Dec 2018 • Etienne de Stoutz, Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Luc van Gool
We extend upon the results of Ignatov et al., where they are able to translate images from compact mobile cameras into images with comparable quality to high-resolution photos taken by DSLR cameras.
1 code implementation • 5 Jan 2019 • Dengxin Dai, Christos Sakaridis, Simon Hecker, Luc van Gool
The method is based on the fact that the results of semantic segmentation in moderately adverse conditions (light fog) can be bootstrapped to solve the same problem in highly adverse conditions (dense fog).
Ranked #5 on Domain Adaptation on Cityscapes-to-FoggyDriving
1 code implementation • CVPR 2018 • Despoina Paschalidou, Ali Osman Ulusoy, Carolin Schmitt, Luc van Gool, Andreas Geiger
RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion.
1 code implementation • ICCV 2019 • Christos Sakaridis, Dengxin Dai, Luc van Gool
Our central contributions are: 1) a curriculum framework to gradually adapt semantic segmentation models from day to night via labeled synthetic images and unlabeled real images, both for progressively darker times of day, which exploits cross-time-of-day correspondences for the real images to guide the inference of their labels; 2) a novel uncertainty-aware annotation and evaluation framework and metric for semantic segmentation, designed for adverse conditions and including image regions beyond human recognition capability in the evaluation in a principled fashion; 3) the Dark Zurich dataset, which comprises 2416 unlabeled nighttime and 2920 unlabeled twilight images with correspondences to their daytime counterparts plus a set of 151 nighttime images with fine pixel-level annotations created with our protocol, which serves as a first benchmark to perform our novel evaluation.
Ranked #7 on Semantic Segmentation on Nighttime Driving
1 code implementation • 1 Feb 2019 • Wouter Van Gansbeke, Bert de Brabandere, Davy Neven, Marc Proesmans, Luc van Gool
The problem with such a two-step approach is that the parameters of the network are not optimized for the true task of interest (estimating the lane curvature parameters) but for a proxy task (segmenting the lane markings), resulting in sub-optimal performance.
2 code implementations • 6 Feb 2019 • Ankit Dhall, Dengxin Dai, Luc van Gool
In this work, we leverage the unique structure of traffic cones and propose a pipelined approach to the problem.
1 code implementation • arXiv 2019 • Wouter Van Gansbeke, Davy Neven, Bert de Brabandere, Luc van Gool
For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions.
1 code implementation • 14 Feb 2019 • Wouter Van Gansbeke, Davy Neven, Bert de Brabandere, Luc van Gool
However, we additionally propose a fusion method with RGB guidance from a monocular camera in order to leverage object information and to correct mistakes in the sparse input.
Ranked #5 on Depth Completion on KITTI Depth Completion
no code implementations • 8 Mar 2019 • Simon Vandenhende, Bert de Brabandere, Davy Neven, Luc van Gool
The generator's objective is to synthesize samples that are both realistic and hard to label for the classifier.
no code implementations • 26 Mar 2019 • Simon Hecker, Dengxin Dai, Luc van Gool
Our model is trained and evaluated on the Drive360 dataset, which features 60 hours and 3000 km of real-world driving data.
no code implementations • 28 Mar 2019 • Sergi Caelles, Albert Pumarola, Francesc Moreno-Noguer, Alberto Sanfeliu, Luc van Gool
To achieve this, we concentrate all the heavy computational load to the training phase with two critics that enforce spatial and temporal mask consistency over the last K frames.
no code implementations • ICLR 2020 • Simon Vandenhende, Stamatios Georgoulis, Bert de Brabandere, Luc van Gool
In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand.
1 code implementation • CVPR 2019 • Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc van Gool
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
Ranked #1 on Video Generation on TrailerFaces
2 code implementations • ICCV 2019 • Goutam Bhat, Martin Danelljan, Luc van Gool, Radu Timofte
The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking.
Ranked #5 on Object Tracking on FE108
no code implementations • 18 Apr 2019 • Liqian Ma, Qianru Sun, Bernt Schiele, Luc van Gool
Image-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.
no code implementations • ICCV 2019 • Ali Diba, Vivek Sharma, Luc van Gool, Rainer Stiefelhagen
With these overall objectives, to this end, we introduce a novel unified spatio-temporal 3D-CNN architecture (DynamoNet) that jointly optimizes the video classification and learning motion representation by predicting future frames as a multi-task learning problem.
1 code implementation • ECCV 2020 • Ali Diba, Mohsen Fayyaz, Vivek Sharma, Manohar Paluri, Jurgen Gall, Rainer Stiefelhagen, Luc van Gool
HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semantic aspects in the dynamic scene.
Ranked #11 on Action Recognition on UCF101
no code implementations • 2 May 2019 • Sergi Caelles, Jordi Pont-Tuset, Federico Perazzi, Alberto Montes, Kevis-Kokitsi Maninis, Luc van Gool
We present the 2019 DAVIS Challenge on Video Object Segmentation, the third edition of the DAVIS Challenge series, a public competition designed for the task of Video Object Segmentation (VOS).
1 code implementation • ICCV 2019 • Qin Wang, Wen Li, Luc van Gool
We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled samples, which often leads to a considerable empirical distribution mismatch between labeled data and unlabeled data.
1 code implementation • CVPR 2019 • Yawei Li, Vagia Tsiminaki, Radu Timofte, Marc Pollefeys, Luc van Gool
Experimental results demonstrate that our proposed networks successfully incorporate the 3D geometric information and super-resolve the texture maps.
no code implementations • 11 Jun 2019 • Anton Obukhov, Stamatios Georgoulis, Dengxin Dai, Luc van Gool
State-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.
Image Segmentation Weakly supervised Semantic Segmentation +1
4 code implementations • CVPR 2019 • Davy Neven, Bert de Brabandere, Marc Proesmans, Luc van Gool
In this work we propose a new clustering loss function for proposal-free instance segmentation.
Ranked #1000000000 on Instance Segmentation on Cityscapes test
no code implementations • 12 Jul 2019 • Simon Hecker, Alexander Liniger, Henrik Maurenbrecher, Dengxin Dai, Luc van Gool
Our contributes are fourfold: 1) we predict the motorcycle's intra-lane position using a convolutional neural network (CNN), 2) we predict the motorcycle roll angle using a CNN, 3) we use an upgraded controller model that incorporates road incline for a more realistic model and prediction, 4) we design a scale-able system by utilizing HERE Technologies map database to obtain the accurate road geometry of the future path.
no code implementations • ECCV 2020 • Chengde Wan, Thomas Probst, Luc van Gool, Angela Yao
In the first stage, the network estimates a dense correspondence field for every pixel on the depth map or image grid to the mesh grid.
3 code implementations • ICCV 2019 • Yawei Li, Shuhang Gu, Luc van Gool, Radu Timofte
Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images.
no code implementations • 29 Aug 2019 • Jan-Nico Zaech, Dengxin Dai, Martin Hahner, Luc van Gool
Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving.
1 code implementation • 18 Sep 2019 • Samarth Shukla, Luc van Gool, Radu Timofte
Recent advances in generative models and adversarial training have led to a flourishing image-to-image (I2I) translation literature.
1 code implementation • IJCNLP 2019 • Thierry Deruyttere, Simon Vandenhende, Dusan Grujicic, Luc van Gool, Marie-Francine Moens
Or more specifically, we consider the problem in an autonomous driving setting, where a passenger requests an action that can be associated with an object found in a street scene.
no code implementations • ICCV 2019 • Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
Notably, we further exploit the POP formulation of non-minimal solver also for the generic consensus maximization problems in 3D vision.
no code implementations • 4 Oct 2019 • Arun Balajee Vasudevan, Dengxin Dai, Luc van Gool
Our first contribution is the creation of a large-scale dataset with verbal navigation instructions.
2 code implementations • 9 Oct 2019 • Martin Hahner, Dengxin Dai, Christos Sakaridis, Jan-Nico Zaech, Luc van Gool
This work addresses the problem of semantic scene understanding under foggy road conditions.
no code implementations • 15 Oct 2019 • Andrey Ignatov, Radu Timofte, Andrei Kulik, Seungsoo Yang, Ke Wang, Felix Baum, Max Wu, Lirong Xu, Luc van Gool
The performance of mobile AI accelerators has been evolving rapidly in the past two years, nearly doubling with each new generation of SoCs.
no code implementations • 23 Oct 2019 • Zhiwu Huang, Danda Pani Paudel, Guanju Li, Jiqing Wu, Radu Timofte, Luc van Gool
This paper introduces a divide-and-conquer inspired adversarial learning (DACAL) approach for photo enhancement.
no code implementations • 9 Dec 2019 • Qi Dai, Vaishakh Patil, Simon Hecker, Dengxin Dai, Luc van Gool, Konrad Schindler
We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video.