arXiv subjects

Luc Van Gool

Publications and source records attributed to Luc Van Gool.

At least 613 records · Page 34Linked to original sources

arXiv2017

Temporal Segment Networks for Action Recognition in Videos

Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework for learning action models in videos. This method, called temporal segment network (TSN), aims to model long-range temporal structures with a new segment-based sampling and aggregation module. This unique design enables our TSN to efficiently learn action models by using the whole action videos. The learned models could be easily adapted for action recognition in both trimmed and untrimmed videos with simple average pooling and multi-scale temporal window integration, respectively. We also study a series of good practices for the instantiation of TSN framework given limited training samples. Our approach obtains the state-the-of-art performance on four challenging action recognition benchmarks: HMDB51 (71.0%), UCF101 (94.9%), THUMOS14 (80.1%), and ActivityNet v1.2 (89.6%). Using the proposed RGB difference for motion models, our method can still achieve competitive accuracy on UCF101 (91.0%) while running at 340 FPS. 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.

cs.CV↗

arXiv2017

Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks

We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for multi-scale contour detection and it uses a novel sparse boundary representation for hierarchical segmentation; it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments for low-level applications on BSDS, PASCAL Context, PASCAL Segmentation, and NYUD to evaluate boundary detection performance, showing that COB provides state-of-the-art contours and region hierarchies in all datasets. We also evaluate COB on high-level tasks when coupled with multiple pipelines for object proposals, semantic contours, semantic segmentation, and object detection on MS-COCO, SBD, and PASCAL; showing that COB also improves the results for all tasks.

cs.CV↗

arXiv2017

One-Shot Video Object Segmentation

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. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).

cs.CV↗

arXiv2017

Deep Learning on Lie Groups for Skeleton-based Action Recognition

In 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 warping, and then shallowly learn favorable Lie group features. In this paper we incorporate the Lie group structure into a deep network architecture to learn more appropriate Lie group features for 3D action recognition. Within the network structure, we design rotation mapping layers to transform the input Lie group features into desirable ones, which are aligned better in the temporal domain. To reduce the high feature dimensionality, the architecture is equipped with rotation pooling layers for the elements on the Lie group. Furthermore, we propose a logarithm mapping layer to map the resulting manifold data into a tangent space that facilitates the application of regular output layers for the final classification. Evaluations of the proposed network for standard 3D human action recognition datasets clearly demonstrate its superiority over existing shallow Lie group feature learning methods as well as most conventional deep learning methods.

cs.CV↗

arXiv2017

On the Relation between Color Image Denoising and Classification

Large 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 scale dataset. 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. We study the importance of (sufficient) training data, how semantic class information can be traded for improved denoising results. As a result, our method greatly improves PSNR performance by 0.34 - 0.51 dB on average over state-of-the art methods on large scale dataset. We conclude that it is beneficial to incorporate in classification models. On the other hand, we also study how noise affect classification performance. In the end, we come to a number of interesting conclusions, some being counter-intuitive.

cs.CV↗

arXiv2017

Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos

Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no examples in training data sets. Temporal information can provide additional cues about the location of body joints and help to alleviate these issues. In this paper, we propose a deep structured model to estimate a sequence of human poses in unconstrained videos. This model can be efficiently trained in an end-to-end manner and is capable of representing appearance of body joints and their spatio-temporal relationships simultaneously. Domain knowledge about the human body is explicitly incorporated into the network providing effective priors to regularize the skeletal structure and to enforce temporal consistency. The proposed end-to-end architecture is evaluated on two widely used benchmarks (Penn Action dataset and JHMDB dataset) for video-based pose estimation. Our approach significantly outperforms the existing state-of-the-art methods.

cs.CV↗

arXiv2017

PathTrack: Fast Trajectory Annotation with Path Supervision

Progress 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 the annotator loosely follows the object with the cursor while watching the video, providing a path annotation for each object in the sequence. Our approach is able to turn such weak annotations into dense box trajectories. Our experiments on existing datasets prove that our framework produces more accurate annotations than the state of the art, in a fraction of the time. We further validate our approach by crowdsourcing the PathTrack dataset, with more than 15,000 person trajectories in 720 sequences. Tracking approaches can benefit training on such large-scale datasets, as did object recognition. We prove this by re-training an off-the-shelf person matching network, originally trained on the MOT15 dataset, almost halving the misclassification rate. Additionally, training on our data consistently improves tracking results, both on our dataset and on MOT15. On the latter, we improve the top-performing tracker (NOMT) dropping the number of IDSwitches by 18% and fragments by 5%.

cs.CV↗

arXiv2017

Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video

Riemannian manifolds have been widely employed for video representations in visual classification tasks including video-based face recognition. The success mainly derives from learning a discriminant Riemannian metric which encodes the non-linear geometry of the underlying Riemannian manifolds. In this paper, we propose a novel metric learning framework to learn a distance metric across a Euclidean space and a Riemannian manifold to fuse the average appearance and pattern variation of faces within one video. The proposed metric learning framework can handle three typical tasks of video-based face recognition: Video-to-Still, Still-to-Video and Video-to-Video settings. To accomplish this new framework, by exploiting typical Riemannian geometries for kernel embedding, we map the source Euclidean space and Riemannian manifold into a common Euclidean subspace, each through a corresponding high-dimensional Reproducing Kernel Hilbert Space (RKHS). 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. By learning information on heterogeneous data with the shared label, the discriminant metric in the common space improves face recognition from videos. Extensive experiments on four challenging video face databases demonstrate that the proposed framework has a clear advantage over the state-of-the-art methods in the three classical video-based face recognition tasks.

cs.CV↗

arXiv2017

AENet: Learning Deep Audio Features for Video Analysis

We 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 due to the lack of clear sub-word units that are present in speech. In order to incorporate this long-time frequency structure of audio events, we introduce a convolutional neural network (CNN) operating on a large temporal input. In contrast to previous works this allows us to train an audio event detection system end-to-end. The combination of our network architecture and a novel data augmentation outperforms previous methods for audio event detection by 16%. Furthermore, we perform transfer learning and show that our model learnt generic audio features, similar to the way CNNs learn generic features on vision tasks. In video analysis, combining visual features and traditional audio features such as MFCC typically only leads to marginal improvements. 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. In video highlight detection, our audio features improve the performance by more than 8% over visual features alone.

cs.MM↗

arXiv2016

A Riemannian Network for SPD Matrix Learning

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. In this paper we build a Riemannian network architecture to open up a new direction of SPD matrix non-linear learning in a deep model. In particular, we devise bilinear mapping layers to transform input SPD matrices to more desirable SPD matrices, exploit eigenvalue rectification layers to apply a non-linear activation function to the new SPD matrices, and design an eigenvalue logarithm layer to perform Riemannian computing on the resulting SPD matrices for regular output layers. For training the proposed deep network, we exploit a new backpropagation with a variant of stochastic gradient descent on Stiefel manifolds to update the structured connection weights and the involved SPD matrix data. We show through experiments that the proposed SPD matrix network can be simply trained and outperform existing SPD matrix learning and state-of-the-art methods in three typical visual classification tasks.

cs.CV↗

arXiv2016

Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection

We 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 to the lack of a clear sub-word unit. In order to incorporate the long-time frequency structure for AED, we introduce a convolutional neural network (CNN) with a large input field. In contrast to previous works, this enables to train audio event detection end-to-end. Our architecture is inspired by the success of VGGNet and uses small, 3x3 convolutions, but more depth than previous methods in AED. In order to prevent over-fitting and to take full advantage of the modeling capabilities of our network, we further propose a novel data augmentation method to introduce data variation. Experimental results show that our CNN significantly outperforms state of the art methods including Bag of Audio Words (BoAW) and classical CNNs, achieving a 16% absolute improvement.

cs.SD↗

arXiv2016

Weakly Supervised Cascaded Convolutional Networks

Object detection is a challenging task in visual understanding domain, and even more so if the supervision is to be weak. Recently, few efforts to handle the task without expensive human annotations is established by promising deep neural network. A new architecture of cascaded networks is proposed to learn a convolutional neural network (CNN) under such conditions. We introduce two such architectures, with either two cascade stages or three which are trained in an end-to-end pipeline. The first stage of both architectures extracts best candidate of class specific region proposals by training a fully convolutional network. In the case of the three stage architecture, the middle stage provides object segmentation, using the output of the activation maps of first stage. 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). Our experiments on the PASCAL VOC 2007, 2010, 2012 and large scale object datasets, ILSVRC 2013, 2014 datasets show improvements in the areas of weakly-supervised object detection, classification and localization.

cs.CV↗

arXiv2016

Deep Temporal Linear Encoding Networks

The 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 sequences. We present a new video representation, called temporal linear encoding (TLE) and embedded inside of CNNs as a new layer, which captures the appearance and motion throughout entire videos. It encodes this aggregated information into a robust video feature representation, via end-to-end learning. 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. We conduct experiments on two challenging human action datasets: HMDB51 and UCF101. The experiments show that TLE outperforms current state-of-the-art methods on both datasets.

cs.CV↗

arXiv2016

Dilemma First Search for Effortless Optimization of NP-Hard Problems

To 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. Second, meta-heuristics are easier to implement but comparatively inefficient. As a result, a number of problems have been left unoptimized and plain greedy solutions are used. We introduce a theoretical framework and propose a powerful yet simple search method called Dilemma First Search (DFS). DFS exploits the decision heuristic needed for the greedy solution for further optimization. DFS is useful when it is hard to design efficient exact inference. We evaluate DFS on two problems: First, the Knapsack problem, for which efficient algorithms exist, serves as a toy example. Second, Decision Tree inference, where state-of-the-art algorithms rely on the greedy or randomness-based solutions. We further show that decision trees benefit from optimizations that are performed in a fraction of the iterations required by a random-based search.

cs.DS↗

arXiv2016

Efficient Volumetric Fusion of Airborne and Street-Side Data for Urban Reconstruction

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. In this work, we introduce an approach that efficiently unifies a detailed street-side Structure-from-Motion (SfM) or Multi-View Stereo (MVS) point cloud and a coarser but more complete point cloud from airborne acquisition in a joint surface mesh. We propose a point cloud blending and a volumetric fusion based on ray casting across a 3D tetrahedralization (3DT), extended with data reduction techniques to handle large datasets. To the best of our knowledge, we are the first to adopt a 3DT approach for airborne/street-side data fusion. Our pipeline exploits typical characteristics of airborne and ground data, and produces a seamless, watertight mesh that is both complete and detailed. Experiments on 3D urban data from multiple sources and different data densities show the effectiveness and benefits of our approach.

cs.CV↗

arXiv2016

Deep Retinal Image Understanding

This paper presents Deep Retinal Image Understanding (DRIU), a unified framework of retinal image analysis that provides both retinal vessel and optic disc segmentation. We make use of deep Convolutional Neural Networks (CNNs), which have proven revolutionary in other fields of computer vision such as object detection and image classification, and we bring their power to the study of eye fundus images. DRIU uses a base network architecture on which two set of specialized layers are trained to solve both the retinal vessel and optic disc segmentation. We present experimental validation, both qualitative and quantitative, in four public datasets for these tasks. In all of them, DRIU presents super-human performance, that is, it shows results more consistent with a gold standard than a second human annotator used as control.

cs.CV↗

arXiv2016

Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification

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. One of the shortcoming of these methods is handling motion information extraction which is done out side of the CNNs and relatively time consuming also on GPUs. So proposing end-to-end methods which are exploring to learn motion representation, like 3D-CNN can achieve faster and accurate performance. We present some novel deep CNNs using 3D architecture to model actions and motion representation in an efficient way to be accurate and also as fast as real-time. Our new networks learn distinctive models to combine deep motion features into appearance model via learning optical flow features inside the network.

cs.CV↗

arXiv2016

Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images

Event recognition in still images is an intriguing problem and has potential for real applications. This paper addresses the problem of event recognition by proposing a convolutional neural network that exploits knowledge of objects and scenes for event classification (OS2E-CNN). Intuitively, it stands to reason that there exists a correlation among the concepts of objects, scenes, and events. We empirically demonstrate that the recognition of objects and scenes substantially contributes to the recognition of events. Meanwhile, we propose an iterative selection method to identify a subset of object and scene classes, which help to more efficiently and effectively transfer their deep representations to event recognition. Specifically, we develop three types of transferring techniques: (1) initialization-based transferring, (2) knowledge-based transferring, and (3) data-based transferring. 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. These multi-task learning frameworks turn out to be effective in reducing the effect of over-fitting and improving the generalization ability of the learned CNNs. With OS2E-CNN, we design a multi-ratio and multi-scale cropping strategy, and propose an end-to-end event recognition pipeline. We perform experiments on three event recognition benchmarks: the ChaLearn Cultural Event Recognition dataset, the Web Image Dataset for Event Recognition (WIDER), and the UIUC Sports Event dataset. The experimental results show that our proposed algorithm successfully adapts object and scene representations towards the event dataset and that it achieves the current state-of-the-art performance on these challenging datasets.

cs.CV↗