Victor Vaquero, German Ros, Francesc Moreno-Noguer, Antonio Lopez, & Alberto Sanfeliu. (2017). Joint coarse-and-fine reasoning for deep optical flow. In 24th International Conference on Image Processing (pp. 2558–2562).
Abstract: We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets.
|
Cesar de Souza, Adrien Gaidon, Yohann Cabon, & Antonio Lopez. (2017). Procedural Generation of Videos to Train Deep Action Recognition Networks. In 30th IEEE Conference on Computer Vision and Pattern Recognition (pp. 2594–2604).
Abstract: Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for ”Procedural Human Action Videos”. It contains a total of 39, 982 videos, with more than 1, 000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly
outperforming fine-tuning state-of-the-art unsupervised generative models of videos.
|
Xinhang Song, Shuqiang Jiang, & Luis Herranz. (2017). Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold. TIP - IEEE Transactions on Image Processing, 26(6), 2721–2735.
Abstract: Before the big data era, scene recognition was often approached with two-step inference using localized intermediate representations (objects, topics, and so on). One of such approaches is the semantic manifold (SM), in which patches and images are modeled as points in a semantic probability simplex. Patch models are learned resorting to weak supervision via image labels, which leads to the problem of scene categories co-occurring in this semantic space. Fortunately, each category has its own co-occurrence patterns that are consistent across the images in that category. Thus, discovering and modeling these patterns are critical to improve the recognition performance in this representation. Since the emergence of large data sets, such as ImageNet and Places, these approaches have been relegated in favor of the much more powerful convolutional neural networks (CNNs), which can automatically learn multi-layered representations from the data. In this paper, we address many limitations of the original SM approach and related works. We propose discriminative patch representations using neural networks and further propose a hybrid architecture in which the semantic manifold is built on top of multiscale CNNs. Both representations can be computed significantly faster than the Gaussian mixture models of the original SM. To combine multiple scales, spatial relations, and multiple features, we formulate rich context models using Markov random fields. To solve the optimization problem, we analyze global and local approaches, where a top-down hierarchical algorithm has the best performance. Experimental results show that exploiting different types of contextual relations jointly consistently improves the recognition accuracy.
|
Yagmur Gucluturk, Umut Guclu, Marc Perez, Hugo Jair Escalante, Xavier Baro, Isabelle Guyon, et al. (2017). Visualizing Apparent Personality Analysis with Deep Residual Networks. In Chalearn Workshop on Action, Gesture, and Emotion Recognition: Large Scale Multimodal Gesture Recognition and Real versus Fake expressed emotions at ICCV (pp. 3101–3109).
Abstract: Automatic prediction of personality traits is a subjective task that has recently received much attention. Specifically, automatic apparent personality trait prediction from multimodal data has emerged as a hot topic within the filed of computer vision and, more particularly, the so called “looking
at people” sub-field. Considering “apparent” personality traits as opposed to real ones considerably reduces the subjectivity of the task. The real world applications are encountered in a wide range of domains, including entertainment, health, human computer interaction, recruitment and security. Predictive models of personality traits are useful for individuals in many scenarios (e.g., preparing for job interviews, preparing for public speaking). However, these predictions in and of themselves might be deemed to be untrustworthy without human understandable supportive evidence. Through a series of experiments on a recently released benchmark dataset for automatic apparent personality trait prediction, this paper characterizes the audio and
visual information that is used by a state-of-the-art model while making its predictions, so as to provide such supportive evidence by explaining predictions made. Additionally, the paper describes a new web application, which gives feedback on apparent personality traits of its users by combining
model predictions with their explanations.
|
Mikhail Mozerov, & Joost Van de Weijer. (2017). Improved Recursive Geodesic Distance Computation for Edge Preserving Filter. TIP - IEEE Transactions on Image Processing, 26(8), 3696–3706.
Abstract: All known recursive filters based on the geodesic distance affinity are realized by two 1D recursions applied in two orthogonal directions of the image plane. The 2D extension of the filter is not valid and has theoretically drawbacks, which lead to known artifacts. In this paper, a maximum influence propagation method is proposed to approximate the 2D extension for the
geodesic distance-based recursive filter. The method allows to partially overcome the drawbacks of the 1D recursion approach. We show that our improved recursion better approximates the true geodesic distance filter, and the application of this improved filter for image denoising outperforms the existing recursive implementation of the geodesic distance. As an application,
we consider a geodesic distance-based filter for image denoising.
Experimental evaluation of our denoising method demonstrates comparable and for several test images better results, than stateof-the-art approaches, while our algorithm is considerably fasterwith computational complexity O(8P).
Keywords: Geodesic distance filter; color image filtering; image enhancement
|
Alejandro Gonzalez Alzate, David Vazquez, Antonio Lopez, & Jaume Amores. (2017). On-Board Object Detection: Multicue, Multimodal, and Multiview Random Forest of Local Experts. Cyber - IEEE Transactions on cybernetics, 47(11), 3980–3990.
Abstract: Despite recent significant advances, object detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities, and a strong multiview (MV) classifier that accounts for different object views and poses. In this paper, we provide an extensive evaluation that gives insight into how each of these aspects (multicue, multimodality, and strong MV classifier) affect accuracy both individually and when integrated together. In the multimodality component, we explore the fusion of RGB and depth maps obtained by high-definition light detection and ranging, a type of modality that is starting to receive increasing attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the accuracy, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient.
Keywords: Multicue; multimodal; multiview; object detection
|
Xinhang Song, Shuqiang Jiang, & Luis Herranz. (2017). Combining Models from Multiple Sources for RGB-D Scene Recognition. In 26th International Joint Conference on Artificial Intelligence (pp. 4523–4529).
Abstract: Depth can complement RGB with useful cues about object volumes and scene layout. However, RGB-D image datasets are still too small for directly training deep convolutional neural networks (CNNs), in contrast to the massive monomodal RGB datasets. Previous works in RGB-D recognition typically combine two separate networks for RGB and depth data, pretrained with a large RGB dataset and then fine tuned to the respective target RGB and depth datasets. These approaches have several limitations: 1) only use low-level filters learned from RGB data, thus not being able to exploit properly depth-specific patterns, and 2) RGB and depth features are only combined at high-levels but rarely at lower-levels. In this paper, we propose a framework that leverages both knowledge acquired from large RGB datasets together with depth-specific cues learned from the limited depth data, obtaining more effective multi-source and multi-modal representations. We propose a multi-modal combination method that selects discriminative combinations of layers from the different source models and target modalities, capturing both high-level properties of the task and intrinsic low-level properties of both modalities.
Keywords: Robotics and Vision; Vision and Perception
|
