Muhammad Anwer Rao, Fahad Shahbaz Khan, Joost Van de Weijer, & Jorma Laaksonen. (2017). Top-Down Deep Appearance Attention for Action Recognition. In 20th Scandinavian Conference on Image Analysis (Vol. 10269, pp. 297–309). LNCS.
Abstract: Recognizing human actions in videos is a challenging problem in computer vision. Recently, convolutional neural network based deep features have shown promising results for action recognition. In this paper, we investigate the problem of fusing deep appearance and motion cues for action recognition. We propose a video representation which combines deep appearance and motion based local convolutional features within the bag-of-deep-features framework. Firstly, dense deep appearance and motion based local convolutional features are extracted from spatial (RGB) and temporal (flow) networks, respectively. Both visual cues are processed in parallel by constructing separate visual vocabularies for appearance and motion. A category-specific appearance map is then learned to modulate the weights of the deep motion features. The proposed representation is discriminative and binds the deep local convolutional features to their spatial locations. Experiments are performed on two challenging datasets: JHMDB dataset with 21 action classes and ACT dataset with 43 categories. The results clearly demonstrate that our approach outperforms both standard approaches of early and late feature fusion. Further, our approach is only employing action labels and without exploiting body part information, but achieves competitive performance compared to the state-of-the-art deep features based approaches.
Keywords: Action recognition; CNNs; Feature fusion
|
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.
|
Andrei Polzounov, Artsiom Ablavatski, Sergio Escalera, Shijian Lu, & Jianfei Cai. (2017). WordFences: Text Localization and Recognition. In 24th International Conference on Image Processing.
|
Maedeh Aghaei, Mariella Dimiccoli, & Petia Radeva. (2017). All the people around me: face clustering in egocentric photo streams. In 24th International Conference on Image Processing.
Abstract: arxiv1703.01790
Given an unconstrained stream of images captured by a wearable photo-camera (2fpm), we propose an unsupervised bottom-up approach for automatic clustering appearing faces into the individual identities present in these data. The problem is challenging since images are acquired under real world conditions; hence the visible appearance of the people in the images undergoes intensive variations. Our proposed pipeline consists of first arranging the photo-stream into events, later, localizing the appearance of multiple people in them, and
finally, grouping various appearances of the same person across different events. Experimental results performed on a dataset acquired by wearing a photo-camera during one month, demonstrate the effectiveness of the proposed approach for the considered purpose.
Keywords: face discovery; face clustering; deepmatching; bag-of-tracklets; egocentric photo-streams
|
Quentin Angermann, Jorge Bernal, Cristina Sanchez Montes, Maroua Hammami, Gloria Fernandez Esparrach, Xavier Dray, et al. (2017). Clinical Usability Quantification Of a Real-Time Polyp Detection Method In Videocolonoscopy. In 25th United European Gastroenterology Week.
|
Cristina Sanchez Montes, F. Javier Sanchez, Cristina Rodriguez de Miguel, Henry Cordova, Jorge Bernal, Maria Lopez Ceron, et al. (2017). Histological Prediction Of Colonic Polyps By Computer Vision. Preliminary Results. In 25th United European Gastroenterology Week.
Abstract: during colonoscopy, clinicians perform visual inspection of the polyps to predict histology. Kudo’s pit pattern classification is one of the most commonly used for optical diagnosis. These surface patterns present a contrast with respect to their neighboring regions and they can be considered as bright regions in the image that can attract the attention of computational methods.
Keywords: polyps; histology; computer vision
|
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
|
Daniel Hernandez, Lukas Schneider, Antonio Espinosa, David Vazquez, Antonio Lopez, Uwe Franke, et al. (2017). Slanted Stixels: Representing San Francisco's Steepest Streets. In 28th British Machine Vision Conference.
Abstract: In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced that uses an extremely efficient over-segmentation. In doing so, the computational complexity of the Stixel inference algorithm is reduced significantly, achieving real-time computation capabilities with only a slight drop in accuracy. We evaluate the proposed approach in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.
|
Arash Akbarinia, Raquel Gil Rodriguez, & C. Alejandro Parraga. (2017). Colour Constancy: Biologically-inspired Contrast Variant Pooling Mechanism. In 28th British Machine Vision Conference.
Abstract: Pooling is a ubiquitous operation in image processing algorithms that allows for higher-level processes to collect relevant low-level features from a region of interest. Currently, max-pooling is one of the most commonly used operators in the computational literature. However, it can lack robustness to outliers due to the fact that it relies merely on the peak of a function. Pooling mechanisms are also present in the primate visual cortex where neurons of higher cortical areas pool signals from lower ones. The receptive fields of these neurons have been shown to vary according to the contrast by aggregating signals over a larger region in the presence of low contrast stimuli. We hypothesise that this contrast-variant-pooling mechanism can address some of the shortcomings of maxpooling. We modelled this contrast variation through a histogram clipping in which the percentage of pooled signal is inversely proportional to the local contrast of an image. We tested our hypothesis by applying it to the phenomenon of colour constancy where a number of popular algorithms utilise a max-pooling step (e.g. White-Patch, Grey-Edge and Double-Opponency). For each of these methods, we investigated the consequences of replacing their original max-pooling by the proposed contrast-variant-pooling. Our experiments on three colour constancy benchmark datasets suggest that previous results can significantly improve by adopting a contrast-variant-pooling mechanism.
|
Rada Deeb, Damien Muselet, Mathieu Hebert, Alain Tremeau, & Joost Van de Weijer. (2017). 3D color charts for camera spectral sensitivity estimation. In 28th British Machine Vision Conference.
Abstract: Estimating spectral data such as camera sensor responses or illuminant spectral power distribution from raw RGB camera outputs is crucial in many computer vision applications.
Usually, 2D color charts with various patches of known spectral reflectance are
used as reference for such purpose. Deducing n-D spectral data (n»3) from 3D RGB inputs is an ill-posed problem that requires a high number of inputs. Unfortunately, most of the natural color surfaces have spectral reflectances that are well described by low-dimensional linear models, i.e. each spectral reflectance can be approximated by a weighted sum of the others. It has been shown that adding patches to color charts does not help in practice, because the information they add is redundant with the information provided by the first set of patches. In this paper, we propose to use spectral data of
higher dimensionality by using 3D color charts that create inter-reflections between the surfaces. These inter-reflections produce multiplications between natural spectral curves and so provide non-linear spectral curves. We show that such data provide enough information for accurate spectral data estimation.
|
Lasse Martensson, Anders Hast, & Alicia Fornes. (2017). Word Spotting as a Tool for Scribal Attribution. In 2nd Conference of the association of Digital Humanities in the Nordic Countries (pp. 87–89).
|
Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes Garcia-Martinez, Fethi Bougares, Loic Barrault, et al. (2017). LIUM-CVC Submissions for WMT17 Multimodal Translation Task. In 2nd Conference on Machine Translation.
Abstract: This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly explored two multimodal architectures where either global visual features or convolutional feature maps are integrated in order to benefit from visual context. Our final systems ranked first for both En-De and En-Fr language pairs according to the automatic evaluation metrics METEOR and BLEU.
|
Aniol Lidon, Marc Bolaños, Mariella Dimiccoli, Petia Radeva, Maite Garolera, & Xavier Giro. (2017). Semantic Summarization of Egocentric Photo-Stream Events. In 2nd Workshop on Lifelogging Tools and Applications.
|
Lluis Gomez, Y. Patel, Marçal Rusiñol, C.V. Jawahar, & Dimosthenis Karatzas. (2017). Self‐supervised learning of visual features through embedding images into text topic spaces. In 30th IEEE Conference on Computer Vision and Pattern Recognition.
Abstract: End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.
|
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.
|