To better learn the dependency relationship between nodes, we address the relationship extraction task by capturing rich contextual dependencies based on the attention mechanism, and using distributional reinforcement learning to generate optimal relation information representation. This method is called Dual Attention Graph Convolutional Network (DAGCN), to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of GCN, which model the semantic interdependencies in spatial and relational dimensions respectively. The position attention module selectively aggregates the feature at each position by a weighted sum of the features at all positions of nodes internal features. Meanwhile, the relation attention module selectively emphasizes interdependent node relations by integrating associated features among all nodes. We sum the outputs of the two attention modules and use reinforcement learning to predict the classification of nodes relationship to further improve feature representation which contributes to more precise extraction results. The results on the TACRED and SemEval datasets show that the model can obtain more useful information for relational extraction tasks, and achieve better performances on various evaluation indexes.

This paper considers three different classifier stacking algorithms: simple stacking, cascades of classifier ensembles and nonlinear version of classifier stacking based on classifier interactions. Classifier interactions can be expressed using classifier prediction pairwise matrix (CPPM). As a meta-learner for the last algorithm Convolutional Neural Networks (CNNs) and two other classifier stacking algorithms (simple classifier stacking and cascades of classifier ensembles) have been applied. This allows applying classical stacking and cascade-based recursive stacking in the Euclidean and the Riemannian geometries. The cascades of random forests (RFs) and extra trees (ETs) are considered as a forest-based alternative to deep neural networks [1]. Our goal is to compare accuracies of the cascades of RFs and CNN-based stacking or deep multi-layer perceptrons (MLPs) for different classifications problems. We use gesture phase dataset from UCI repository [2] to compare and analyze cascades of RFs and extra trees (ETs) in both geometries and CNN-based version of classifier stacking. This data set was selected because generally motion is considered as a nonlinear process (patterns do no lie in Euclidean vector space) in computer vision applications. Thus we can assess how good are forest-based deep learning and the Riemannian manifolds (R-manifolds) when applied to nonlinear processes. Some more datasets from UCI repository were used to compare the aforementioned algorithms to some other well-known classifiers and their stacking-based versions in both geometries. Experimental results show that classifier stacking algorithms in Riemannian geometry (R-geometry) are less dependent on some properties of individual classifiers (e.g. depth of decision trees in RFs or ETs) in comparison to Euclidean geometry. More independent individual classifiers allow to obtain R-manifolds with better properties for classification. Generally, accuracy of classification using classifier stacking in R-geometry is higher than in Euclidean one.

The study of the physical properties of porous media is crucial for petrophysics laboratories. Even though micro computed tomography (CT) could be useful, the appropriate evaluation of flow properties would involve the acquisition of a large number of representative images. That is often unfeasible. Stochastic reconstruction methods aim to generate novel, realistic rock images from a small sample, thus avoiding a large acquisition process. In this contribution, we improve a previous method for 3D-to-3D reconstruction of the structure of porous media by applying generative adversarial neural networks (GANs). We compare several measures of pore morphology between simulated and acquired images. Experiments include Beadpack, Berea sandstone, and Ketton limestone images. Results show that our GANs-based method can reconstruct three-dimensional images of porous media at different scales that are representative of the morphology of the original images. Furthermore, the generation of multiple images is much faster than classical image reconstruction methods.

We propose an automatic method for pain intensity measurement from video. For each video, pain intensity was measured using the dynamics of facial movement using 66 facial points. Gram matrices formulation was used for facial points trajectory representations on the Riemannian manifold of symmetric positive semi-definite matrices of fixed rank. Curve fitting and temporal alignment were then used to smooth the extracted trajectories. A SVR regression model was then trained to encode the extracted trajectories into ten pain intensity scores consistent with the Visual Analogue Scale for pain intensity measurement. The proposed approach was evaluated using the UNBC McMaster Shoulder Pain Expression database and compared to the state of the art on the same data. Using both 5-folds cross-validation and leave-one-subject-out cross-validation, our results are competitive with respect to state of the art methods.

Point clouds obtained from real word scanning are always incomplete and ununiformly distributed, which would cause structural losses in 3D shape representations. Therefore, a learning-based method is introduced in this paper to repair partial point clouds and restore the complete shapes of target objects. First, we design an encoder that takes both local features and global features into consideration. Second, we establish a graph to connect the local features together, and then implement graph convolution with multi-head attention on it. The graph enables each local feature vector to search across the regions and selectively absorb other local features based on the its own features and global features. Third, we design a coarse decoder to collect cross-region features from the graph and generate coarse point clouds with low resolution, and a folding-based decoder to generate fine point clouds with high resolution. Our network is trained on six categories of objects in the ModelNet dataset, and its performance is compared with several existing methods, the results show that our network is able to generate dense complete point cloud with the highest accuracy.

Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable training triplets. Some of these mining methods rely on the extreme distances between instances, and some others make use of sampling. However, sampling from stochastic distributions of data rather than sampling merely from the existing embedding instances can provide more discriminative information. In this work, we sample triplets from distributions of data rather than from existing instances. We consider a multivariate normal distribution for the embedding of each class. Using Bayesian updating and conjugate priors, we update the distributions of classes dynamically by receiving the new mini-batches of training data. The proposed triplet mining with Bayesian updating can be used with any triplet-based loss function, e.g., \textit{triplet-loss} or Neighborhood Component Analysis (NCA) loss. Accordingly, Our triplet mining approaches are called Bayesian Updating Triplet (BUT) and Bayesian Updating NCA (BUNCA), depending on which loss function is being used. Experimental results on two public datasets, namely MNIST and histopathology colorectal cancer (CRC), substantiate the effectiveness of the proposed triplet mining method.

Objects and activities (temporal objects) are composed of a recursive hierarchy of perceptual wholes and parts, whose properties, such as shape, reflectance, and color, constitute a hierarchy of intrinsic causal factors of object appearance.However, object appearance is the compositional consequence of both an object’s intrinsic and extrinsic causal factors, where the extrinsic causal factors are related to illumination, and imaging conditions.We propose a unified tensor model of wholes and parts that statistically models the mechanism of data formation. We derive a compositional hierarchical block tensor factorization that computes a disentangled representation of the causal factors of object image formation by optimizing simultaneously across wholes and parts. Given computational efficiency considerations,we introduce an incremental bottom-up computational alternative that employs the lower level part representations to represent the higher level of abstractions, the parent wholes. This incremental computational approach may also be employed to update the causal model representation when data that becomes available incrementally. The resulting object representation is an interpretable combinatorial choice of intrinsic causal factor representations related to an object’s recursive hierarchy of wholes and parts that renders object recognition robust to occlusion and reduces training data requirements.

It is well-known that identity-unrelated variations (e.g., viewpoint or illumination) degrade the performances of face recognition methods. In order to handle this challenge, a robust method for disentangling the identity and view representations has drawn an attention in the machine learning area. However, existing methods learn discriminative features which require a manual supervision of such factors of variations. In this paper, we propose a novel disentangling framework through modeling three representations of identity, viewpoint, and residues (i.e., identity and pose unrelated) which do not require supervision of the variations. By jointly modeling the three representations, we enhance the disentanglement of each representation and achieve robust face recognition performance. Further, the learned viewpoint representation can be utilized for pose estimation or editing of a posed facial image. Extensive quantitative and qualitative evaluations verify the effectiveness of our proposed method which disentangles identity, viewpoint, and residues of facial images.

In this paper, we present a distinct discriminant canonical correlation analysis network (DDCCANet) based deep information quality representation with application to image classification. Specifically, to explore the sufficient discriminant information between different data sets, the within-class and between-class correlation matrices are employed and optimized jointly. Moreover, different from the existing canonical correlation analysis network (CCANet) and related algorithms, an information theoretic descriptor, information quality (IQ), is adopted to generate the deep-level feature representation for image classification. Benefiting from the explored discriminant information and IQ descriptor, it is potential to gain a more effective deep-level representation from multi-view data sets, leading to improved performance in classification tasks. To demonstrate the effectiveness of the proposed DDCCANet, we conduct experiments on the Olivetti Research Lab (ORL) face database, ETH80 database and CIFAR10 database. Experimental results show the superiority of the proposed solution on image classification.

A 3layered skin model is built to simulate hyperspectral reflectance using Monte Carlo simulations based on biological components, which include melanin volume fraction, water level, blood volume fraction, oxygen saturation, etc. A forward neural network is trained for mapping biological components and reflectance. Then a database, which contains 50,000 samples spectra from 450 to 750 nm with randomly given biological components information, are generated by this forward neural network. Support vector regression, inverse neural networks and random forest are applied for the regression analysis of reflectance data and melanin volume fraction. Dimensionality reduction is used to accelerate the training time. The performances of three regression methods are measured and show promising prediction results.

Recent advances in Handwritten Text Recognition and Document Layout Analysis make it possible to extract information from digitized documents and make them accessible beyond the archive shelves. But the reading order of the elements in those documents still is an open problem that has to be solved in order to provide that information with the correct structure. Most of the studies on the reading order task are rule-base approaches that focus on printed documents, while less attention has been paid to handwritten text documents. In this work we propose a new approach to automatically determine the reading order of text lines in handwritten text documents. The task is approached as a sorting problem where the order-relation operator is learned directly from examples. We demonstrate the effectiveness of our method on three different datasets.

Eye movements are intricate and dynamic events that contain a wealth of information about the subject and the stimuli. We propose an abstract representation of eye movements that preserve the important nuances in gaze behavior while being stimuli-agnostic. We consider eye movements as raw position and velocity signals and train a deep temporal convolutional autoencoder to learn micro-scale and macro-scale representations corresponding to the fast and slow features of eye movements. These joint representations are evaluated by fitting a linear classifier on various tasks and outperform other works in biometrics and stimuli classification. Further experiments highlight the validity and generalizability of this method, bringing eye tracking research closer to real-world applications.

Predictive Coding Network (PCN) is an important neural network inspired by visual processing models in neuroscience. It combines the feedforward and feedback processing and has the architecture of recurrent neural networks (RNNs). This type of network is usually trained with backpropagation through time (BPTT). With infinite recurrent steps, PCN is a dynamic system. However, as one of the most important properties, stability is rarely studied in this type of network. Inspired by reservoir computing, we investigate the stability of hierarchical RNNs from the perspective of dynamic systems, and propose a sufficient condition for their echo state property (ESP). Our study shows the global stability is determined by stability of the local layers and the feedback between neighboring layers. Based on it, we further propose Weight Norm Supervision, a new algorithm that controls the stability of PCN dynamics by imposing different weight norm constraints on different parts of the network. We compare our approach with other training methods in terms of stability and prediction capability. The experiments show that our algorithm learns stable PCNs with a reliable prediction precision in the most effective and controllable way.

We consider the problem of uncovering an unknown attributed graph, where both its edges and vertices are hidden from view, through a sequence of binary questions about it. In order to select questions efficiently, we define a probability distribution over graphs, with randomness not just over edges, but over vertices as well. We then sequentially select questions so as to: (1) minimize the expected entropy of the random graph, given the answers to the previous questions in the sequence; and (2) to instantiate the vertices that compose the graph. We propose some basic question spaces, from which to select questions, that vary in their capacity. We apply this framework to the problem of test generation in Visual Question Answering (VQA), where semantic questions are used to evaluate vision systems over rich image representations. To do this, we use a restricted question vocabulary, resulting in image representations that take the form of scene graphs; by defining a distribution over them, a consistent set of probabilities is associated with the questions, and used in their selection.

A rapidly growing amount of content posted online, such as food recipes, opens doors to new exciting applications at the intersection of vision and language. In this work, we aim to estimate the calorie amount of a meal directly from an image by learning from recipes people have published on the Internet, thus skipping time-consuming manual data annotation. Since there are few large-scale publicly available datasets captured in unconstrained environments, we propose the pic2kcal benchmark comprising 308,000 images from over 70,000 recipes including photographs, ingredients and instructions. To obtain nutritional information of the ingredients and automatically determine the ground-truth calorie value, we match the items in the recipes with structured information from a food item database. We evaluate various neural networks for regression of the calorie quantity and extend them with the multi-task paradigm. Our learning procedure combines the calorie estimation with prediction of proteins, carbohydrates, and fat amounts as well as a multi-label ingredient classification. Our experiments demonstrate clear benefits of multi-task learning for calorie estimation, surpassing the single-task calorie regression by 9.9%. To encourage further research on this task, we make the code for generating the dataset and the models publicly available.

This paper introduces a highly efficient image retrieval technique called DCNN-vForest (Decomposition Convolution Neural Network and vocabulary Forest), which aims to retrieve the relevant images to the given image query by studying the correlation between images in the image database based on decomposition. The regional and global features of the image database are first extracted using the convolution neural network, and then divided into similar clusters using the Kmeans algorithm. We propose a new structure called vForest (vocabulary Forest), by calculating the vocabulary tree on each cluster of images. The retrieval process benefits from the knowledge provided by the vForest, and instead of considering the whole image database, only the most similar clusters to the image query are explored. To demonstrate the usefulness of our approach, intensive experiments have been carried out on ground-truth image databases, the results reveal the superiority of DCNN-vForest against the baseline image retrieval solutions, in terms of runtime and accuracy.

The importance of developing an application based on intervention technology that leads to a healthier life is widely recognized. A challenging part of realizing the application is the need for planning, i.e., considering a user's health goal (e.g., sleep at 10:00 p.m. to get enough sleep), providing intervention at the appropriate timing to help the user achieve the goal. The reinforcement learning (RL) approach is well suited to this type of problem since it is a methodology for planning; RL finds the optimal strategy as that which maximizes future expected profit. The purpose of this study is to clarify the effects of intervention based on RL to support healthy daily life. Therefore, we (i) collect real daily activity data from participants, (ii) generate a user model that imitates the user's response to system interventions, (iii) examine valuable goals and design them as rewards in RL and (iv) obtain optimal intervention strategies by RL via simulations given a user model and goals. We evaluate a generated user model and verify by simulations whether our method could successfully achieve the goal. In addition, we analyze the cases that demonstrated higher probability of achieving the goal and report the features.

Depth estimation from a single 2D image has been widely applied in 3D understanding, 3D modelling and robotics. It is challenging as reliable cues (e.g. stereo correspondences and motions) are not available. Most of the modern approaches exploited multi-scale feature extraction to provide more powerful representations for deep networks. However, these studies have not focused on how to effectively fuse the learned multi-scale features. This paper proposes a novel region-based self-attention (rSA) module. The rSA recalibrates the multi-scale responses by explicitly modelling the interdependency between channels in separate image regions. We discretize continuous depths to solve an ordinal depth classification in which the relative order between categories is significant. We contribute a dataset of 4410 RGB-D images, captured in outdoor environments at the University of Wollongong's campus. In our experimental results, the proposed module improves the lightweight models on small-sized datasets by 22% - 40%

Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning and adversarial learning. On one side, clustering groups training images into pseudo-ID labels, and uses them to fine-tune the feature extractor. On the other side, adversarial learning is used, inspired by domain adaptation, to match distributions from different domains. Since target data is distributed across different camera viewpoints, we propose to model each camera as an independent domain, and aim to learn domain-independent features. Straightforward adversarial learning yields negative transfer, we thus introduce a conditioning vector to mitigate this undesirable effect. In our framework, the centroid of the cluster to which the visual sample belongs is used as conditioning vector of our conditional adversarial network, where the vector is permutation invariant (clusters ordering does not matter) and its size is independent of the number of clusters. To our knowledge, we are the first to propose the use of conditional adversarial networks for unsupervised person re-ID. We evaluate the proposed architecture on top of two state-of-the-art clustering-based unsupervised person re-identification (re-ID) methods on four different experimental settings with three different data sets and set the new state-of-the-art performance on all four of them. Our code and model will be made publicly available at https://team.inria.fr/perception/canu-reid/.

Digital era has changed the way music is produced and propagated creating new needs for automated and more effective management of music tracks in big volumes. Automated music mood detection constitutes an active task in the field of MIR (Music Information Retrieval) and connected with many research papers in the past few years. In order to approach the task of mood detection, we faced separately the analysis of musical lyrics and the analysis of musical audio signal. Then we applied a uniform multichannel analysis to classify our data in mood classes. The available data we will use to train and evaluate our models consists of a total of 2.000 song titles, classified in four mood classes {happy, angry, sad, relaxed}. The result of this process leads to a uniform prediction for emotional arousal that a music track can cause to a listener and show the way to develop many applications.

Social online video has emerged as one of the most popular application, where "bullet screen comment" is one of the favorite features of Asian users. User behavior report finds that most people are used to quickly navigate and locate his concerned video clip according to its corresponding video labels. Traditional scene segmentation algorithms are mostly based on the analysis of frames, which cannot automatically generate labels. Since time-synchronized comments can reflect the episode of current moment, this paper proposed an unsupervised video episode boundary detection model (VEBD) for bullet screen comment video. It could not only automatically identify each episode boundary, but also detect the topic for video tagging. Specifically, a Joint Episode-Topic model is first constructed to detect the hidden topic in initial partitioned time slices. Then, based on the detected topics, temporal and semantic relevancy between adjacent time slices are measured to refine the boundary detection accuracy. Experiments based on real data show that our model outperforms the existing algorithms in both boundary detection and semantic tagging quality.