Italy

One of the main challenges of visual question answering (VQA) lies in properly reasoning relations among visual regions involved in the question. In this paper, we propose a novel neural network to perform question-guided relational reasoning in multi-scales for visual question answering, in which each region of image is enhanced by regional attention. 
Specifically, we present regional attention module, which consists of a soft attention module and a hard attention module, to select informative regions of the image according to informative evaluations implemented by question-guided soft attention. Combinations of different informative regions are then concatenated with question embedding in different scales to capture relational information. Relational reasoning module can extract question-based relational information among regions, in which multi-scale mechanism gives it the ability to model scaled relationships and makes it sensitive to numbers. We conduct experiments to show that our proposed architecture is effective and achieves competitive results VQA v2. 



ICPR 2020

Multi-scale Relational Reasoning with Regional Attention for Visual Question Answering

multi-scale relational reasoning

visual question learning

attention

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


poster


The massive adoption of social networks has made available an unprecedented amount of user-generated content, which may be analyzed in order to determine people's opinions and emotions on a large variety of topics. Research has made many efforts in defining accurate algorithms for the analysis of emotions conveyed by texts, however their performance often relies on the existence of large annotated datasets, whose current scarcity represents a major issue.
The manual creation of such datasets represents a costly and time-consuming activity and hence there is an increasing demand for techniques for the automatic annotation of corpora.
In this work we present a methodology for the automatic annotation of video subtitles on the basis of the analysis of facial expressions of people in videos, with the goal of creating annotated corpora that may be used to train emotion recognition algorithms. Facial expressions are analyzed through machine learning algorithms, on the basis of a set of manually-engineered facial features that are extracted from video frames. The soundness of the proposed methodology has been evaluated through an extensive experimentation aimed at determining the performance on real datasets of each methodological step.

Automatic Annotation of Corpora for Emotion Recognition Through Facial Expression Analysis

Clustering is an unsupervised machine learning method giving insights on data without early knowledge. Classes of data are return by assembling similar elements together. Giving the increasing of the available data, this method is now applied in a lot of fields with various data types. Here, we propose to explore the case of time series clustering. Indeed, time series are one of the most classic data type, and are present in various fields such as medical or finance. This kind of data can be pre-processed by of dimension reduction methods, such as the recent UMAP algorithm. In this paper, a benchmark of time series clustering is created, comparing the results with and without UMAP as a pre-processing step. UMAP is used to enhance clustering results. For completeness, three different clustering algorithms and two different geometric representation for the time series (Classic Euclidean geometry, and Riemannian geometry on the Stiefel Manifold) are applied. The results are compared with and without UMAP as a pre-processing step on the databases available at UCR Time Series Classification Archive.

Improved Time-Series Clustering with UMAP dimension reduction method

Deep neural networks (DNNs) for nonlinear generative mixture modeling typically rely on unsupervised learning that employs hard clustering schemes, or variational learning with loose/approximate bounds, or under-regularized modeling.

We propose a novel statistical framework for a DNN mixture model using a single generative adversarial network. Our learning formulation proposes a novel data-likelihood term relying on a well-regularized/constrained Gaussian mixture model in the latent space along with a prior term on the DNN weights. Our min-max learning increases the data likelihood using a tight variational lower bound using expectation maximization (EM). We leverage our min-max EM learning scheme for semi-supervised learning.

Results on three real-world image datasets demonstrate the benefits of our compact modeling and learning formulation over the state of the art for nonlinear generative image (mixture) modeling and image clustering.

Generative Deep-Neural-Network Mixture Modeling with Semi-Supervised MinMax+EM Learning


The analysis of Magnetic Resonance Imaging (MRI) sequences enables clinical professionals to monitor the progression of a brain tumor. As the interest for automatizing brain volume MRI analysis increases, it becomes convenient to have each sequence well identified. However, the unstandardized naming of MRI sequences makes their identification difficult for automated systems, as well as makes it difficult for researches to generate or use datasets for machine learning research. In the face of that, we propose a system for identifying types of brain MRI sequences based on deep learning. By training a Convolutional Neural Network (CNN) based on 18-layer ResNet architecture, our system can classify a volumetric brain MRI as a FLAIR, T1, T1c or T2 sequence, or whether it does not belong to any of these classes. The network was evaluated on publicly available datasets comprising both, pre-processed (BraTS dataset) and non-pre-processed (TCGA-GBM dataset), image types with diverse acquisition protocols, requiring only a few slices of the volume for training. Our system can classify among sequence types with an accuracy of 96.81%.

Deep Learning-based Type Identification of Volumetric MRI Sequences

As one of the primary tasks in data mining, outlier detection serves a significant role in data quality enhancement for the scientific model prediction and revealing the abnormal hidden patterns from large scale trajectory datasets. In this paper, we introduce a versatile framework for detecting local trajectory outliers using spatial and temporal features of moving objects. Our local outlier detection consists of three phases. First, we divide the raw trajectory into trajectory segments by using a time-based partition strategy and extracting trajectory features from spatial attributes for each trajectory segment. Second, we create template trajectory segments based on a clustering schema. Finally, we compute the abnormal score, which measures the dissimilarity among the query and template trajectory segments, and thus determine the outlying trajectory segments according to the overall distribution of the abnormal score. To show the effectiveness of our approach, we conduct two case studies on the real-life solar active region and Coronal Mass Ejection (CME) trajectory datasets. Our results show that our local outlier detection method can successfully detect the reporting errors and anomalous phenomenon in both of our case studies.

A Framework for Local Outlier Detection from Spatio-Temporal Trajectory Datasets


Recently deep learning-based networks have achieved advanced performance in medical image segmentation. However, the development of deep learning is slow in magnetic resonance image (MRI) segmentation of normal brain tissues. In this paper, inspired by channel attention module, we propose a new architecture, Binary Channel Attention U-Net (BCAU-Net), by introducing a novel Binary Channel Attention Module (BCAM) into skip connection of U-Net, which can take full advantages of the channel information extracted from the encoding path and corresponding decoding path. To better aggregate multi-scale spatial information of the feature map, spatial pyramid pooling (SPP) modules with different pooling operations are used in BCAM instead of original average-pooling and max-pooling operations. We verify this model on two datasets including IBSR and MRBrainS18, and obtain better performance on MRI brain segmentation compared with other methods. We believe the proposed method can advance the performance in brain segmentation and clinical diagnosis.

BCAU-Net: A Novel Architecture with Binary Channel Attention Module for MRI Brain Segmentation


We consider hypergraphs as a tool obtained with bi-dimensional Probabilistic Context-Free Grammars to compactly represent the result of the n-best parse trees for an input image that represents a mathematical expression. More specifically, in this paper we propose: i) an algorithm to compute the N-best parse trees from a 2D-PCFGs, ii) an algorithm to represent the n-best parse trees using a compact representation in the form of hypergraphs, and iii) a formal framework for the development of inference algorithms (\emph{inside} and \emph{outside}) and normalization strategies of hypergraphs.

Generation of Hypergraphs from the N-Best Parsing of 2D-Probabilistic Context-Free Grammars for Mathematical Expression Recognition

Errors in semantic segmentation could be classified into two types: the large area misclassification and inaccurate local boundaries. Previously attention-based methods typically capture rich global contextual information, which benefits the large area classification but cannot address the local errors of boundaries. In this paper, we propose a Global-Local Attention Network (GLANet) which can simultaneously consider the global context and local details. Specifically, our GLANet consists of two branches: (1) the global attention branch and (2) local attention branch. Furthermore, three different modules are embedded in GLANet for respectively modelling the semantic interdependencies in spatial, channel and boundary dimension. Lastly, we merge the outputs of different branches to enhance the feature representation further, resulting in more precise segmentation. Overall, the proposed method achieves the competitive segmentation accuracy on two public aerial image datasets, bringing significant improvements over the existing baselines.

Global-Local Attention Network for Semantic Segmentation in Aerial Images

Feature learning in the presence of a mixed type of variables, numerical and categorical types, is important for related modeling problems. In this work, we propose a novel strategy to explicitly model the probabilistic dependence structure among the mixed type of variables by an undirected graph. The dependence structure among different pairs of variables is encoded by a suitable mapping function to estimate the edges of the graph. Spectral decomposition of the graph Laplacian provides the desired feature transformation. We numerically validate the implications of the feature learning strategy on various datasets in terms of data clustering

Graph Spectral Feature Learning for Mixed Data of Categorical and Numerical Type

We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment. Point cloud patches are extracted, canonicalised with respect to their estimated local reference frame and encoded into rotation-invariant compact descriptors by a PointNet-based deep neural network. DIPs can effectively generalise across different sensor modalities because they are learnt end-to-end from locally and randomly sampled points Because DIPs encode only local geometric information, they are robust to clutter, occlusions and missing regions. We evaluate and compare DIPs against alternative hand-crafted and deep descriptors on several indoor and outdoor datasets consisting of point clouds reconstructed using different sensors. Results show that DIPs (i) achieve comparable results to the state-of-the-art on RGB-D indoor scenes (3DMatch dataset), (ii) outperform state-of-the-art by a large margin on laser-scanner outdoor scenes (ETH dataset), and (iii) generalise to indoor scenes reconstructed with the Visual-SLAM system of Android ARCore.

Premium content

Downloads

Next from ICPR 2020

Automatic Annotation of Corpora for Emotion Recognition Through Facial Expression Analysis

Similar lecture

Multistage Attention based Visual Question Answering