1
Location Dependency in Video Prediction
Deep convolutional neural networks are used to address many computer vision problems, including video prediction. The task of video prediction requires analyzing the video frames, temporally and spatially, and constructing a model of how the environment evolves.
2
Structured Argument Extraction of Korean Question and Command
Intention identification and slot filling is a core issue in dialog management. However, due to the non-canonicality of the spoken language, it is difficult to extract the content automatically from the conversation-style utterances.
3
Let's take a Walk on Superpixels Graphs: Deformable Linear Objects Segmentation and Model Estimation
While robotic manipulation of rigid objects is quite straightforward, coping with deformable objects is an open issue. More specifically, tasks like tying a knot, wiring a connector or even surgical suturing deal with the domain of Deformable Linear Objects (DLOs).
4
Let's take a Walk on Superpixels Graphs: Deformable Linear Objects Segmentation and Model Estimation
While robotic manipulation of rigid objects is quite straightforward, coping with deformable objects is an open issue. More specifically, tasks like tying a knot, wiring a connector or even surgical suturing deal with the domain of Deformable Linear Objects (DLOs).
5
Batch Active Preference-Based Learning of Reward Functions
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by querying users with preference questions.
6
Bird Species Classification using Transfer Learning with Multistage Training
Bird species classification has received more and more attention in the field of computer vision, for its promising applications in biology and environmental studies. Recognizing bird species is difficult due to the challenges of discriminative region localization and fine-grained feature learning.
7
Convolutional Neural Networks In Convolution
Currently, increasingly deeper neural networks have been applied to improve their accuracy. In contrast, We propose a novel wider Convolutional Neural Networks (CNN) architecture, motivated by the Multi-column Deep Neural Networks and the Network In Network(NIN), aiming for higher accuracy without input data transmutation.
8
What made you do this? Understanding black-box decisions with sufficient input subsets
Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor or based on input saliency, which may be undesirably sensitive to factors unrelated to the model's decision making process.
10
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
Learning depth and optical flow via deep neural networks by watching videos has made significant progress recently. Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion.
11
Understanding the Origins of Bias in Word Embeddings
The power of machine learning systems not only promises great technical progress, but risks societal harm. Given a word embedding trained on a corpus, our method identifies how perturbing the corpus will affect the bias of the resulting embedding.
12
Improving the Transformer Translation Model with Document-Level Context
Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge. In this work, we extend the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder.
13
Stein Neural Sampler
We propose two novel samplers to produce high-quality samples from a given (un-normalized) probability density. The sampling is achieved by transforming a reference distribution to the target distribution with neural networks, which are trained separately by minimizing two kinds of Stein Discrepancies, and hence our method is named as Stein neural sampler.
14
An AMR Aligner Tuned by Transition-based Parser
In this paper, we propose a new rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser. Our aligner is further tuned by our oracle parser via picking the alignment that leads to the highest-scored achievable AMR graph.
15
MRI Super-Resolution using Multi-Channel Total Variation
This paper presents a generative model for super-resolution in routine clinical magnetic resonance images (MRI), of arbitrary orientation and contrast. The model recasts the recovery of high resolution images as an inverse problem, in which a forward model simulates the slice-select profile of the MR scanner.
16
MRI Super-Resolution using Multi-Channel Total Variation
This paper presents a generative model for super-resolution in routine clinical magnetic resonance images (MRI), of arbitrary orientation and contrast. The model recasts the recovery of high resolution images as an inverse problem, in which a forward model simulates the slice-select profile of the MR scanner.
17
Deep learning cardiac motion analysis for human survival prediction
Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimising the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be used for prediction tasks.
18
High-quality Ellipse Detection Based on Arc-support Line Segments
Over the years many ellipse detection algorithms spring up and are studied broadly, while the critical issue of detecting ellipses accurately and efficiently in real-world images remains a challenge. In this paper, an accurate and efficient ellipse detector by arc-support line segments is proposed.
19
Image Completion on CIFAR-10
This project performed image completion on CIFAR-10, a dataset of 60,000 32x32 RGB images, using three different neural network architectures: fully convolutional networks, convolutional networks with fully connected layers, and encoder-decoder convolutional networks. The highest performing model was a deep fully convolutional network, which was able to achieve a mean squared error of .015 when comparing the original image pixel values with the predicted pixel values.
20
European Court of Human Right Open Data project
This paper presents thirteen datasets for binary, multiclass and multilabel classification based on the European Court of Human Rights judgments since its creation. The interest of such datasets is explained through the prism of the researcher, the data scientist, the citizen and the legal practitioner.
21
CSI-Net: Unified Human Body Characterization and Action Recognition
In majority of existing works, CSI sequences are analyzed by traditional signal processing approaches. Besides the technical contribution of CSI-Net, we present major discoveries and insights on how the multi-frequency CSI signals are encoded and processed in DNNs, which, to the best of our knowledge, is the first attempt that bridges the WiFi sensing and deep learning in human sensing problems.
22
Deep convolutional Gaussian processes
We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. The model is a principled Bayesian framework for detecting hierarchical combinations of local features for image classification.
23
Mining Novel Multivariate Relationships in Time Series Data Using Correlation Networks
In many domains, there is significant interest in capturing novel relationships between time series that represent activities recorded at different nodes of a highly complex system. In this paper, we introduce multipoles, a novel class of linear relationships between more than two time series.
24
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
Person re-identification (reID) is an important task that requires to retrieve a person's images from an image dataset, given one image of the person of interest. Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN.
25
On the Art and Science of Machine Learning Explanations
This text discusses several explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the methods are tools of the trade while others are rigorously derived and backed by long-standing theory.
26
Model Cards for Model Reporting
Trained machine learning models are increasingly used to perform high-impact tasks in areas such as law enforcement, medicine, education, and employment. Model cards also disclose the context in which models are intended to be used, details of the performance evaluation procedures, and other relevant information.
27
Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
In particular, DCR places a separate classification network in parallel with the localization network (base detector). During training, DCR samples hard false positives from the base detector and trains a strong classifier to refine classification results.
28
TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
We present TRANX, a transition-based neural semantic parser that maps natural language (NL) utterances into formal meaning representations (MRs). TRANX uses a transition system based on the abstract syntax description language for the target MR, which gives it two major advantages: (1) it is highly accurate, using information from the syntax of the target MR to constrain the output space and model the information flow, and (2) it is highly generalizable, and can easily be applied to new types of MR by just writing a new abstract syntax description corresponding to the allowable structures in the MR.
29
GPdoemd: a python package for design of experiments for model discrimination
GPdoemd is an open-source python package for design of experiments for model discrimination that uses Gaussian process surrogate models to approximate and maximise the divergence between marginal predictive distributions of rival mechanistic models. GPdoemd uses the divergence prediction to suggest a maximally informative next experiment.
30
PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation
However, in continuous state and actions spaces and a Gaussian policy -- common in computer animation and robotics -- PPO is prone to getting stuck in local optima. Motivated by this, we borrow ideas from CMA-ES, a black-box optimization method designed for intelligent adaptive Gaussian exploration, to derive PPO-CMA, a novel proximal policy optimization approach that can expand the exploration variance on objective function slopes and shrink the variance when close to the optimum.
31
Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. We find that adaptive optimizers have a narrow window of effective learning rates, diverging in other cases, and that the effectiveness of momentum varies depending on the properties of the environment.
32
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
Emotion recognition in conversations is a challenging Artificial Intelligence (AI) task. In this work, we propose the Multimodal EmotionLines Dataset (MELD), which we created by enhancing and extending the previously introduced EmotionLines dataset.
33
Co-Learning Feature Fusion Maps from PET-CT Images of Lung Cancer
Our aim is to improve fusion of the complementary information in multi-modality PET-CT with a new supervised convolutional neural network (CNN) that learns to fuse complementary information for multi-modality medical image analysis. These fusion maps are then multiplied with the modality-specific feature maps to obtain a representation of the complementary multi-modality information at different locations, which can then be used for image analysis, e.g. region detection.
34
Graph Embedding with Shifted Inner Product Similarity and its Improved Approximation Capability
We propose shifted inner-product similarity (SIPS), which is a novel yet very simple extension of the ordinary inner-product similarity (IPS) for neural-network based graph embedding (GE). In contrast to IPS, that is limited to approximating positive-definite (PD) similarities, SIPS goes beyond the limitation by introducing bias terms in IPS; we theoretically prove that SIPS is capable of approximating not only PD but also conditionally PD (CPD) similarities with many examples such as cosine similarity, negative Poincare distance and negative Wasserstein distance.
35
Progressive Feature Fusion Network for Realistic Image Dehazing
Single image dehazing is a challenging ill-posed restoration problem. Most of them follow a classic atmospheric scattering model which is an elegant simplified physical model based on the assumption of single-scattering and homogeneous atmospheric medium.
36
A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation
The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. We show that, while gains in BLEU are moderate for those systems, they outperform baselines by a large margin in terms of accuracy on our contrastive test set.
38
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. We show that GNNs have the same expressiveness as the $1$-WL in terms of distinguishing non-isomorphic (sub-)graphs.
39
Learning Depth with Convolutional Spatial Propagation Network
In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for various depth estimation tasks. In practice, we further extend CSPN in two aspects: 1) take sparse depth map as additional input, which is useful for the task of depth completion; 2) similar to commonly used 3D convolution operation in CNNs, we propose 3D CSPN to handle features with one additional dimension, which is effective in the task of stereo matching using 3D cost volume.
41
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking.
42
McTorch, a manifold optimization library for deep learning
In this paper, we introduce McTorch, a manifold optimization library for deep learning that extends PyTorch. It aims to lower the barrier for users wishing to use manifold constraints in deep learning applications, i.e., when the parameters are constrained to lie on a manifold.
44
SAVOIAS: A Diverse, Multi-Category Visual Complexity Dataset
Visual complexity identifies the level of intricacy and details in an image or the level of difficulty to describe the image. In this work, we introduce Savoias, a visual complexity dataset that compromises of more than 1,400 images from seven image categories relevant to the above research areas, namely Scenes, Advertisements, Visualization and infographics, Objects, Interior design, Art, and Suprematism.
45
GINN: Geometric Illustration of Neural Networks
This informal technical report details the geometric illustration of decision boundaries for ReLU units in a three layer fully connected neural network. The network is designed and trained to predict pixel intensity from an (x, y) input location.
47
GLAD: GLocalized Anomaly Detection via Active Feature Space Suppression
We propose an algorithm called GLAD (GLocalized Anomaly Detection) that allows end-users to retain the use of simple and understandable global anomaly detectors by automatically learning their local relevance to specific data instances using label feedback. The key idea is to place a uniform prior over the input feature space for each member of the anomaly detection ensemble via a neural network trained on unlabeled instances, and tune the weights of the neural network to adjust the local relevance of each ensemble member using all labeled instances.
48
Generative Ensembles for Robust Anomaly Detection
Deep generative models are capable of learning probability distributions over large, high-dimensional datasets such as images, video and natural language. Generative models trained on samples from $p(x)$ ought to assign low likelihoods to out-of-distribution (OoD) samples from $q(x)$, making them suitable for anomaly detection applications.
49
Efficient Dialog Policy Learning via Positive Memory Retention
This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples.
50
Efficient Dialog Policy Learning via Positive Memory Retention
This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples.
51
Energy-Based Hindsight Experience Prioritization
To verify our hypothesis, we designed a framework for hindsight experience prioritization based on the trajectory energy of goal states. We evaluate our Energy-Based Prioritization (EBP) approach on four challenging robotic manipulation tasks in simulation.
53
Landmine Detection Using Autoencoders on Multi-polarization GPR Volumetric Data
Buried landmines and unexploded remnants of war are a constant threat for the population of many countries that have been hit by wars in the past years. This method works in an anomaly detection framework, indeed we only train the autoencoder on GPR data acquired on landmine-free areas.
54
CEM-RL: Combining evolutionary and gradient-based methods for policy search
Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency.
55
CEM-RL: Combining evolutionary and gradient-based methods for policy search
Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency.
56
Predicting Factuality of Reporting and Bias of News Media Sources
We present a study on predicting the factuality of reporting and bias of news media. While previous work has focused on studying the veracity of claims or documents, here we are interested in characterizing entire news media.
57
CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction
Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms. In comparison with existing VO and V-SLAM algorithms, semi-direct visual odometry (SVO) has two main advantages that lead to state-of-the-art frame rate camera motion estimation: direct pixel correspondence and efficient implementation of probabilistic mapping method.
58
Challenges of Using Text Classifiers for Causal Inference
Causal understanding is essential for many kinds of decision-making, but causal inference from observational data has typically only been applied to structured, low-dimensional datasets. While text classifiers produce low-dimensional outputs, their use in causal inference has not previously been studied.
59
Improved robustness to adversarial examples using Lipschitz regularization of the loss
Adversarial training is an effective method for improving robustness to adversarial attacks. We show that adversarial training using the Fast Signed Gradient Method can be interpreted as a form of regularization.
60
Geometric Constellation Shaping for Fiber Optic Communication Systems via End-to-end Learning
In this paper, an unsupervised machine learning method for geometric constellation shaping is investigated. By embedding a differentiable fiber channel model within two neural networks, the learning algorithm is optimizing for a geometric constellation shape.
61
Benchmark Analysis of Representative Deep Neural Network Architectures
This work presents an in-depth analysis of the majority of the deep neural networks (DNNs) proposed in the state of the art for image recognition. For each DNN multiple performance indices are observed, such as recognition accuracy, model complexity, computational complexity, memory usage, and inference time.
62
SurfelMeshing: Online Surfel-Based Mesh Reconstruction
In contrast to most existing approaches, we do not fuse depth measurements in a volume but in a dense surfel cloud. This is possible by deforming the surfel cloud and asynchronously remeshing the surface where necessary.
63
Classification Using Link Prediction
Using a graph representation of the data, we can convert the problem of classification to the problem of link prediction which aims at finding the missing links between the unlabeled data (unlabeled nodes) and their classes. To our knowledge, despite the fact that numerous algorithms use the graph representation of the data for classification, none are using link prediction as the heart of their classifying procedure.
64
Counterfactually Fair Prediction Using Multiple Causal Models
In this paper we study the problem of making predictions using multiple structural casual models defined by different agents, under the constraint that the prediction satisfies the criterion of counterfactual fairness. Relying on the frameworks of causality, fairness and opinion pooling, we build upon and extend previous work focusing on the qualitative aggregation of causal Bayesian networks and causal models.
65
Taming VAEs
In spite of remarkable progress in deep latent variable generative modeling, training still remains a challenge due to a combination of optimization and generalization issues. In practice, a combination of heuristic algorithms (such as hand-crafted annealing of KL-terms) is often used in order to achieve the desired results, but such solutions are not robust to changes in model architecture or dataset.
66
Learnable Pooling Methods for Video Classification
Rather than using ensembles of existing architectures, we provide an insight on creating new architectures. We demonstrate our solutions in the "The 2nd YouTube-8M Video Understanding Challenge", by using frame-level video and audio descriptors.
67
Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network
The existence of hybrid noise in hyperspectral images (HSIs) severely degrades the data quality, reduces the interpretation accuracy of HSIs, and restricts the subsequent HSIs applications. In this paper, the spatial-spectral gradient network (SSGN) is presented for mixed noise removal in HSIs.
68
3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Image
We propose a mechanism to reconstruct part annotated 3D point clouds of objects given just a single input image. We demonstrate that jointly training for both reconstruction and segmentation leads to improved performance in both the tasks, when compared to training for each task individually.
69
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements. Consequently, model size reduction has become an utmost goal in deep learning.
70
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements. Consequently, model size reduction has become an utmost goal in deep learning.
71
Distributed linear regression by averaging
We do linear regression on each machine, and take a weighted average of the parameters. Here we study the performance loss in estimation error, test error, and confidence interval length in high dimensions, where the number of parameters is comparable to the training data size.
72
Extending Stan for Deep Probabilistic Programming
Deep probabilistic programming combines deep neural networks (for automatic hierarchical representation learning) with probabilistic models (for principled handling of uncertainty). Unfortunately, it is difficult to write deep probabilistic models, because existing programming frameworks lack concise, high-level, and clean ways to express them.
73
Deep Quality-Value (DQV) Learning
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values.
74
Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning
Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the future.
76
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
Despite advances in scalable models, the inference tools used for Gaussian processes (GPs) have yet to fully capitalize on developments in computing hardware. We present an efficient and general approach to GP inference based on Blackbox Matrix-Matrix multiplication (BBMM).
77
Weighted Spectral Embedding of Graphs
We present a novel spectral embedding of graphs that incorporates weights assigned to the nodes, quantifying their relative importance. This spectral embedding is based on the first eigenvectors of some properly normalized version of the Laplacian.
78
SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
Automatic sleep staging has been often treated as a simple classification problem that aims at determining the label of individual target polysomnography (PSG) epochs one at a time. At the sequence processing level, a recurrent layer placed on top of the learned epoch-wise features for long-term modelling of sequential epochs.
80
Generative replay with feedback connections as a general strategy for continual learning
Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning problematic. To enable more meaningful comparisons, we identified three distinct continual learning scenarios based on whether task identity is known and, if it is not, whether it needs to be inferred.
81
Solving Statistical Mechanics using Variational Autoregressive Networks
We propose a general framework for solving statistical mechanics of systems with a finite size. The approach extends the celebrated variational mean-field approaches using autoregressive neural networks which support direct sampling and exact calculation of normalized probability of configurations.
82
AlphaGomoku: An AlphaGo-based Gomoku Artificial Intelligence using Curriculum Learning
In this project, we combine AlphaGo algorithm with Curriculum Learning to crack the game of Gomoku. Modifications like Double Networks Mechanism and Winning Value Decay are implemented to solve the intrinsic asymmetry and short-sight of Gomoku.
83
Boosting Trust Region Policy Optimization by Normalizing Flows Policy
We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraint, normalizing flows policy can generate samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps avoid bad local optima.
84
Learning Preconditioners on Lie Groups
We study two types of preconditioners and preconditioned stochastic gradient descent (SGD) methods in a unified framework. We call the first one the Newton type due to its close relationship to Newton method, and the second one the Fisher type as its preconditioner is closely related to the inverse of Fisher information matrix.
85
CNN-based Pore Detection and Description for High-Resolution Fingerprint Recognition
High-resolution fingerprint recognition usually relies on sophisticated matching algorithms to match hand-crafted keypoint, usually pores, descriptors. In this work, we improve the state-of-the-art results in a public benchmark by using instead a CNN pore descriptor with a simpler matching algorithm.
86
Monge-Ampère Flow for Generative Modeling
We present a deep generative model, named Monge-Amp\`ere flow, which builds on continuous-time gradient flow arising from the Monge-Amp\`ere equation in optimal transport theory. This approach brings insights and techniques from Monge-Amp\`ere equation, optimal transport, and fluid dynamics into reversible flow-based generative models.
87
Bayesian inference for PCA and MUSIC algorithms with unknown number of sources
We then use Bayesian method to, for the first time, compute the MAP estimate for the number of sources in PCA and MUSIC algorithms. In simulations of overlapping multi-tone sources for linear sensor array, our exact MAP estimate is far superior to the asymptotic Akaike information criterion (AIC), which is a popular method for estimating the number of components in PCA and MUSIC algorithms.
88
Bayesian inference for PCA and MUSIC algorithms with unknown number of sources
We then use Bayesian method to, for the first time, compute the MAP estimate for the number of sources in PCA and MUSIC algorithms. In simulations of overlapping multi-tone sources for linear sensor array, our exact MAP estimate is far superior to the asymptotic Akaike information criterion (AIC), which is a popular method for estimating the number of components in PCA and MUSIC algorithms.
89
Sampling Theory for Graph Signals on Product Graphs
In this paper, we extend the sampling theory on graphs by constructing a framework that exploits the structure in product graphs for efficient sampling and recovery of bandlimited graph signals that lie on them. Product graphs are graphs that are composed from smaller graph atoms; we motivate how this model is a flexible and useful way to model richer classes of data that can be multi-modal in nature.
90
A Novel Online Stacked Ensemble for Multi-Label Stream Classification
As data streams become more prevalent, the necessity for online algorithms that mine this transient and dynamic data becomes clearer. Multi-label data stream classification is a supervised learning problem where each instance in the data stream is classified into one or more pre-defined sets of labels.
91
Robot Bed-Making: Deep Transfer Learning Using Depth Sensing of Deformable Fabric
Bed-making is a common task well-suited for home robots since it is tolerant to error and not time-critical. We train two networks: one to identify a corner of the blanket and another to determine when to transition to the other side of the bed.
92
Robot Bed-Making: Deep Transfer Learning Using Depth Sensing of Deformable Fabric
Bed-making is a common task well-suited for home robots since it is tolerant to error and not time-critical. We train two networks: one to identify a corner of the blanket and another to determine when to transition to the other side of the bed.
93
Night-to-Day Image Translation for Retrieval-based Localization
An efficient and scalable approach to visual localization is to use image retrieval techniques. We then compare the daytime and translated-night images to obtain a pose estimate for the night image using the known 6-DOF position of the closest day image.
94
DSR: Direct Self-rectification for Uncalibrated Dual-lens Cameras
It is achieved by di-rectly minimizing the vertical displacements of correspond-ing points between the original master image and the trans-formed slave image. Our method is evaluated on both real-istic and synthetic stereo image pairs, and produces supe-rior results compared to the calibrated rectification or otherself-rectification approaches
95
PhotoShape: Photorealistic Materials for Large-Scale Shape Collections
Existing online 3D shape repositories contain thousands of 3D models but lack photorealistic appearance. We present an approach to automatically assign high-quality, realistic appearance models to large scale 3D shape collections.
96
Automatic brain tumor grading from MRI data using convolutional neural networks and quality assessment
Glioblastoma Multiforme is a high grade, very aggressive, brain tumor, with patients having a poor prognosis. In this way, we overcome the need for expert annotations of regions of interest.
97
TTMF: A Triple Trustworthiness Measurement Frame for Knowledge Graphs
It has been widely used in intelligent analysis and understanding of big data. Therefore, in this paper, we establish a unified knowledge graph triple trustworthiness measurement framework to calculate the confidence values for the triples that quantify its semantic correctness and the true degree of the facts expressed.
98
S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using generic priors on the state characteristics.
99
