Paper Group ANR 392
Real-Time Deep Learning Method for Abandoned Luggage Detection in Video. Hand-tremor frequency estimation in videos. A simulation study to distinguish prompt photon from $π^0$ and beam halo in a granular calorimeter using deep networks. Classification of histopathological breast cancer images using iterative VMD aided Zernike moments & textural sig …
Real-Time Deep Learning Method for Abandoned Luggage Detection in Video
| Title | Real-Time Deep Learning Method for Abandoned Luggage Detection in Video |
| Authors | Sorina Smeureanu, Radu Tudor Ionescu |
| Abstract | Recent terrorist attacks in major cities around the world have brought many casualties among innocent citizens. One potential threat is represented by abandoned luggage items (that could contain bombs or biological warfare) in public areas. In this paper, we describe an approach for real-time automatic detection of abandoned luggage in video captured by surveillance cameras. The approach is comprised of two stages: (i) static object detection based on background subtraction and motion estimation and (ii) abandoned luggage recognition based on a cascade of convolutional neural networks (CNN). To train our neural networks we provide two types of examples: images collected from the Internet and realistic examples generated by imposing various suitcases and bags over the scene’s background. We present empirical results demonstrating that our approach yields better performance than a strong CNN baseline method. |
| Tasks | Motion Estimation, Object Detection |
| Published | 2018-03-03 |
| URL | http://arxiv.org/abs/1803.01160v3 |
| http://arxiv.org/pdf/1803.01160v3.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-deep-learning-method-for-abandoned |
| Repo | |
| Framework | |
Hand-tremor frequency estimation in videos
| Title | Hand-tremor frequency estimation in videos |
| Authors | Silvia L. Pintea, Jian Zheng, Xilin Li, Paulina J. M. Bank, Jacobus J. van Hilten, Jan C. van Gemert |
| Abstract | We focus on the problem of estimating human hand-tremor frequency from input RGB video data. Estimating tremors from video is important for non-invasive monitoring, analyzing and diagnosing patients suffering from motor-disorders such as Parkinson’s disease. We consider two approaches for hand-tremor frequency estimation: (a) a Lagrangian approach where we detect the hand at every frame in the video, and estimate the tremor frequency along the trajectory; and (b) an Eulerian approach where we first localize the hand, we subsequently remove the large motion along the movement trajectory of the hand, and we use the video information over time encoded as intensity values or phase information to estimate the tremor frequency. We estimate hand tremors on a new human tremor dataset, TIM-Tremor, containing static tasks as well as a multitude of more dynamic tasks, involving larger motion of the hands. The dataset has 55 tremor patient recordings together with: associated ground truth accelerometer data from the most affected hand, RGB video data, and aligned depth data. |
| Tasks | |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03218v1 |
| http://arxiv.org/pdf/1809.03218v1.pdf | |
| PWC | https://paperswithcode.com/paper/hand-tremor-frequency-estimation-in-videos |
| Repo | |
| Framework | |
A simulation study to distinguish prompt photon from $π^0$ and beam halo in a granular calorimeter using deep networks
| Title | A simulation study to distinguish prompt photon from $π^0$ and beam halo in a granular calorimeter using deep networks |
| Authors | Shamik Ghosh, Abhirami Harilal, A. R. Sahasransu, Ritesh Kumar Singh, Satyaki Bhattacharya |
| Abstract | In a hadron collider environment identification of prompt photons originating in a hard partonic scattering process and rejection of non-prompt photons coming from hadronic jets or from beam related sources, is the first step for study of processes with photons in final state. Photons coming from decay of $\pi_0$'s produced inside a hadronic jet and photons produced in catastrophic bremsstrahlung by beam halo muons are two major sources of non-prompt photons. In this paper the potential of deep learning methods for separating the prompt photons from beam halo and $\pi^0$'s in the electromagnetic calorimeter of a collider detector is investigated, using an approximate description of the CMS detector. It is shown that, using only calorimetric information as images with a Convolutional Neural Network, beam halo (and $\pi^{0}$) can be separated from photon with 99.96% (97.7%) background rejection for 99.00% (90.0%) signal efficiency which is much better than traditionally employed variables. |
| Tasks | |
| Published | 2018-08-12 |
| URL | http://arxiv.org/abs/1808.03987v3 |
| http://arxiv.org/pdf/1808.03987v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-simulation-study-to-distinguish-prompt |
| Repo | |
| Framework | |
Classification of histopathological breast cancer images using iterative VMD aided Zernike moments & textural signatures
| Title | Classification of histopathological breast cancer images using iterative VMD aided Zernike moments & textural signatures |
| Authors | Subhankar Chattoraj, Karan Vishwakarma |
| Abstract | In this paper we present a novel method for an automated diagnosis of breast carcinoma through multilevel iterative variational mode decomposition (VMD) and textural features encompassing Zernaike moments, fractal dimension and entropy features namely, Kapoor entropy, Renyi entropy, Yager entropy features are extracted from VMD components. The proposed method considers the histopathological image as a set of multidimensional spatially-evolving signals. ReliefF algorithm is used to select the discriminatory features and statistically most significant features are fed to squares support vector machine (SVM) for classification. We evaluate the efficiency of the proposed methodology on publicly available Breakhis dataset containing 7,909 breast cancer histological images, collected from 82 patients, of both benign and malignant cases. Experimental results shows the efficacy of the proposed method in outperforming the state of the art while achieving an average classification rates of 89.61% and 88:23% using three-fold and ten-fold cross-validation strategies, respectively. This system can aid the pathologist in accurate and reliable diagnosis of biopsy samples. BreaKHis, a publicly dataset available at http://web.inf.ufpr.br/vri/breast-cancer-database. |
| Tasks | |
| Published | 2018-01-15 |
| URL | http://arxiv.org/abs/1801.04880v1 |
| http://arxiv.org/pdf/1801.04880v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-histopathological-breast |
| Repo | |
| Framework | |
Learning Human Poses from Actions
| Title | Learning Human Poses from Actions |
| Authors | Aditya Arun, C. V. Jawahar, M. Pawan Kumar |
| Abstract | We consider the task of learning to estimate human pose in still images. In order to avoid the high cost of full supervision, we propose to use a diverse data set, which consists of two types of annotations: (i) a small number of images are labeled using the expensive ground-truth pose; and (ii) other images are labeled using the inexpensive action label. As action information helps narrow down the pose of a human, we argue that this approach can help reduce the cost of training without significantly affecting the accuracy. To demonstrate this we design a probabilistic framework that employs two distributions: (i) a conditional distribution to model the uncertainty over the human pose given the image and the action; and (ii) a prediction distribution, which provides the pose of an image without using any action information. We jointly estimate the parameters of the two aforementioned distributions by minimizing their dissimilarity coefficient, as measured by a task-specific loss function. During both training and testing, we only require an efficient sampling strategy for both the aforementioned distributions. This allows us to use deep probabilistic networks that are capable of providing accurate pose estimates for previously unseen images. Using the MPII data set, we show that our approach outperforms baseline methods that either do not use the diverse annotations or rely on pointwise estimates of the pose. |
| Tasks | |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09075v1 |
| http://arxiv.org/pdf/1807.09075v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-human-poses-from-actions |
| Repo | |
| Framework | |
A Reputation System for Artificial Societies
| Title | A Reputation System for Artificial Societies |
| Authors | Anton Kolonin, Ben Goertzel, Deborah Duong, Matt Ikle |
| Abstract | One approach to achieving artificial general intelligence (AGI) is through the emergence of complex structures and dynamic properties arising from decentralized networks of interacting artificial intelligence (AI) agents. Understanding the principles of consensus in societies and finding ways to make consensus more reliable becomes critically important as connectivity and interaction speed increase in modern distributed systems of hybrid collective intelligences, which include both humans and computer systems. We propose a new form of reputation-based consensus with greater resistance to reputation gaming than current systems have. We discuss options for its implementation, and provide initial practical results. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07342v1 |
| http://arxiv.org/pdf/1806.07342v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-reputation-system-for-artificial-societies |
| Repo | |
| Framework | |
Object-oriented Targets for Visual Navigation using Rich Semantic Representations
| Title | Object-oriented Targets for Visual Navigation using Rich Semantic Representations |
| Authors | Jean-Benoit Delbrouck, Stéphane Dupont |
| Abstract | When searching for an object humans navigate through a scene using semantic information and spatial relationships. We look for an object using our knowledge of its attributes and relationships with other objects to infer the probable location. In this paper, we propose to tackle the visual navigation problem using rich semantic representations of the observed scene and object-oriented targets to train an agent. We show that both allows the agent to generalize to new targets and unseen scene in a short amount of training time. |
| Tasks | Visual Navigation |
| Published | 2018-11-22 |
| URL | http://arxiv.org/abs/1811.09178v2 |
| http://arxiv.org/pdf/1811.09178v2.pdf | |
| PWC | https://paperswithcode.com/paper/object-oriented-targets-for-visual-navigation |
| Repo | |
| Framework | |
Understanding Latent Factors Using a GWAP
| Title | Understanding Latent Factors Using a GWAP |
| Authors | Johannes Kunkel, Benedikt Loepp, Jürgen Ziegler |
| Abstract | Recommender systems relying on latent factor models often appear as black boxes to their users. Semantic descriptions for the factors might help to mitigate this problem. Achieving this automatically is, however, a non-straightforward task due to the models’ statistical nature. We present an output-agreement game that represents factors by means of sample items and motivates players to create such descriptions. A user study shows that the collected output actually reflects real-world characteristics of the factors. |
| Tasks | Recommendation Systems |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.10260v1 |
| http://arxiv.org/pdf/1808.10260v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-latent-factors-using-a-gwap |
| Repo | |
| Framework | |
conformalClassification: A Conformal Prediction R Package for Classification
| Title | conformalClassification: A Conformal Prediction R Package for Classification |
| Authors | Niharika Gauraha, Ola Spjuth |
| Abstract | The conformalClassification package implements Transductive Conformal Prediction (TCP) and Inductive Conformal Prediction (ICP) for classification problems. Conformal Prediction (CP) is a framework that complements the predictions of machine learning algorithms with reliable measures of confidence. TCP gives results with higher validity than ICP, however ICP is computationally faster than TCP. The package conformalClassification is built upon the random forest method, where votes of the random forest for each class are considered as the conformity scores for each data point. Although the main aim of the conformalClassification package is to generate CP errors (p-values) for classification problems, the package also implements various diagnostic measures such as deviation from validity, error rate, efficiency, observed fuzziness and calibration plots. In future releases, we plan to extend the package to use other machine learning algorithms, (e.g. support vector machines) for model fitting. |
| Tasks | Calibration |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.05494v1 |
| http://arxiv.org/pdf/1804.05494v1.pdf | |
| PWC | https://paperswithcode.com/paper/conformalclassification-a-conformal |
| Repo | |
| Framework | |
Seismic-Net: A Deep Densely Connected Neural Network to Detect Seismic Events
| Title | Seismic-Net: A Deep Densely Connected Neural Network to Detect Seismic Events |
| Authors | Yue Wu, Youzuo Lin, Zheng Zhou, Andrew Delorey |
| Abstract | One of the risks of large-scale geologic carbon sequestration is the potential migration of fluids out of the storage formations. Accurate and fast detection of this fluids migration is not only important but also challenging, due to the large subsurface uncertainty and complex governing physics. Traditional leakage detection and monitoring techniques rely on geophysical observations including seismic. However, the resulting accuracy of these methods is limited because of indirect information they provide requiring expert interpretation, therefore yielding in-accurate estimates of leakage rates and locations. In this work, we develop a novel machine-learning detection package, named “Seismic-Net”, which is based on the deep densely connected neural network. To validate the performance of our proposed leakage detection method, we employ our method to a natural analog site at Chimay'o, New Mexico. The seismic events in the data sets are generated because of the eruptions of geysers, which is due to the leakage of $\mathrm{CO}\mathrm{2}$. In particular, we demonstrate the efficacy of our Seismic-Net by formulating our detection problem as an event detection problem with time series data. A fixed-length window is slid throughout the time series data and we build a deep densely connected network to classify each window to determine if a geyser event is included. Through our numerical tests, we show that our model achieves precision/recall as high as 0.889/0.923. Therefore, our Seismic-Net has a great potential for detection of $\mathrm{CO}\mathrm{2}$ leakage. |
| Tasks | Time Series |
| Published | 2018-01-17 |
| URL | http://arxiv.org/abs/1802.02241v1 |
| http://arxiv.org/pdf/1802.02241v1.pdf | |
| PWC | https://paperswithcode.com/paper/seismic-net-a-deep-densely-connected-neural |
| Repo | |
| Framework | |
A stigmergy-based analysis of city hotspots to discover trends and anomalies in urban transportation usage
| Title | A stigmergy-based analysis of city hotspots to discover trends and anomalies in urban transportation usage |
| Authors | Antonio L. Alfeo, Mario G. C. A. Cimino, Sara Egidi, Bruno Lepri, Gigliola Vaglini |
| Abstract | A key aspect of a sustainable urban transportation system is the effectiveness of transportation policies. To be effective, a policy has to consider a broad range of elements, such as pollution emission, traffic flow, and human mobility. Due to the complexity and variability of these elements in the urban area, to produce effective policies remains a very challenging task. With the introduction of the smart city paradigm, a widely available amount of data can be generated in the urban spaces. Such data can be a fundamental source of knowledge to improve policies because they can reflect the sustainability issues underlying the city. In this context, we propose an approach to exploit urban positioning data based on stigmergy, a bio-inspired mechanism providing scalar and temporal aggregation of samples. By employing stigmergy, samples in proximity with each other are aggregated into a functional structure called trail. The trail summarizes relevant dynamics in data and allows matching them, providing a measure of their similarity. Moreover, this mechanism can be specialized to unfold specific dynamics. Specifically, we identify high-density urban areas (i.e hotspots), analyze their activity over time, and unfold anomalies. Moreover, by matching activity patterns, a continuous measure of the dissimilarity with respect to the typical activity pattern is provided. This measure can be used by policy makers to evaluate the effect of policies and change them dynamically. As a case study, we analyze taxi trip data gathered in Manhattan from 2013 to 2015. |
| Tasks | |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.05697v2 |
| http://arxiv.org/pdf/1804.05697v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-stigmergy-based-analysis-of-city-hotspots |
| Repo | |
| Framework | |
Interpretable Reinforcement Learning with Ensemble Methods
| Title | Interpretable Reinforcement Learning with Ensemble Methods |
| Authors | Alexander Brown, Marek Petrik |
| Abstract | We propose to use boosted regression trees as a way to compute human-interpretable solutions to reinforcement learning problems. Boosting combines several regression trees to improve their accuracy without significantly reducing their inherent interpretability. Prior work has focused independently on reinforcement learning and on interpretable machine learning, but there has been little progress in interpretable reinforcement learning. Our experimental results show that boosted regression trees compute solutions that are both interpretable and match the quality of leading reinforcement learning methods. |
| Tasks | Interpretable Machine Learning |
| Published | 2018-09-19 |
| URL | http://arxiv.org/abs/1809.06995v1 |
| http://arxiv.org/pdf/1809.06995v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-reinforcement-learning-with |
| Repo | |
| Framework | |
Adaptive Neural Trees
| Title | Adaptive Neural Trees |
| Authors | Ryutaro Tanno, Kai Arulkumaran, Daniel C. Alexander, Antonio Criminisi, Aditya Nori |
| Abstract | Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures. We unite the two via adaptive neural trees (ANTs) that incorporates representation learning into edges, routing functions and leaf nodes of a decision tree, along with a backpropagation-based training algorithm that adaptively grows the architecture from primitive modules (e.g., convolutional layers). We demonstrate that, whilst achieving competitive performance on classification and regression datasets, ANTs benefit from (i) lightweight inference via conditional computation, (ii) hierarchical separation of features useful to the task e.g. learning meaningful class associations, such as separating natural vs. man-made objects, and (iii) a mechanism to adapt the architecture to the size and complexity of the training dataset. |
| Tasks | Representation Learning |
| Published | 2018-07-17 |
| URL | https://arxiv.org/abs/1807.06699v5 |
| https://arxiv.org/pdf/1807.06699v5.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-neural-trees |
| Repo | |
| Framework | |
Building Context-aware Clause Representations for Situation Entity Type Classification
| Title | Building Context-aware Clause Representations for Situation Entity Type Classification |
| Authors | Zeyu Dai, Ruihong Huang |
| Abstract | Capabilities to categorize a clause based on the type of situation entity (e.g., events, states and generic statements) the clause introduces to the discourse can benefit many NLP applications. Observing that the situation entity type of a clause depends on discourse functions the clause plays in a paragraph and the interpretation of discourse functions depends heavily on paragraph-wide contexts, we propose to build context-aware clause representations for predicting situation entity types of clauses. Specifically, we propose a hierarchical recurrent neural network model to read a whole paragraph at a time and jointly learn representations for all the clauses in the paragraph by extensively modeling context influences and inter-dependencies of clauses. Experimental results show that our model achieves the state-of-the-art performance for clause-level situation entity classification on the genre-rich MASC+Wiki corpus, which approaches human-level performance. |
| Tasks | |
| Published | 2018-09-20 |
| URL | http://arxiv.org/abs/1809.07483v1 |
| http://arxiv.org/pdf/1809.07483v1.pdf | |
| PWC | https://paperswithcode.com/paper/building-context-aware-clause-representations |
| Repo | |
| Framework | |
Gaussian Material Synthesis
| Title | Gaussian Material Synthesis |
| Authors | Károly Zsolnai-Fehér, Peter Wonka, Michael Wimmer |
| Abstract | We present a learning-based system for rapid mass-scale material synthesis that is useful for novice and expert users alike. The user preferences are learned via Gaussian Process Regression and can be easily sampled for new recommendations. Typically, each recommendation takes 40-60 seconds to render with global illumination, which makes this process impracticable for real-world workflows. Our neural network eliminates this bottleneck by providing high-quality image predictions in real time, after which it is possible to pick the desired materials from a gallery and assign them to a scene in an intuitive manner. Workflow timings against Disney’s “principled” shader reveal that our system scales well with the number of sought materials, thus empowering even novice users to generate hundreds of high-quality material models without any expertise in material modeling. Similarly, expert users experience a significant decrease in the total modeling time when populating a scene with materials. Furthermore, our proposed solution also offers controllable recommendations and a novel latent space variant generation step to enable the real-time fine-tuning of materials without requiring any domain expertise. |
| Tasks | |
| Published | 2018-04-23 |
| URL | http://arxiv.org/abs/1804.08369v1 |
| http://arxiv.org/pdf/1804.08369v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-material-synthesis |
| Repo | |
| Framework | |
