May 5, 2019

3058 words 15 mins read

Paper Group ANR 539

Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach. Knowledge Extraction and Knowledge Integration governed by Łukasiewicz Logics. A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure. Mitochondria-based Renal Cell Carcinoma Subtyping: Learni …

Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach


Title	Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach
Authors	Lin Wu, Chunhua Shen, Anton van den Hengel
Abstract	In this paper, we present an end-to-end approach to simultaneously learn spatio-temporal features and corresponding similarity metric for video-based person re-identification. Given the video sequence of a person, features from each frame that are extracted from all levels of a deep convolutional network can preserve a higher spatial resolution from which we can model finer motion patterns. These low-level visual percepts are leveraged into a variant of recurrent model to characterize the temporal variation between time-steps. Features from all time-steps are then summarized using temporal pooling to produce an overall feature representation for the complete sequence. The deep convolutional network, recurrent layer, and the temporal pooling are jointly trained to extract comparable hidden-unit representations from input pair of time series to compute their corresponding similarity value. The proposed framework combines time series modeling and metric learning to jointly learn relevant features and a good similarity measure between time sequences of person. Experiments demonstrate that our approach achieves the state-of-the-art performance for video-based person re-identification on iLIDS-VID and PRID 2011, the two primary public datasets for this purpose.
Tasks	Metric Learning, Person Re-Identification, Time Series, Video-Based Person Re-Identification
Published	2016-06-06
URL	http://arxiv.org/abs/1606.01609v2
PDF	http://arxiv.org/pdf/1606.01609v2.pdf
PWC	https://paperswithcode.com/paper/deep-recurrent-convolutional-networks-for
Repo
Framework

Knowledge Extraction and Knowledge Integration governed by Łukasiewicz Logics


Title	Knowledge Extraction and Knowledge Integration governed by Łukasiewicz Logics
Authors	Carlos Leandro
Abstract	The development of machine learning in particular and artificial intelligent in general has been strongly conditioned by the lack of an appropriate interface layer between deduction, abduction and induction. In this work we extend traditional algebraic specification methods in this direction. Here we assume that such interface for AI emerges from an adequate Neural-Symbolic integration. This integration is made for universe of discourse described on a Topos governed by a many-valued {\L}ukasiewicz logic. Sentences are integrated in a symbolic knowledge base describing the problem domain, codified using a graphic-based language, wherein every logic connective is defined by a neuron in an artificial network. This allows the integration of first-order formulas into a network architecture as background knowledge, and simplifies symbolic rule extraction from trained networks. For the train of such neural networks we changed the Levenderg-Marquardt algorithm, restricting the knowledge dissemination in the network structure using soft crystallization. This procedure reduces neural network plasticity without drastically damaging the learning performance, allowing the emergence of symbolic patterns. This makes the descriptive power of produced neural networks similar to the descriptive power of {\L}ukasiewicz logic language, reducing the information lost on translation between symbolic and connectionist structures. We tested this method on the extraction of knowledge from specified structures. For it, we present the notion of fuzzy state automata, and we use automata behaviour to infer its structure. We use this type of automata on the generation of models for relations specified as symbolic background knowledge.
Tasks
Published	2016-04-11
URL	http://arxiv.org/abs/1604.02780v1
PDF	http://arxiv.org/pdf/1604.02780v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-extraction-and-knowledge
Repo
Framework

A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure


Title	A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure
Authors	Peter Schulam, Suchi Saria
Abstract	For many complex diseases, there is a wide variety of ways in which an individual can manifest the disease. The challenge of personalized medicine is to develop tools that can accurately predict the trajectory of an individual’s disease, which can in turn enable clinicians to optimize treatments. We represent an individual’s disease trajectory as a continuous-valued continuous-time function describing the severity of the disease over time. We propose a hierarchical latent variable model that individualizes predictions of disease trajectories. This model shares statistical strength across observations at different resolutions–the population, subpopulation and the individual level. We describe an algorithm for learning population and subpopulation parameters offline, and an online procedure for dynamically learning individual-specific parameters. Finally, we validate our model on the task of predicting the course of interstitial lung disease, a leading cause of death among patients with the autoimmune disease scleroderma. We compare our approach against state-of-the-art and demonstrate significant improvements in predictive accuracy.
Tasks
Published	2016-01-18
URL	http://arxiv.org/abs/1601.04674v2
PDF	http://arxiv.org/pdf/1601.04674v2.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-individualizing-predictions
Repo
Framework

Mitochondria-based Renal Cell Carcinoma Subtyping: Learning from Deep vs. Flat Feature Representations


Title	Mitochondria-based Renal Cell Carcinoma Subtyping: Learning from Deep vs. Flat Feature Representations
Authors	Peter J. Schüffler, Judy Sarungbam, Hassan Muhammad, Ed Reznik, Satish K. Tickoo, Thomas J. Fuchs
Abstract	Accurate subtyping of renal cell carcinoma (RCC) is of crucial importance for understanding disease progression and for making informed treatment decisions. New discoveries of significant alterations to mitochondria between subtypes make immunohistochemical (IHC) staining based image classification an imperative. Until now, accurate quantification and subtyping was made impossible by huge IHC variations, the absence of cell membrane staining for cytoplasm segmentation as well as the complete lack of systems for robust and reproducible image based classification. In this paper we present a comprehensive classification framework to overcome these challenges for tissue microarrays (TMA) of RCCs. We compare and evaluate models based on domain specific hand-crafted “flat”-features versus “deep” feature representations from various layers of a pre-trained convolutional neural network (CNN). The best model reaches a cross-validation accuracy of 89%, which demonstrates for the first time, that robust mitochondria-based subtyping of renal cancer is feasible
Tasks	Image Classification
Published	2016-08-02
URL	http://arxiv.org/abs/1608.00842v1
PDF	http://arxiv.org/pdf/1608.00842v1.pdf
PWC	https://paperswithcode.com/paper/mitochondria-based-renal-cell-carcinoma
Repo
Framework

Reasoning and Algorithm Selection Augmented Symbolic Segmentation


Title	Reasoning and Algorithm Selection Augmented Symbolic Segmentation
Authors	Martin Lukac, Kamila Abdiyeva, Michitaka Kameyama
Abstract	In this paper we present an alternative method to symbolic segmentation: we approach symbolic segmentation as an algorithm selection problem. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input features $F$, a set of image attribute $\mathbb{A}$ and a selection mechanism $S(F,\mathbb{A},A)$ that selects on a case by case basis the best algorithm. The semantic segmentation is then an optimization process that combines best component segments from multiple results into a single optimal result. The experiments compare three different algorithm selection mechanisms using three selected semantic segmentation algorithms. The results show that using the current state of art algorithms and relatively low accuracy of algorithm selection the accuracy of the semantic segmentation can be improved by 2%.
Tasks	Semantic Segmentation
Published	2016-08-12
URL	http://arxiv.org/abs/1608.03667v1
PDF	http://arxiv.org/pdf/1608.03667v1.pdf
PWC	https://paperswithcode.com/paper/reasoning-and-algorithm-selection-augmented
Repo
Framework

DAP3D-Net: Where, What and How Actions Occur in Videos?


Title	DAP3D-Net: Where, What and How Actions Occur in Videos?
Authors	Li Liu, Yi Zhou, Ling Shao
Abstract	Action parsing in videos with complex scenes is an interesting but challenging task in computer vision. In this paper, we propose a generic 3D convolutional neural network in a multi-task learning manner for effective Deep Action Parsing (DAP3D-Net) in videos. Particularly, in the training phase, action localization, classification and attributes learning can be jointly optimized on our appearancemotion data via DAP3D-Net. For an upcoming test video, we can describe each individual action in the video simultaneously as: Where the action occurs, What the action is and How the action is performed. To well demonstrate the effectiveness of the proposed DAP3D-Net, we also contribute a new Numerous-category Aligned Synthetic Action dataset, i.e., NASA, which consists of 200; 000 action clips of more than 300 categories and with 33 pre-defined action attributes in two hierarchical levels (i.e., low-level attributes of basic body part movements and high-level attributes related to action motion). We learn DAP3D-Net using the NASA dataset and then evaluate it on our collected Human Action Understanding (HAU) dataset. Experimental results show that our approach can accurately localize, categorize and describe multiple actions in realistic videos.
Tasks	Action Localization, Action Parsing, Multi-Task Learning
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03346v1
PDF	http://arxiv.org/pdf/1602.03346v1.pdf
PWC	https://paperswithcode.com/paper/dap3d-net-where-what-and-how-actions-occur-in
Repo
Framework

Principal Polynomial Analysis


Title	Principal Polynomial Analysis
Authors	Valero Laparra, Sandra Jiménez, Devis Tuia, Gustau Camps-Valls, Jesús Malo
Abstract	This paper presents a new framework for manifold learning based on a sequence of principal polynomials that capture the possibly nonlinear nature of the data. The proposed Principal Polynomial Analysis (PPA) generalizes PCA by modeling the directions of maximal variance by means of curves, instead of straight lines. Contrarily to previous approaches, PPA reduces to performing simple univariate regressions, which makes it computationally feasible and robust. Moreover, PPA shows a number of interesting analytical properties. First, PPA is a volume-preserving map, which in turn guarantees the existence of the inverse. Second, such an inverse can be obtained in closed form. Invertibility is an important advantage over other learning methods, because it permits to understand the identified features in the input domain where the data has physical meaning. Moreover, it allows to evaluate the performance of dimensionality reduction in sensible (input-domain) units. Volume preservation also allows an easy computation of information theoretic quantities, such as the reduction in multi-information after the transform. Third, the analytical nature of PPA leads to a clear geometrical interpretation of the manifold: it allows the computation of Frenet-Serret frames (local features) and of generalized curvatures at any point of the space. And fourth, the analytical Jacobian allows the computation of the metric induced by the data, thus generalizing the Mahalanobis distance. These properties are demonstrated theoretically and illustrated experimentally. The performance of PPA is evaluated in dimensionality and redundancy reduction, in both synthetic and real datasets from the UCI repository.
Tasks	Dimensionality Reduction
Published	2016-01-31
URL	http://arxiv.org/abs/1602.00221v1
PDF	http://arxiv.org/pdf/1602.00221v1.pdf
PWC	https://paperswithcode.com/paper/principal-polynomial-analysis
Repo
Framework

Change-point Detection Methods for Body-Worn Video


Title	Change-point Detection Methods for Body-Worn Video
Authors	Stephanie Allen, David Madras, Ye Ye, Greg Zanotti
Abstract	Body-worn video (BWV) cameras are increasingly utilized by police departments to provide a record of police-public interactions. However, large-scale BWV deployment produces terabytes of data per week, necessitating the development of effective computational methods to identify salient changes in video. In work carried out at the 2016 RIPS program at IPAM, UCLA, we present a novel two-stage framework for video change-point detection. First, we employ state-of-the-art machine learning methods including convolutional neural networks and support vector machines for scene classification. We then develop and compare change-point detection algorithms utilizing mean squared-error minimization, forecasting methods, hidden Markov models, and maximum likelihood estimation to identify noteworthy changes. We test our framework on detection of vehicle exits and entrances in a BWV data set provided by the Los Angeles Police Department and achieve over 90% recall and nearly 70% precision – demonstrating robustness to rapid scene changes, extreme luminance differences, and frequent camera occlusions.
Tasks	Change Point Detection, Scene Classification
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06453v1
PDF	http://arxiv.org/pdf/1610.06453v1.pdf
PWC	https://paperswithcode.com/paper/change-point-detection-methods-for-body-worn
Repo
Framework

Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach


Title	Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach
Authors	Prashant Khanduri, Bhavya Kailkhura, Jayaraman J. Thiagarajan, Pramod K. Varshney
Abstract	This paper considers the problem of high dimensional signal detection in a large distributed network whose nodes can collaborate with their one-hop neighboring nodes (spatial collaboration). We assume that only a small subset of nodes communicate with the Fusion Center (FC). We design optimal collaboration strategies which are universal for a class of deterministic signals. By establishing the equivalence between the collaboration strategy design problem and sparse PCA, we solve the problem efficiently and evaluate the impact of collaboration on detection performance.
Tasks	Sparse Learning
Published	2016-01-22
URL	http://arxiv.org/abs/1601.06201v2
PDF	http://arxiv.org/pdf/1601.06201v2.pdf
PWC	https://paperswithcode.com/paper/universal-collaboration-strategies-for-signal
Repo
Framework

Model-Free Imitation Learning with Policy Optimization


Title	Model-Free Imitation Learning with Policy Optimization
Authors	Jonathan Ho, Jayesh K. Gupta, Stefano Ermon
Abstract	In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or reinforcement learning problems. Such algorithms are therefore not directly applicable to large, high-dimensional environments, and their performance can significantly degrade if the planning problems are not solved to optimality. Under the apprenticeship learning formalism, we develop alternative model-free algorithms for finding a parameterized stochastic policy that performs at least as well as an expert policy on an unknown cost function, based on sample trajectories from the expert. Our approach, based on policy gradients, scales to large continuous environments with guaranteed convergence to local minima.
Tasks	Imitation Learning
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08478v1
PDF	http://arxiv.org/pdf/1605.08478v1.pdf
PWC	https://paperswithcode.com/paper/model-free-imitation-learning-with-policy
Repo
Framework

Mining of health and disease events on Twitter: validating search protocols within the setting of Indonesia


Title	Mining of health and disease events on Twitter: validating search protocols within the setting of Indonesia
Authors	Aditya L. Ramadona, Rendra Agusta, Sulistyawati, Lutfan Lazuardi, Anwar D. Cahyono, Åsa Holmner, Fatwa S. T. Dewi, Hari Kusnanto, Joacim Röcklov
Abstract	This study seeks to validate a search protocol of ill health-related terms using Twitter data which can later be used to understand if, and how, Twitter can reveal information on the current health situation. We extracted conversations related to health and disease postings on Twitter using a set of pre-defined keywords, assessed the prevalence, frequency, and timing of such content in these conversations, and validated how this search protocol was able to detect relevant disease tweets. Classification and Regression Trees (CART) algorithm was used to train and test search protocols of disease and health hits comparing to those identified by our team. The accuracy of predictions showed a good validity with AUC beyond 0.8. Our study shows that monitoring of public sentiment on Twitter can be used as a real-time proxy for health events.
Tasks
Published	2016-08-21
URL	http://arxiv.org/abs/1608.05910v2
PDF	http://arxiv.org/pdf/1608.05910v2.pdf
PWC	https://paperswithcode.com/paper/mining-of-health-and-disease-events-on
Repo
Framework

Structural Correspondence Learning for Cross-lingual Sentiment Classification with One-to-many Mappings


Title	Structural Correspondence Learning for Cross-lingual Sentiment Classification with One-to-many Mappings
Authors	Nana Li, Shuangfei Zhai, Zhongfei Zhang, Boying Liu
Abstract	Structural correspondence learning (SCL) is an effective method for cross-lingual sentiment classification. This approach uses unlabeled documents along with a word translation oracle to automatically induce task specific, cross-lingual correspondences. It transfers knowledge through identifying important features, i.e., pivot features. For simplicity, however, it assumes that the word translation oracle maps each pivot feature in source language to exactly only one word in target language. This one-to-one mapping between words in different languages is too strict. Also the context is not considered at all. In this paper, we propose a cross-lingual SCL based on distributed representation of words; it can learn meaningful one-to-many mappings for pivot words using large amounts of monolingual data and a small dictionary. We conduct experiments on NLP&CC 2013 cross-lingual sentiment analysis dataset, employing English as source language, and Chinese as target language. Our method does not rely on the parallel corpora and the experimental results show that our approach is more competitive than the state-of-the-art methods in cross-lingual sentiment classification.
Tasks	Sentiment Analysis
Published	2016-11-26
URL	http://arxiv.org/abs/1611.08737v1
PDF	http://arxiv.org/pdf/1611.08737v1.pdf
PWC	https://paperswithcode.com/paper/structural-correspondence-learning-for-cross
Repo
Framework

MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification


Title	MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
Authors	Daoyu Lin, Kun Fu, Yang Wang, Guangluan Xu, Xian Sun
Abstract	With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks (CNNs). However, due to the limited amount of labeled data available, supervised learning is often difficult to carry out. Therefore, we proposed an unsupervised model called multiple-layer feature-matching generative adversarial networks (MARTA GANs) to learn a representation using only unlabeled data. MARTA GANs consists of both a generative model $G$ and a discriminative model $D$. We treat $D$ as a feature extractor. To fit the complex properties of remote sensing data, we use a fusion layer to merge the mid-level and global features. $G$ can produce numerous images that are similar to the training data; therefore, $D$ can learn better representations of remotely sensed images using the training data provided by $G$. The classification results on two widely used remote sensing image databases show that the proposed method significantly improves the classification performance compared with other state-of-the-art methods.
Tasks	Image Classification, Remote Sensing Image Classification, Representation Learning, Unsupervised Representation Learning
Published	2016-12-28
URL	http://arxiv.org/abs/1612.08879v3
PDF	http://arxiv.org/pdf/1612.08879v3.pdf
PWC	https://paperswithcode.com/paper/marta-gans-unsupervised-representation
Repo
Framework

Weakly-Supervised Semantic Segmentation using Motion Cues


Title	Weakly-Supervised Semantic Segmentation using Motion Cues
Authors	Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
Abstract	Fully convolutional neural networks (FCNNs) trained on a large number of images with strong pixel-level annotations have become the new state of the art for the semantic segmentation task. While there have been recent attempts to learn FCNNs from image-level weak annotations, they need additional constraints, such as the size of an object, to obtain reasonable performance. To address this issue, we present motion-CNN (M-CNN), a novel FCNN framework which incorporates motion cues and is learned from video-level weak annotations. Our learning scheme to train the network uses motion segments as soft constraints, thereby handling noisy motion information. When trained on weakly-annotated videos, our method outperforms the state-of-the-art EM-Adapt approach on the PASCAL VOC 2012 image segmentation benchmark. We also demonstrate that the performance of M-CNN learned with 150 weak video annotations is on par with state-of-the-art weakly-supervised methods trained with thousands of images. Finally, M-CNN substantially outperforms recent approaches in a related task of video co-localization on the YouTube-Objects dataset.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2016-03-23
URL	http://arxiv.org/abs/1603.07188v3
PDF	http://arxiv.org/pdf/1603.07188v3.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-semantic-segmentation-using
Repo
Framework

Big Data analytics. Three use cases with R, Python and Spark


Title	Big Data analytics. Three use cases with R, Python and Spark
Authors	Philippe Besse, Brendan Guillouet, Jean-Michel Loubes
Abstract	Management and analysis of big data are systematically associated with a data distributed architecture in the Hadoop and now Spark frameworks. This article offers an introduction for statisticians to these technologies by comparing the performance obtained by the direct use of three reference environments: R, Python Scikit-learn, Spark MLlib on three public use cases: character recognition, recommending films, categorizing products. As main result, it appears that, if Spark is very efficient for data munging and recommendation by collaborative filtering (non-negative factorization), current implementations of conventional learning methods (logistic regression, random forests) in MLlib or SparkML do not ou poorly compete habitual use of these methods (R, Python Scikit-learn) in an integrated or undistributed architecture
Tasks
Published	2016-09-30
URL	http://arxiv.org/abs/1609.09619v1
PDF	http://arxiv.org/pdf/1609.09619v1.pdf
PWC	https://paperswithcode.com/paper/big-data-analytics-three-use-cases-with-r
Repo
Framework